SlideShare a Scribd company logo
1 of 26
Download to read offline
Copyright © 2017 PATHPARTNER TECHNOLOGY 1
Approaches for Vision-based
Driver Monitoring
Jayachandra Dakala
May 2017
Copyright © 2017 PATHPARTNER TECHNOLOGY 2
• Inattention – Distraction and Drowsiness
• Vision-based DMS – Overview and Scope
• Detection vs. Classification – CNN vs. Boosted Cascades
• Drowsiness from Eye
• Optimization on PC
• Summary
Outline
Copyright © 2017 PATHPARTNER TECHNOLOGY 3
Distraction & Drowsiness
Comprehending
Environment
Decision
Making
Taking
Action
Driving
Symptoms of Fatigue
Repeated yawning / Lazy steering
Slower reaction and responses
Nodding off at the wheel
Day dreaming
Difficulty keeping eyes open and
burning sensation in the eye
Vehicle wandering from the road or
into another lane
Visual
distraction
Auditory
distraction
Cognitive
distraction
Biomechanical
distraction
Types of Distraction (acc. To NHTSA)
Copyright © 2017 PATHPARTNER TECHNOLOGY 4
• Visual cues
• Eyes-off-road duration
• Head-off-road duration
• Texting / Talking over phone
• Eye closure, eye blink, PERCLOS
• Yawning, nodding
• Standard deviation of lane position
Distraction and Drowsiness
Copyright © 2017 PATHPARTNER TECHNOLOGY 5
Vision-based DMS
Driver Monitoring System
Drowsiness Distraction Driving behaviourEmotions Personalization
YawningEye closure,
Eye openness,
Pupil dilation,
Eye blink
frequency
Nodding off
&
Head down
Looking
elsewhere!
Talking over
phone,
Texting, etc.
Anger,
Stress,
Pain, etc.
Steering angle,
Acceleration &
Break,
(OBD data in
general)
Recognition &
Personalized
learning
Copyright © 2017 PATHPARTNER TECHNOLOGY 6
Core vision technologies needed!
Eye
Measurements
Face and
Landmark
Detector
Eye Gaze
3D Face Pose
Facial Expression
Face Recognition
Copyright © 2017 PATHPARTNER TECHNOLOGY 7
Cascaded detector
All
image
patches
Detected
faces
Rejected non-face
patches
Weak classifier
Classification score
Copyright © 2017 PATHPARTNER TECHNOLOGY 8
Choice of weak classifier
Decision stumps on
• Multiscale Haar-like features
• Multiscale Local Binary Patterns
Decision trees on
• Pixel differences: (p1-p2)
• Normalized pixel differences (NPD): (p1-p2)/(p1+p2)
• These features use
averaging over an area of
the image!
• Susceptible to occlusions
and alignment!
• Needs many cascades to
cover all face poses!
Single cascade could handle
multiple poses, better at
handling occlusions!
Copyright © 2017 PATHPARTNER TECHNOLOGY 9
Multi-task Cascaded Detector
All
image
patches
Detected
faces with
landmarks
& pose
Rejected non-face
patches
Incremental detection score, shape update, pose update!
Multi-task Classification / Regression tree
Copyright © 2017 PATHPARTNER TECHNOLOGY 10
CNNs for Detection
Image Multiscale linear search Selective search
• RCNN-like methods
• Region Proposal + Region evaluation = Region Inference
• Region Proposal
• Multiscale Linear search
• Selective search
• CNN based Region Proposal network
Copyright © 2017 PATHPARTNER TECHNOLOGY 11
• Motivation: Let the CNN do the search
• Pros: Fast, One-pass inference
• Cons:
• Chance of mis-aligned face bbox, sensitive to Ground truth preparation
• High false positive rate
• Needs effective search and NMS method
• Model: AlexNet trained as a face/no-face classifier
