SlideShare a Scribd company logo
1 of 28
Download to read offline
1
Minyoung Kim
May 1st, 2017
A Fast Object Detector for ADAS
Using Deep Learning
2
Panasonic Silicon Valley Laboratory
Silicon Valley Laboratory
(PSVL)
Cupertino, California
3
•  Pros
•  High performance
•  Beat state-of-the-art records in many tasks including image
classification and detection
•  Cons
•  Large set of database
•  High computational power
•  Deep Neural Networks with millions of parameters
•  Slower running time than most of conventional algorithms
Object Detection with Deep Learning
4
Tradeoffs
Speed vs. Accuracy
5
Object Detection System
Building Object Detection System
•  Training Deep Neural Network for Classification
•  Pedestrian detection: Binary classification
•  Object Proposal Generation at different scales
•  Generate box proposals (1000 ~ 2000 boxes)
•  Selective Search*, Edge Boxes**
•  Merge largely overlapping boxes
•  Non Maximum Suppression
* J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, A. W. M. Smeulders, IJCV 2013
** C. Lawrence Zitnick and Piotr Doll´ar, Microsoft Research
Run Recognizer
Proposal Generation
Recognition Network
Classification
Pedestrian
Background
Merge boxes
6
Time Consuming!
Proposal Generation & Scaling
•  Region proposal
•  Selective Search: 2 seconds per image (CPU)
•  Order of magnitude slower
•  Edge Boxes: 0.2 seconds per image
•  Scaling
•  Multiple forward propagations
•  Bottleneck
•  A forward propagation of an image
•  Less than 0.1 seconds (GPU)
Object Detection System
Proposal Generation
Scaling
7
PSVL Pedestrian Detection System
Our Pedestrian Detection System
INPUT
A Single Forward Propagation
OUTPUT
PSVL
Neural Detector
8
Recognition Network
Our Pedestrian Detection System
Add Regression Layer and Finetune
Fully Convolutional Network as Detector
Detection by a single forward propagation
9
Train DNN for recognition
•  GPU & Framework
•  NVIDIA Titan X, NVIDIA Tesla K80
•  Caffe*
•  Network Architectures
•  Modified GoogLeNet**
•  25~30 Convolutional layers
•  Input: Pedestrian and Backgrounds (80x32)
•  Output: Sigmoid or Softmax
•  Dataset
•  Caltech Pedestrian Detection Benchmark***
•  10 hours of 640(w) x 480(h) 30Hz video
•  About 250,000 frames with a total of
350,000 bounding boxes
Recognition Network
* http://caffe.berkeleyvision.org/
** C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed,
D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich (2014)
*** http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/
10
Convert recognition network to a fully convolutional network
Fully Convolutional Network
Base
Network
limited input size
Kernel sliding
Input size not limited
Fully connected Convolutional
11
Regression Layer
•  Regress bounding boxes on useful features
•  Nx4 box coordinates data
•  N: Feature Map resolution (NX x NY)
•  Original GT Box: B = [x1, y1, x2, y2]
•  New GT Box: B’ = rel(B) / m (m: multiplier of Window Size)
Fully Convolutional Network
240 120
m = 2
Output
Feature
Map
4
NX
NY
12
Training detector network
•  Network Architectures
•  Custom loss functions
•  Feature Map: Cross Entropy Loss with Boosting
•  Boosting
•  Ped: Correct Results (TPs) + Ground Truths (FNs)
•  True Positive if IOU > 0.5
•  False Negative if Ground Truths not detected
•  NonPed: FPs
•  False Positive if IOU < 0.5
•  Regression: Euclidean Loss with Feature Map Data incorporated
PSVL Neural Detector
+
640x480
Original
Images
Regression Layer
Fully
Convolutional
Network
Feature
Map
Box
Coord-
inates
13
More Data
PSVL Neural Detector
14
Even fewer box prediction with Center-Height features
PSVL Neural Detector
15
Performance – Very Fast with Competitive
Accuracy
•  From DeepCascade paper1)
•  DeepCascade: NVIDIA K20
•  15 fps
•  Ours: NVIDIA GTX770
•  34 fps
•  Speed Adjustment
•  34*0.96992) = 33 fps
•  Ours: NVIDIA Titan X
•  51.422 fps w/o cuDNN
•  85.565 fps with cuDNN4
(*): Left hand side for methods with unknown
fps or less than 0.2 fps
(**): DeepCascade without extra data
(***): SpatialPooling+/Katamari methods use
additional motion information
1) A. Angelova, A. Krizhevsky V. Vanhoucke, A. Ogale, D. Ferguson (2015)
2) http://caffe.berkeleyvision.org/performance_hardware.html
Performance of Pedestrian Detection Methods (Accuracy vs. Speed)
PSVL ND
(**)
(*)
(***)
Faster
Moreaccurate
16
Deploy PSVL ND on Google Nexus 9
•  Processor
•  NVIDIA Tegra K1
•  GPU: NVIDIA Kepler with 192 CUDA cores
•  Speed (without any optimization)
•  Base resolution (600x390): 5 fps
•  Lower resolution (280x240): 16 fps
ND on Portable Device
17
Threshold Information
Probability and NMS
Threshold Bar
Detection box with Probability
Toggle for Threshold Bar
ND Application
18
ND Application Demo (Cluster with Titan X)
19
ND Application Demo at ITSWC 2015
GTX980m Tegra K1
20
More Approaches
•  Faster-RCNN (2015)*
•  Region Proposal Network
•  +10 ms
•  Anchor boxes
•  Predicts offsets & confidences
Object Detection from others
* S. Ren, K. He, R. Girshick, J. Sun (NIPS 2015)
21
Object Detection from others
* J. Redmon, S. Divvala, R. Girshick, and A. Farhadi (CVPR 2016)
** J. Redmon and A. Farhadi (CVPR 2017)
•  YOLO9000 (2017)**
•  Improved localization/recall
•  (-) fully connected layer
Similar Approaches
•  YOLO (2016)*
•  Fully Convolutional Network
•  + fc layer + regression
22
OURS
* F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, K. Keutzer (arXiv:1602.07360)
PSVL Multiple-Object Detection System
•  Fire modules*
•  Only 13 MB size
•  16.5 fps on max scale (600x2200)
Performance
(Speed, Accuracy)
23
PSVL Multiple-Object Detection System
•  Only real-time demo at ITSWC 2016
•  30+ fps (2 views per GPU)
Demo at ITSWC 2016
24
OURS (DEMO)
25
PSVL Neural Tracker
•  Critical Risk Management by tracking nearby
objects (pedestrians, cars, cyclists)
•  arXiv:1609.09156
•  State-of-the-art on KITTI MOT
What’s Next?
( : weight sharing )
pairdata
datap
featp
datap
feat
ContrastiveLoss
NB
DIoU DArat
deconvI
reluA
reluI
deconvA
concat
concatp
26
PSVL Neural Tracker
27
Conclusion
Speed & Accuracy
No Separate Region Proposal
Network Size Optimization
28
Thank You!