• Method:
• Fine-tune AlexNet with Face/No face patches
• Perform Network surgery, convert fc6, fc7 and fc8 to convolutional layers
• Pass multiscale images to network, obtain heatmap for each scale
• Obtain candidate Bounding boxes by thresholding heatmap
• Perform NMS to obtain final bbox
Deep Dense CNNs
Required “Depth”
of CNNs can still
make it difficult on
embedded
systems!
Copyright © 2017 PATHPARTNER TECHNOLOGY 12
• For RCNN-like models and Dense detection, AlexNet was fine-tuned on
AFLW dataset (~24 k images, 65 k faces)
• Obtained 100 k face images, 240 k non-face images by GT bounding box
jittering
• Model evaluation on FDDB dataset (~2800 images, ~5 k faces)
• Evaluation metric: IoU > 50%
Experiments / Results
Copyright © 2017 PATHPARTNER TECHNOLOGY 13
Experiments / Results (on TitanX Pascal) on FDDB
* For one set of scale factor (1.3) and step size (32)!
** Selective search with 2400 regions
*** For faces of size > 64x64
FD Method Accuracy False
positives
Time
RCNN Linear search* 66.03% 1806 14.04 sec
Selective
search**
64.55% 1100 7.52 sec
Deep
dense
NMS-Max 74.03% 2808 1.3 sec
NMS-Avg 81.23% 1564 1.67 sec
NPD
Cascade
Linear search 72.24%,
95.68%***
500 ~40 ms on PC
Copyright © 2017 PATHPARTNER TECHNOLOGY 14
Hence, we say…
Eye
Measurements
Face and
Landmark
Detector
Eye Gaze
3D Face Pose
Facial Expression
Face Recognition
• Use boosted multi-task cascades for
detecting correlated tasks
Ex: Face, landmarks, and face pose detection
• Use CNNs for one-shot inference of a
given patch
Ex: Eye state analysis, facial expression, etc.,
on detected faces
Copyright © 2017 PATHPARTNER TECHNOLOGY 15
• Drowsiness is reflected in PERCLOS, eye blink variations
• Eye openness is specific to each person
• Challenging to differentiate partially open eyes, closed eyes, and the
person specific eye openness
Drowsiness from Eye
Copyright © 2017 PATHPARTNER TECHNOLOGY 16
• Trained as a patch classifier, i.e., Open-eye vs. Closed-eye vs. No-Eye inference
• Total 0.75 million parameters, 80 times smaller than AlexNet
EyeNet
Copyright © 2017 PATHPARTNER TECHNOLOGY 17
• Motivation
• Make model robust to mis-aligned query patch
• Extract meta-data from class-conditioned filters learned in EyeNet
• Perform Network surgery on EyeNet
• Transform weights of FC5 into 9x5 Convolution, FC6 and FC7 to 1x1
convolutions
• Perform Hole Transform (Atrous algorithm) on Conv2, Conv3 and Conv4
• Model desensitized to Facial effects, eyebrows, and spectacles by Hard-negative
mining during training
• Takes ~15 ms on CPU for a patch of 60x40
EyeNet for Dense Prediction
Copyright © 2017 PATHPARTNER TECHNOLOGY 18
EyeNet for Dense prediction
Sample heatmaps
Copyright © 2017 PATHPARTNER TECHNOLOGY 19
• Model works well on a conservative eye crop, independent of
template size
• The saliency maps, “heatmaps” generated indicate the model’s
confidence that each pixel belongs to the target classes
• Meta-data useful to drowsiness detection encapsulated in the
distribution of the dense confidence scores
EyeNet for Dense prediction
Copyright © 2017 PATHPARTNER TECHNOLOGY 20
Optimization of Multi-task Cascaded Detector
Parallelize “one” tree
for “n” patches!
Parallelize “n” trees
for “one” patch!
Parallelize “n” trees
for “m” patches!
0
20
40
60
80
100
120
1
19
37
55
73
91
109
127
145
163
181
199
217
235
253
271
289
307
325
343
361
379
397
415
433
451
469
487
505
523
Cumulative rejection rate after every tree!
• Using SIMD implementation and 3 cores of an Intel i7, gives ~25 fps for
VGA (640x480)
Tree number
%ofrejections
Copyright © 2017 PATHPARTNER TECHNOLOGY 21
• With minimal system delay, parallelize multi-task Cascade Detector and
the Dense Eyenet
• We could get real time performance on 4-core intel i7 for VGA
• Parallelizing between DSP and EVEs, and with SIMD on EVE, we
forecast real-time performance on TI’s TDA2x
Optimization of Overall System
Copyright © 2017 PATHPARTNER TECHNOLOGY 22
• Group correlated tasks together to learn multi-task cascades
• Use multi-task cascades for computationally intensive detection problems
• Use negative patch rejection statistics to optimize multi-task cascades
• Use CNNs for dense prediction from a coarsely cropped patches
Summary
Copyright © 2017 PATHPARTNER TECHNOLOGY 23
• Y. Dong, Z. Hu, K. Uchimura and N. Murayama, “Driver Inattention Monitoring System for Intelligent
Vehicles: A Review,” in IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 2, pp. 596-
614, June 2011.
• S. Liao, A. K. Jain and S. Z. Li, “A Fast and Accurate Unconstrained Face Detector,” in IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 211-223, Feb. 1 2016.
• D. Chen, S. Ren, Y. Wei, X. Cao, and J. Sun, “Joint cascade face detection and alignment,” in European
Conference on Computer Vision, 2014.
• Cao, X., Wei, Y., Wen, F., Sun, J.: Face Alignment by Explicit Shape Regression. In: Computer Vision and
Pattern Recognition (2012).
• Sachin Sudhakar Farfade, Mohammad J. Saberian, and Li-Jia Li. 2015. Multi-view Face Detection Using
Deep Convolutional Neural Networks. In ICMR 2015.
• L.C. Chen, G Papandreou, I Kokkinos, K. Murphy, A. Yuille, “Semantic Segmentation with Deep
Convolutional Neural Networks, atrous Convolutions and Fully Connected CRFs,” ICLR 2015.
• F. Yu, V. Koltun, “Multiscale Context Aggregation by Dilated Convolutions,” ICLR 2016.
Resource Slide
Copyright © 2017 PATHPARTNER TECHNOLOGY 24
PathPartner is a top notch design engineering services company and works with several
semiconductor companies, OEMs and ODMs in embedded media-centric devices and
intelligent systems
About PathPartner
• Incorporated in July 2006 HQ in
Bangalore, India
• R&D Centers: Bangalore, India and
California, USA
• Marketing representatives in USA,
Japan and India
• PathPartner is a member of
Embedded Vision Alliance, GENIVI
and CARCONNECTIVITY consortium
• Semiconductor Companies
• OEMs and ODMs
• Camera Sensor Integration &
Image Quality Tuning
• Device Drivers, BSP & OS
integration
• Embedded Vision
• Multimedia Codecs & Middleware
• Algorithm Optimization
• Present company strength is ~250
• Grown at 40% in 2015-16
Copyright © 2017 PATHPARTNER TECHNOLOGY 25
PathPartner Technology Pvt.Ltd.
#16, PSS Plaza, 1st and 2nd Floor,
New Thippasandra Main Road,
HAL III Stage, Bangalore-560075
Contact Us
+91 80 6772 2000 | +1 408 242 7411 | +81 9055466819
sales.india@pathpartnertech.com | sales.usa@pathpartnertech.com | sales.japan@pathpartnertech.com
THANK YOU
Copyright © 2017 PATHPARTNER TECHNOLOGY 26
Questions?