More Related Content

What's hot

Ieee gold 2010 resta
Ieee gold 2010 restaIeee gold 2010 resta
Ieee gold 2010 restagrssieee
 
Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
Disaster Monitoring using Unmanned Aerial Vehicles and Deep LearningDisaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
Disaster Monitoring using Unmanned Aerial Vehicles and Deep LearningAndreas Kamilaris
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...KAIST
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...KAIST
 
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...Edge AI and Vision Alliance
 
Calit2 Technology Overview for New Channels for Bio Com
Calit2 Technology Overview for New Channels for Bio ComCalit2 Technology Overview for New Channels for Bio Com
Calit2 Technology Overview for New Channels for Bio ComMontana State University
 
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...KIMMINHA3
 
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...inside-BigData.com
 
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...Edge AI and Vision Alliance
 
Multi spectral imaging sensors
Multi spectral imaging sensorsMulti spectral imaging sensors
Multi spectral imaging sensorsLanrewaju ADETUNJI
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...University of Southern California
 
The World Wide Distributed Computing Architecture of the LHC Datagrid
The World Wide Distributed Computing Architecture of the LHC DatagridThe World Wide Distributed Computing Architecture of the LHC Datagrid
The World Wide Distributed Computing Architecture of the LHC DatagridSwiss Big Data User Group
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecastsinside-BigData.com
 
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...Nexgen Technology
 
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...South Tyrol Free Software Conference
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA Taiwan
 
Computing Just What You Need: Online Data Analysis and Reduction at Extreme ...
Computing Just What You Need: Online Data Analysis and Reduction  at Extreme ...Computing Just What You Need: Online Data Analysis and Reduction  at Extreme ...
Computing Just What You Need: Online Data Analysis and Reduction at Extreme ...Ian Foster
 
Science and Cyberinfrastructure in the Data-Dominated Era
Science and Cyberinfrastructure in the Data-Dominated EraScience and Cyberinfrastructure in the Data-Dominated Era
Science and Cyberinfrastructure in the Data-Dominated EraLarry Smarr
 

What's hot (20)

Ieee gold 2010 resta
Ieee gold 2010 restaIeee gold 2010 resta
Ieee gold 2010 resta
 
Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
Disaster Monitoring using Unmanned Aerial Vehicles and Deep LearningDisaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
 
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...
“Introduction to Simultaneous Localization and Mapping (SLAM),” a Presentatio...
 