More Related Content

What's hot

"Developing Real-time Video Applications with CoaXPress," A Presentation from...
"Developing Real-time Video Applications with CoaXPress," A Presentation from..."Developing Real-time Video Applications with CoaXPress," A Presentation from...
"Developing Real-time Video Applications with CoaXPress," A Presentation from...Edge AI and Vision Alliance
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...Edge AI and Vision Alliance
 
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...Edge AI and Vision Alliance
 
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy AnalyticsEdge AI and Vision Alliance
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecastsinside-BigData.com
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...Edge AI and Vision Alliance
 
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ..."Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...Edge AI and Vision Alliance
 
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from MovidiusEdge AI and Vision Alliance
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...Edge AI and Vision Alliance
 
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation..."Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...Edge AI and Vision Alliance
 
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde..."Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...Edge AI and Vision Alliance
 
An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)Julien SIMON
 
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...Edge AI and Vision Alliance
 
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P..."Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...Edge AI and Vision Alliance
 
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ..."Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...Edge AI and Vision Alliance
 
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a..."Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...Edge AI and Vision Alliance
 
Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309DrVictorFang
 
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision System
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision SystemHai Tao at AI Frontiers: Deep Learning For Embedded Vision System
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision SystemAI Frontiers
 
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present...
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present..."Machine Learning- based Image Compression: Ready for Prime Time?," a Present...
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present...Edge AI and Vision Alliance
 

What's hot (20)

"Developing Real-time Video Applications with CoaXPress," A Presentation from...
"Developing Real-time Video Applications with CoaXPress," A Presentation from..."Developing Real-time Video Applications with CoaXPress," A Presentation from...
"Developing Real-time Video Applications with CoaXPress," A Presentation from...
 
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from..."End to End Fire Detection Deep Neural Network Platform," a Presentation from...
"End to End Fire Detection Deep Neural Network Platform," a Presentation from...
 
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...
“A Practical Guide to Implementing ML on Embedded Devices,” a Presentation fr...
 
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
"The Path from ADAS to Autonomy," a Presentation from Strategy Analytics
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecasts
 
On-Device AI
On-Device AIOn-Device AI
On-Device AI
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
 
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ..."Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
"Collaboratively Benchmarking and Optimizing Deep Learning Implementations," ...
 
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius
"Dataflow: Where Power Budgets Are Won and Lost," a Presentation from Movidius
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation..."Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...
 
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde..."Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...
"Deep Learning Beyond Cats and Cars: Developing a Real-life DNN-based Embedde...
 
An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)
 
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
 
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P..."Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...
"Performing Multiple Perceptual Tasks With a Single Deep Neural Network," a P...
 
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ..."Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
 
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a..."Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
"Designing Vision Systems for Human Operators and Workflows: A Case Study," a...
 
Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309Video Analytics on Hadoop webinar victor fang-201309
Video Analytics on Hadoop webinar victor fang-201309
 
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision System
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision SystemHai Tao at AI Frontiers: Deep Learning For Embedded Vision System
Hai Tao at AI Frontiers: Deep Learning For Embedded Vision System
 
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present...
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present..."Machine Learning- based Image Compression: Ready for Prime Time?," a Present...
"Machine Learning- based Image Compression: Ready for Prime Time?," a Present...
 

Similar to "Approaches for Vision-based Driver Monitoring," a Presentation from PathPartner Technology

"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...
"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"..."How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...
"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...Edge AI and Vision Alliance
 
Biometric Recognition using Deep Learning
Biometric Recognition using Deep LearningBiometric Recognition using Deep Learning
Biometric Recognition using Deep LearningSahithiKotha2
 
Séminaire IA & VA- Yassine Ruichek, UTBM
Séminaire IA & VA- Yassine Ruichek, UTBMSéminaire IA & VA- Yassine Ruichek, UTBM
Séminaire IA & VA- Yassine Ruichek, UTBMMahdi Zarg Ayouna
 
Long-term Face Tracking in the Wild using Deep Learning
Long-term Face Tracking in the Wild using Deep LearningLong-term Face Tracking in the Wild using Deep Learning
Long-term Face Tracking in the Wild using Deep LearningElaheh Rashedi
 
Face Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural NetworksFace Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural NetworksElaheh Rashedi
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
AI and Machine Learning PG program
AI and Machine Learning PG programAI and Machine Learning PG program
AI and Machine Learning PG programMamathaSharma4
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningAli Alkan
 
Deep learning for understanding faces
Deep learning for understanding facesDeep learning for understanding faces
Deep learning for understanding facessieubebu
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...Edge AI and Vision Alliance
 
COMP 4010 - Lecture4 VR Technology - Visual and Haptic Displays
COMP 4010 - Lecture4 VR Technology - Visual and Haptic DisplaysCOMP 4010 - Lecture4 VR Technology - Visual and Haptic Displays
COMP 4010 - Lecture4 VR Technology - Visual and Haptic DisplaysMark Billinghurst
 
Face Recognition Techniques
Face Recognition TechniquesFace Recognition Techniques
Face Recognition TechniquesDaksh Verma
 
[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...NAVER D2
 
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptx
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptxReview A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptx
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptxAravindHari22
 
Xiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin Ren
 
TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019sipij
 
Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsPractical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsAlexey Rybakov
 
SCREENLESS DISPLAY.pptx
SCREENLESS DISPLAY.pptxSCREENLESS DISPLAY.pptx
SCREENLESS DISPLAY.pptxAlenJames14
 
Robotic design: Frontiers in visual and tactile sensing
Robotic design: Frontiers in visual and tactile sensingRobotic design: Frontiers in visual and tactile sensing
Robotic design: Frontiers in visual and tactile sensingDesign World
 
Nervana AI Overview Deck April 2016
Nervana AI Overview Deck April 2016Nervana AI Overview Deck April 2016
Nervana AI Overview Deck April 2016Sean Everett
 

Similar to "Approaches for Vision-based Driver Monitoring," a Presentation from PathPartner Technology (20)

"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...
"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"..."How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...
"How Image Sensor and Video Compression Parameters Impact Vision Algorithms,"...
 
Biometric Recognition using Deep Learning
Biometric Recognition using Deep LearningBiometric Recognition using Deep Learning
Biometric Recognition using Deep Learning
 
Séminaire IA & VA- Yassine Ruichek, UTBM
Séminaire IA & VA- Yassine Ruichek, UTBMSéminaire IA & VA- Yassine Ruichek, UTBM
Séminaire IA & VA- Yassine Ruichek, UTBM
 
Long-term Face Tracking in the Wild using Deep Learning
Long-term Face Tracking in the Wild using Deep LearningLong-term Face Tracking in the Wild using Deep Learning
Long-term Face Tracking in the Wild using Deep Learning
 
Face Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural NetworksFace Recognition Methods based on Convolutional Neural Networks
Face Recognition Methods based on Convolutional Neural Networks
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
AI and Machine Learning PG program
AI and Machine Learning PG programAI and Machine Learning PG program
AI and Machine Learning PG program
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
Deep learning for understanding faces
Deep learning for understanding facesDeep learning for understanding faces
Deep learning for understanding faces
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
 
COMP 4010 - Lecture4 VR Technology - Visual and Haptic Displays
COMP 4010 - Lecture4 VR Technology - Visual and Haptic DisplaysCOMP 4010 - Lecture4 VR Technology - Visual and Haptic Displays
COMP 4010 - Lecture4 VR Technology - Visual and Haptic Displays
 
Face Recognition Techniques
Face Recognition TechniquesFace Recognition Techniques
Face Recognition Techniques
 
[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...[212]big models without big data using domain specific deep networks in data-...
[212]big models without big data using domain specific deep networks in data-...
 