Calit2 Technology Overview for New Channels for Bio Com
Calit2 Technology Overview for New Channels for Bio ComCalit2 Technology Overview for New Channels for Bio Com
Calit2 Technology Overview for New Channels for Bio Com
 
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
[CVPRW 2020]Real world Super-Resolution via Kernel Estimation and Noise Injec...
 
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
The Incorporation of Machine Learning into Scientific Simulations at Lawrence...
 
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...
“Efficient Deep Learning for 3D Point Cloud Understanding,” a Presentation fr...
 
Multi spectral imaging sensors
Multi spectral imaging sensorsMulti spectral imaging sensors
Multi spectral imaging sensors
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
 
The World Wide Distributed Computing Architecture of the LHC Datagrid
The World Wide Distributed Computing Architecture of the LHC DatagridThe World Wide Distributed Computing Architecture of the LHC Datagrid
The World Wide Distributed Computing Architecture of the LHC Datagrid
 
Machine Learning for Weather Forecasts
Machine Learning for Weather ForecastsMachine Learning for Weather Forecasts
Machine Learning for Weather Forecasts
 
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAME...
 
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...
SFScon21 - Roberto Confalonieri - Boyuan Sun - Hyper-spectral image classific...
 
Fine tuning a convolutional network for cultural event recognition
Fine tuning a convolutional network for cultural event recognitionFine tuning a convolutional network for cultural event recognition
Fine tuning a convolutional network for cultural event recognition
 
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digitsNVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
NVIDIA 深度學習教育機構 (DLI): Medical image segmentation using digits
 
Resume_optics_Gupta Roy
Resume_optics_Gupta RoyResume_optics_Gupta Roy
Resume_optics_Gupta Roy
 
Computing Just What You Need: Online Data Analysis and Reduction at Extreme ...
Computing Just What You Need: Online Data Analysis and Reduction  at Extreme ...Computing Just What You Need: Online Data Analysis and Reduction  at Extreme ...
Computing Just What You Need: Online Data Analysis and Reduction at Extreme ...
 
Science and Cyberinfrastructure in the Data-Dominated Era
Science and Cyberinfrastructure in the Data-Dominated EraScience and Cyberinfrastructure in the Data-Dominated Era
Science and Cyberinfrastructure in the Data-Dominated Era
 

Similar to "A Fast Object Detector for ADAS using Deep Learning," a Presentation from Panasonic

“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...Edge AI and Vision Alliance
 
PhD Thesis Proposal
PhD Thesis Proposal PhD Thesis Proposal
PhD Thesis Proposal Ziqiang Feng
 
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...Frederic Desprez
 
FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...Hiroki Nakahara
 
Object Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IObject Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IWanjin Yu
 
Visualisation of Big Imaging Data
Visualisation of Big Imaging DataVisualisation of Big Imaging Data
Visualisation of Big Imaging DataSlava Kitaeff, PhD
 
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"Dov Nimratz, Roman Chobik "Embedded artificial intelligence"
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"Lviv Startup Club
 
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Aritra Sarkar
 
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...Mehryar (Mike) E., Ph.D.
 
Cognitive Engine: Boosting Scientific Discovery
Cognitive Engine:  Boosting Scientific DiscoveryCognitive Engine:  Boosting Scientific Discovery
Cognitive Engine: Boosting Scientific Discoverydiannepatricia
 
URBAN OBJECT DETECTION IN UAV RESNETpptx
URBAN OBJECT DETECTION IN UAV RESNETpptxURBAN OBJECT DETECTION IN UAV RESNETpptx
URBAN OBJECT DETECTION IN UAV RESNETpptxbalajimankena
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningAly Abdelkareem
 
LambdaFabric for Machine Learning Acceleration
LambdaFabric for Machine Learning AccelerationLambdaFabric for Machine Learning Acceleration
LambdaFabric for Machine Learning AccelerationKnuEdge
 