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptx
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptxReview A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptx
Review A DCNN APPROACH FOR REAL TIME UNCONSTRAINED FACE.pptx
 
Xiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCL
 
TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019TOP 5 Most View Article From Academia in 2019
TOP 5 Most View Article From Academia in 2019
 
Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and CarsPractical Artificial Intelligence: Deep Learning Beyond Cats and Cars
Practical Artificial Intelligence: Deep Learning Beyond Cats and Cars
 
SCREENLESS DISPLAY.pptx
SCREENLESS DISPLAY.pptxSCREENLESS DISPLAY.pptx
SCREENLESS DISPLAY.pptx
 
Robotic design: Frontiers in visual and tactile sensing
Robotic design: Frontiers in visual and tactile sensingRobotic design: Frontiers in visual and tactile sensing
Robotic design: Frontiers in visual and tactile sensing
 
Nervana AI Overview Deck April 2016
Nervana AI Overview Deck April 2016Nervana AI Overview Deck April 2016
Nervana AI Overview Deck April 2016
 

More from Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from SamsaraEdge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 

Recently uploaded

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 

Recently uploaded (20)

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 

"Approaches for Vision-based Driver Monitoring," a Presentation from PathPartner Technology

  • 1. Copyright © 2017 PATHPARTNER TECHNOLOGY 1 Approaches for Vision-based Driver Monitoring Jayachandra Dakala May 2017
  • 2. Copyright © 2017 PATHPARTNER TECHNOLOGY 2 • Inattention – Distraction and Drowsiness • Vision-based DMS – Overview and Scope • Detection vs. Classification – CNN vs. Boosted Cascades • Drowsiness from Eye • Optimization on PC • Summary Outline
  • 3. Copyright © 2017 PATHPARTNER TECHNOLOGY 3 Distraction & Drowsiness Comprehending Environment Decision Making Taking Action Driving Symptoms of Fatigue Repeated yawning / Lazy steering Slower reaction and responses Nodding off at the wheel Day dreaming Difficulty keeping eyes open and burning sensation in the eye Vehicle wandering from the road or into another lane Visual distraction Auditory distraction Cognitive distraction Biomechanical distraction Types of Distraction (acc. To NHTSA)
  • 4. Copyright © 2017 PATHPARTNER TECHNOLOGY 4 • Visual cues • Eyes-off-road duration • Head-off-road duration • Texting / Talking over phone • Eye closure, eye blink, PERCLOS • Yawning, nodding • Standard deviation of lane position Distraction and Drowsiness
  • 5. Copyright © 2017 PATHPARTNER TECHNOLOGY 5 Vision-based DMS Driver Monitoring System Drowsiness Distraction Driving behaviourEmotions Personalization YawningEye closure, Eye openness, Pupil dilation, Eye blink frequency Nodding off & Head down Looking elsewhere! Talking over phone, Texting, etc. Anger, Stress, Pain, etc. Steering angle, Acceleration & Break, (OBD data in general) Recognition & Personalized learning
  • 6. Copyright © 2017 PATHPARTNER TECHNOLOGY 6 Core vision technologies needed! Eye Measurements Face and Landmark Detector Eye Gaze 3D Face Pose Facial Expression Face Recognition
  • 7. Copyright © 2017 PATHPARTNER TECHNOLOGY 7 Cascaded detector All image patches Detected faces Rejected non-face patches Weak classifier Classification score
  • 8. Copyright © 2017 PATHPARTNER TECHNOLOGY 8 Choice of weak classifier Decision stumps on • Multiscale Haar-like features • Multiscale Local Binary Patterns Decision trees on • Pixel differences: (p1-p2) • Normalized pixel differences (NPD): (p1-p2)/(p1+p2) • These features use averaging over an area of the image! • Susceptible to occlusions and alignment! • Needs many cascades to cover all face poses! Single cascade could handle multiple poses, better at handling occlusions!