From pixels to point clouds - Using drones,game engines and virtual reality t...
From pixels to point clouds - Using drones,game engines and virtual reality t...From pixels to point clouds - Using drones,game engines and virtual reality t...
From pixels to point clouds - Using drones,game engines and virtual reality t...ARDC
 
Deep learning fundamental and Research project on IBM POWER9 system from NUS
Deep learning fundamental and Research project on IBM POWER9 system from NUSDeep learning fundamental and Research project on IBM POWER9 system from NUS
Deep learning fundamental and Research project on IBM POWER9 system from NUSGanesan Narayanasamy
 
"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
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Sergey Karayev
 

Similar to "A Fast Object Detector for ADAS using Deep Learning," a Presentation from Panasonic (20)

“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
 
PhD Thesis Proposal
PhD Thesis Proposal PhD Thesis Proposal
PhD Thesis Proposal
 
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...
Grid'5000: Running a Large Instrument for Parallel and Distributed Computing ...
 
FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...FPT17: An object detector based on multiscale sliding window search using a f...
FPT17: An object detector based on multiscale sliding window search using a f...
 
Object Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IObject Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet I
 
Deep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLabDeep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLab
 
Visualisation of Big Imaging Data
Visualisation of Big Imaging DataVisualisation of Big Imaging Data
Visualisation of Big Imaging Data
 
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"Dov Nimratz, Roman Chobik "Embedded artificial intelligence"
Dov Nimratz, Roman Chobik "Embedded artificial intelligence"
 
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
 
kanimozhi2019.pdf
kanimozhi2019.pdfkanimozhi2019.pdf
kanimozhi2019.pdf
 
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...
POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infr...
 
Cognitive Engine: Boosting Scientific Discovery
Cognitive Engine:  Boosting Scientific DiscoveryCognitive Engine:  Boosting Scientific Discovery
Cognitive Engine: Boosting Scientific Discovery
 
URBAN OBJECT DETECTION IN UAV RESNETpptx
URBAN OBJECT DETECTION IN UAV RESNETpptxURBAN OBJECT DETECTION IN UAV RESNETpptx
URBAN OBJECT DETECTION IN UAV RESNETpptx
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learning
 
Quantum Computing at NIST
Quantum Computing at NISTQuantum Computing at NIST
Quantum Computing at NIST
 
LambdaFabric for Machine Learning Acceleration
LambdaFabric for Machine Learning AccelerationLambdaFabric for Machine Learning Acceleration
LambdaFabric for Machine Learning Acceleration
 
From pixels to point clouds - Using drones,game engines and virtual reality t...
From pixels to point clouds - Using drones,game engines and virtual reality t...From pixels to point clouds - Using drones,game engines and virtual reality t...
From pixels to point clouds - Using drones,game engines and virtual reality t...
 
Deep learning fundamental and Research project on IBM POWER9 system from NUS
Deep learning fundamental and Research project on IBM POWER9 system from NUSDeep learning fundamental and Research project on IBM POWER9 system from NUS
Deep learning fundamental and Research project on IBM POWER9 system from NUS
 
"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...
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
 

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
 
“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
 
“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
 
“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
 
“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
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...Edge AI and Vision Alliance
 
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic LeapEdge AI and Vision Alliance
 
“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from InstrumentalEdge AI and Vision Alliance
 
“Learning for 360° Vision,” a Presentation from Google
“Learning for 360° Vision,” a Presentation from Google“Learning for 360° Vision,” a Presentation from Google
“Learning for 360° Vision,” a Presentation from GoogleEdge AI and Vision Alliance
 
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...Edge AI and Vision Alliance
 
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...Edge AI and Vision Alliance
 
May 2023 Embedded Vision Summit Opening Remarks (May 23)
May 2023 Embedded Vision Summit Opening Remarks (May 23)May 2023 Embedded Vision Summit Opening Remarks (May 23)
May 2023 Embedded Vision Summit Opening Remarks (May 23)Edge AI and Vision Alliance
 
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...Edge AI and Vision Alliance
 
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...Edge AI and Vision Alliance
 
“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group
“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group
“3D Sensing: Market and Industry Update,” a Presentation from the Yole GroupEdge 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...
 
“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...
 
“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...
 
“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...
 
“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...
 
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
 
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
 
“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental“A Survey of Model Compression Methods,” a Presentation from Instrumental
“A Survey of Model Compression Methods,” a Presentation from Instrumental
 
“Learning for 360° Vision,” a Presentation from Google
“Learning for 360° Vision,” a Presentation from Google“Learning for 360° Vision,” a Presentation from Google
“Learning for 360° Vision,” a Presentation from Google
 
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...
“Introduction to Optimizing ML Models for the Edge,” a Presentation from Cisc...
 
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...
“Efficient Neuromorphic Computing with Dynamic Vision Sensor, Spiking Neural ...
 
May 2023 Embedded Vision Summit Opening Remarks (May 23)
May 2023 Embedded Vision Summit Opening Remarks (May 23)May 2023 Embedded Vision Summit Opening Remarks (May 23)
May 2023 Embedded Vision Summit Opening Remarks (May 23)
 
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...
“Frontiers in Perceptual AI: First-person Video and Multimodal Perception,” a...
 
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...
“LiDAR Technologies and Markets: What’s Changing?,” a Presentation from the Y...
 
“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group
“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group
“3D Sensing: Market and Industry Update,” a Presentation from the Yole Group
 

Recently uploaded

Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioChristian Posta
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopBachir Benyammi
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesDavid Newbury
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAshyamraj55
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...Aggregage
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfDianaGray10
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureEric D. Schabell
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxUdaiappa Ramachandran
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXTarek Kalaji
 
Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024SkyPlanner
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7DianaGray10
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfJamie (Taka) Wang
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsSafe Software
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Will Schroeder
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemAsko Soukka
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarPrecisely
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationIES VE
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesMd Hossain Ali
 
COMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a WebsiteCOMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a Websitedgelyza
 

Recently uploaded (20)

Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and Istio
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 Workshop
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond Ontologies
 
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability Adventure
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptx
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBX
 
Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024Salesforce Miami User Group Event - 1st Quarter 2024
Salesforce Miami User Group Event - 1st Quarter 2024
 
UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7UiPath Studio Web workshop series - Day 7
UiPath Studio Web workshop series - Day 7
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystem
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity Webinar
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
 
COMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a WebsiteCOMPUTER 10 Lesson 8 - Building a Website
COMPUTER 10 Lesson 8 - Building a Website
 

"A Fast Object Detector for ADAS using Deep Learning," a Presentation from Panasonic