  • 9. Copyright © 2017 PATHPARTNER TECHNOLOGY 9 Multi-task Cascaded Detector All image patches Detected faces with landmarks & pose Rejected non-face patches Incremental detection score, shape update, pose update! Multi-task Classification / Regression tree
  • 10. Copyright © 2017 PATHPARTNER TECHNOLOGY 10 CNNs for Detection Image Multiscale linear search Selective search • RCNN-like methods • Region Proposal + Region evaluation = Region Inference • Region Proposal • Multiscale Linear search • Selective search • CNN based Region Proposal network
  • 11. Copyright © 2017 PATHPARTNER TECHNOLOGY 11 • Motivation: Let the CNN do the search • Pros: Fast, One-pass inference • Cons: • Chance of mis-aligned face bbox, sensitive to Ground truth preparation • High false positive rate • Needs effective search and NMS method • Model: AlexNet trained as a face/no-face classifier • Method: • Fine-tune AlexNet with Face/No face patches • Perform Network surgery, convert fc6, fc7 and fc8 to convolutional layers • Pass multiscale images to network, obtain heatmap for each scale • Obtain candidate Bounding boxes by thresholding heatmap • Perform NMS to obtain final bbox Deep Dense CNNs Required “Depth” of CNNs can still make it difficult on embedded systems!
  • 12. Copyright © 2017 PATHPARTNER TECHNOLOGY 12 • For RCNN-like models and Dense detection, AlexNet was fine-tuned on AFLW dataset (~24 k images, 65 k faces) • Obtained 100 k face images, 240 k non-face images by GT bounding box jittering • Model evaluation on FDDB dataset (~2800 images, ~5 k faces) • Evaluation metric: IoU > 50% Experiments / Results
  • 13. Copyright © 2017 PATHPARTNER TECHNOLOGY 13 Experiments / Results (on TitanX Pascal) on FDDB * For one set of scale factor (1.3) and step size (32)! ** Selective search with 2400 regions *** For faces of size > 64x64 FD Method Accuracy False positives Time RCNN Linear search* 66.03% 1806 14.04 sec Selective search** 64.55% 1100 7.52 sec Deep dense NMS-Max 74.03% 2808 1.3 sec NMS-Avg 81.23% 1564 1.67 sec NPD Cascade Linear search 72.24%, 95.68%*** 500 ~40 ms on PC
  • 14. Copyright © 2017 PATHPARTNER TECHNOLOGY 14 Hence, we say… Eye Measurements Face and Landmark Detector Eye Gaze 3D Face Pose Facial Expression Face Recognition • Use boosted multi-task cascades for detecting correlated tasks Ex: Face, landmarks, and face pose detection • Use CNNs for one-shot inference of a given patch Ex: Eye state analysis, facial expression, etc., on detected faces
  • 15. Copyright © 2017 PATHPARTNER TECHNOLOGY 15 • Drowsiness is reflected in PERCLOS, eye blink variations • Eye openness is specific to each person • Challenging to differentiate partially open eyes, closed eyes, and the person specific eye openness Drowsiness from Eye
  • 16. Copyright © 2017 PATHPARTNER TECHNOLOGY 16 • Trained as a patch classifier, i.e., Open-eye vs. Closed-eye vs. No-Eye inference • Total 0.75 million parameters, 80 times smaller than AlexNet EyeNet
  • 17. Copyright © 2017 PATHPARTNER TECHNOLOGY 17 • Motivation • Make model robust to mis-aligned query patch • Extract meta-data from class-conditioned filters learned in EyeNet • Perform Network surgery on EyeNet • Transform weights of FC5 into 9x5 Convolution, FC6 and FC7 to 1x1 convolutions • Perform Hole Transform (Atrous algorithm) on Conv2, Conv3 and Conv4 • Model desensitized to Facial effects, eyebrows, and spectacles by Hard-negative mining during training • Takes ~15 ms on CPU for a patch of 60x40 EyeNet for Dense Prediction
  • 18. Copyright © 2017 PATHPARTNER TECHNOLOGY 18 EyeNet for Dense prediction Sample heatmaps