  • 1. 1 Minyoung Kim May 1st, 2017 A Fast Object Detector for ADAS Using Deep Learning
  • 2. 2 Panasonic Silicon Valley Laboratory Silicon Valley Laboratory (PSVL) Cupertino, California
  • 3. 3 •  Pros •  High performance •  Beat state-of-the-art records in many tasks including image classification and detection •  Cons •  Large set of database •  High computational power •  Deep Neural Networks with millions of parameters •  Slower running time than most of conventional algorithms Object Detection with Deep Learning
  • 5. 5 Object Detection System Building Object Detection System •  Training Deep Neural Network for Classification •  Pedestrian detection: Binary classification •  Object Proposal Generation at different scales •  Generate box proposals (1000 ~ 2000 boxes) •  Selective Search*, Edge Boxes** •  Merge largely overlapping boxes •  Non Maximum Suppression * J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, A. W. M. Smeulders, IJCV 2013 ** C. Lawrence Zitnick and Piotr Doll´ar, Microsoft Research Run Recognizer Proposal Generation Recognition Network Classification Pedestrian Background Merge boxes
  • 6. 6 Time Consuming! Proposal Generation & Scaling •  Region proposal •  Selective Search: 2 seconds per image (CPU) •  Order of magnitude slower •  Edge Boxes: 0.2 seconds per image •  Scaling •  Multiple forward propagations •  Bottleneck •  A forward propagation of an image •  Less than 0.1 seconds (GPU) Object Detection System Proposal Generation Scaling
  • 7. 7 PSVL Pedestrian Detection System Our Pedestrian Detection System INPUT A Single Forward Propagation OUTPUT PSVL Neural Detector
  • 8. 8 Recognition Network Our Pedestrian Detection System Add Regression Layer and Finetune Fully Convolutional Network as Detector Detection by a single forward propagation
  • 9. 9 Train DNN for recognition •  GPU & Framework •  NVIDIA Titan X, NVIDIA Tesla K80 •  Caffe* •  Network Architectures •  Modified GoogLeNet** •  25~30 Convolutional layers •  Input: Pedestrian and Backgrounds (80x32) •  Output: Sigmoid or Softmax •  Dataset •  Caltech Pedestrian Detection Benchmark*** •  10 hours of 640(w) x 480(h) 30Hz video •  About 250,000 frames with a total of 350,000 bounding boxes Recognition Network * http://caffe.berkeleyvision.org/ ** C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich (2014) *** http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/
  • 10. 10 Convert recognition network to a fully convolutional network Fully Convolutional Network Base Network limited input size Kernel sliding Input size not limited Fully connected Convolutional
  • 11. 11 Regression Layer •  Regress bounding boxes on useful features •  Nx4 box coordinates data •  N: Feature Map resolution (NX x NY) •  Original GT Box: B = [x1, y1, x2, y2] •  New GT Box: B’ = rel(B) / m (m: multiplier of Window Size) Fully Convolutional Network 240 120 m = 2 Output Feature Map 4 NX NY
  • 12. 12 Training detector network •  Network Architectures •  Custom loss functions •  Feature Map: Cross Entropy Loss with Boosting •  Boosting •  Ped: Correct Results (TPs) + Ground Truths (FNs) •  True Positive if IOU > 0.5 •  False Negative if Ground Truths not detected •  NonPed: FPs •  False Positive if IOU < 0.5 •  Regression: Euclidean Loss with Feature Map Data incorporated PSVL Neural Detector + 640x480 Original Images Regression Layer Fully Convolutional Network Feature Map Box Coord- inates
  • 14. 14 Even fewer box prediction with Center-Height features PSVL Neural Detector
  • 15. 15 Performance – Very Fast with Competitive Accuracy •  From DeepCascade paper1) •  DeepCascade: NVIDIA K20 •  15 fps •  Ours: NVIDIA GTX770 •  34 fps •  Speed Adjustment •  34*0.96992) = 33 fps •  Ours: NVIDIA Titan X •  51.422 fps w/o cuDNN •  85.565 fps with cuDNN4 (*): Left hand side for methods with unknown fps or less than 0.2 fps (**): DeepCascade without extra data (***): SpatialPooling+/Katamari methods use additional motion information 1) A. Angelova, A. Krizhevsky V. Vanhoucke, A. Ogale, D. Ferguson (2015) 2) http://caffe.berkeleyvision.org/performance_hardware.html Performance of Pedestrian Detection Methods (Accuracy vs. Speed) PSVL ND (**) (*) (***) Faster Moreaccurate
  • 16. 16 Deploy PSVL ND on Google Nexus 9 •  Processor •  NVIDIA Tegra K1 •  GPU: NVIDIA Kepler with 192 CUDA cores •  Speed (without any optimization) •  Base resolution (600x390): 5 fps •  Lower resolution (280x240): 16 fps ND on Portable Device
  • 17. 17 Threshold Information Probability and NMS Threshold Bar Detection box with Probability Toggle for Threshold Bar ND Application
  • 18. 18 ND Application Demo (Cluster with Titan X)
  • 19. 19 ND Application Demo at ITSWC 2015 GTX980m Tegra K1
  • 20. 20 More Approaches •  Faster-RCNN (2015)* •  Region Proposal Network •  +10 ms •  Anchor boxes •  Predicts offsets & confidences Object Detection from others * S. Ren, K. He, R. Girshick, J. Sun (NIPS 2015)
  • 21. 21 Object Detection from others * J. Redmon, S. Divvala, R. Girshick, and A. Farhadi (CVPR 2016) ** J. Redmon and A. Farhadi (CVPR 2017) •  YOLO9000 (2017)** •  Improved localization/recall •  (-) fully connected layer Similar Approaches •  YOLO (2016)* •  Fully Convolutional Network •  + fc layer + regression
  • 22. 22 OURS * F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, K. Keutzer (arXiv:1602.07360) PSVL Multiple-Object Detection System •  Fire modules* •  Only 13 MB size •  16.5 fps on max scale (600x2200) Performance (Speed, Accuracy)
  • 23. 23 PSVL Multiple-Object Detection System •  Only real-time demo at ITSWC 2016 •  30+ fps (2 views per GPU) Demo at ITSWC 2016
  • 25. 25 PSVL Neural Tracker •  Critical Risk Management by tracking nearby objects (pedestrians, cars, cyclists) •  arXiv:1609.09156 •  State-of-the-art on KITTI MOT What’s Next? ( : weight sharing ) pairdata datap featp datap feat ContrastiveLoss NB DIoU DArat deconvI reluA reluI deconvA concat concatp
  • 27. 27 Conclusion Speed & Accuracy No Separate Region Proposal Network Size Optimization