  • 19. Copyright © 2017 PATHPARTNER TECHNOLOGY 19 • Model works well on a conservative eye crop, independent of template size • The saliency maps, “heatmaps” generated indicate the model’s confidence that each pixel belongs to the target classes • Meta-data useful to drowsiness detection encapsulated in the distribution of the dense confidence scores EyeNet for Dense prediction
  • 20. Copyright © 2017 PATHPARTNER TECHNOLOGY 20 Optimization of Multi-task Cascaded Detector Parallelize “one” tree for “n” patches! Parallelize “n” trees for “one” patch! Parallelize “n” trees for “m” patches! 0 20 40 60 80 100 120 1 19 37 55 73 91 109 127 145 163 181 199 217 235 253 271 289 307 325 343 361 379 397 415 433 451 469 487 505 523 Cumulative rejection rate after every tree! • Using SIMD implementation and 3 cores of an Intel i7, gives ~25 fps for VGA (640x480) Tree number %ofrejections
  • 21. Copyright © 2017 PATHPARTNER TECHNOLOGY 21 • With minimal system delay, parallelize multi-task Cascade Detector and the Dense Eyenet • We could get real time performance on 4-core intel i7 for VGA • Parallelizing between DSP and EVEs, and with SIMD on EVE, we forecast real-time performance on TI’s TDA2x Optimization of Overall System
  • 22. Copyright © 2017 PATHPARTNER TECHNOLOGY 22 • Group correlated tasks together to learn multi-task cascades • Use multi-task cascades for computationally intensive detection problems • Use negative patch rejection statistics to optimize multi-task cascades • Use CNNs for dense prediction from a coarsely cropped patches Summary
  • 23. Copyright © 2017 PATHPARTNER TECHNOLOGY 23 • Y. Dong, Z. Hu, K. Uchimura and N. Murayama, “Driver Inattention Monitoring System for Intelligent Vehicles: A Review,” in IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 2, pp. 596- 614, June 2011. • S. Liao, A. K. Jain and S. Z. Li, “A Fast and Accurate Unconstrained Face Detector,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 211-223, Feb. 1 2016. • D. Chen, S. Ren, Y. Wei, X. Cao, and J. Sun, “Joint cascade face detection and alignment,” in European Conference on Computer Vision, 2014. • Cao, X., Wei, Y., Wen, F., Sun, J.: Face Alignment by Explicit Shape Regression. In: Computer Vision and Pattern Recognition (2012). • Sachin Sudhakar Farfade, Mohammad J. Saberian, and Li-Jia Li. 2015. Multi-view Face Detection Using Deep Convolutional Neural Networks. In ICMR 2015. • L.C. Chen, G Papandreou, I Kokkinos, K. Murphy, A. Yuille, “Semantic Segmentation with Deep Convolutional Neural Networks, atrous Convolutions and Fully Connected CRFs,” ICLR 2015. • F. Yu, V. Koltun, “Multiscale Context Aggregation by Dilated Convolutions,” ICLR 2016. Resource Slide
  • 24. Copyright © 2017 PATHPARTNER TECHNOLOGY 24 PathPartner is a top notch design engineering services company and works with several semiconductor companies, OEMs and ODMs in embedded media-centric devices and intelligent systems About PathPartner • Incorporated in July 2006 HQ in Bangalore, India • R&D Centers: Bangalore, India and California, USA • Marketing representatives in USA, Japan and India • PathPartner is a member of Embedded Vision Alliance, GENIVI and CARCONNECTIVITY consortium • Semiconductor Companies • OEMs and ODMs • Camera Sensor Integration & Image Quality Tuning • Device Drivers, BSP & OS integration • Embedded Vision • Multimedia Codecs & Middleware • Algorithm Optimization • Present company strength is ~250 • Grown at 40% in 2015-16
  • 25. Copyright © 2017 PATHPARTNER TECHNOLOGY 25 PathPartner Technology Pvt.Ltd. #16, PSS Plaza, 1st and 2nd Floor, New Thippasandra Main Road, HAL III Stage, Bangalore-560075 Contact Us +91 80 6772 2000 | +1 408 242 7411 | +81 9055466819 sales.india@pathpartnertech.com | sales.usa@pathpartnertech.com | sales.japan@pathpartnertech.com THANK YOU
  • 26. Copyright © 2017 PATHPARTNER TECHNOLOGY 26 Questions?