SlideShare a Scribd company logo
1 of 14
Download to read offline
Fine-grained Walking Activity Recognition
via Driving Recorder Dataset
Hirokatsu KATAOKA, Yoshimitsu AOKI†, Yutaka SATOH
Shoko, OIKAWA‡, Yasuhiro MATSUI‡
National Institute of Advanced Industrial Science and Technology (AIST)
† Keio University
‡ National Traffic Safety and Environment Laboratory (NTSEL)
http://www.hirokatsukataoka.net/
Background
•  ADAS; Advanced Driver Assistance Systems
–  A large amount of technologies have been proposed
–  The pedestrian deaths are on the rise
–  Detection systems, environment, autonomous driving car
@Pedestrian	
  and	
  vehicle	
  detec0on	
   @Lane	
  detec0on	
  (Environment	
  understanding)	
  
@Autonomous	
  driving	
  in	
  Google	
  
ADAS technologies are highly required!
Pedestrian detection
•  Vision-based detection is one of the important techniques
–  Pedestrian detection survey [Benenson+, ECCVW2014]
•  They implemented and compared 40+ detection approaches
–  Deep Learning is applied to detect pedestrians [Sermanet+, CVPR2013]
•  Convolutional neural networks (CNN)
•  Automatic feature training and classifier
Better
Detection rate has been improving
New step toward “pedestrian analysis”
•  High-performance pedestrian localization
–  Task-assistant CNN (TA-CNN) [Tian+, CVPR2015]
•  The framework is consist of CNN feat. & attribute (e.g. background, location)
•  Limitations of pedestrian safety systems
–  Pedestrian detection at present
–  Detection range: width of the vehicle
Going to the next “pedestrian analysis” researches!
Motivation
•  Fine-grained pedestrian activity recognition in addition to
pedestrian detection
–  More detailed activity analysis
–  Pedestrian activity intention understanding
Probabilitymapofdanger
1.0 second is crucial time in ADAS
Why fine-grained?
Walking along a sidewalk
Turning
Crossing a roadway
Process flow
•  Fine-grained walking activity recognition
1.  Pedestrian localization
2.  Activity analysis
Improved dense trajectories (iDT)
Pedestrian detection	
x	
x	
x	
x	
x	
x	
x	
 x	
x	
x	
x	
x	
x	
x	
x	
x	
x	
x	
Trajectory (in t + L frames)	
Feature extraction
(HOG, HOF, MBH, Traj.)	
Bag-of-words (BoW)	
iDT
Detection system
•  Per-frame CNN feature and NMS
–  Region of interesting (ROI)
–  VGGNet feature in the detection problem
–  Non-maximum suppression for combining detection windows
・・・~	
  
~・・・	
  
NMS
Activity Recognition
•  Improved Dense Trajectories (iDT) [Wang+, ICCV2013]
–  Pyramidal image sequences and flow tracking
–  Feature descriptors on trajectories
–  Feature representation with bag-of-words (BoW)
WalkingCrossing Turning
Experiments
•  Fine-grained walking activity recognition
–  Understanding small changes while people walking
•  Walking along a side walk & Crossing a road way
•  Walking straight & turning
•  Walking & riding a bicycle
(a)	
  crossing	
 (b)	
  walking	
 (c)	
  turning	
 (d)	
  bicycle
Datasets and implementations
•  NTSEL dataset & Near-miss dataset
•  Implementation
–  Localization: VGGNet layer-pooling-5
–  Feature: IDT (HOG, HOF, MBH, Traj.)
–  Classifier: Support vector machine (SVM)
(a)	
  crossing	
 (b)	
  walking	
 (c)	
  turning	
 (d)	
  bicycle	
NTSEL dataset Near-miss DR dataset
http://www.jsae.or.jp/hiyari/0907/
Results
•  On the NTSEL and Near-miss DR dataset
Descriptor % on NTSEL % on Near-miss
DT (Traj.) 76.5 77.9
DT (HOF) 93.7 75.9
DT (HOG) 85.6 76.4
DT (MBHx) 87.7 59.3
DT (MBHy) 86.7 60.8
–  Outstanding performance rate with IDT 93.7% on NTSEL and 77.9% on Near-
miss DR dataset
Spatio-temporal analysis
•  Using iDT, temporal direction is analyzed
–  Fewer frames are better in the space-time
–  Sudden motion should be recognized
Demonstration
•  Fine-grained ped. activity recognition on NTSEL dataset
–  Improved Dense Trajectories (93.7%)
Conclusion
•  Fine-grained walking activity analysis for the new step of
pedestrian intention understanding
–  State-of-the-art motion analysis algorithms are implemented
–  High-performance localization and recognition on the traffic datasets
–  Pedestrian analysis are executed in detail
•  More flexible models and intention understanding
–  We need more data in learning step
–  Transition model or more strong temporal feature should be implemented

More Related Content

What's hot

Scanning 3 d full human bodies using kinects
Scanning 3 d full human bodies using kinectsScanning 3 d full human bodies using kinects
Scanning 3 d full human bodies using kinects
Fensa Saj
 
Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)
nikhilus85
 
Human Action Recognition Based on Spacio-temporal features
Human Action Recognition Based on Spacio-temporal featuresHuman Action Recognition Based on Spacio-temporal features
Human Action Recognition Based on Spacio-temporal features
nikhilus85
 
Human Action Recognition Based on Spacio-temporal features-Poster
Human Action Recognition Based on Spacio-temporal features-PosterHuman Action Recognition Based on Spacio-temporal features-Poster
Human Action Recognition Based on Spacio-temporal features-Poster
nikhilus85
 
Real Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth SensorsReal Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth Sensors
Wassim Filali
 

What's hot (20)

Scanning 3 d full human bodies using kinects
Scanning 3 d full human bodies using kinectsScanning 3 d full human bodies using kinects
Scanning 3 d full human bodies using kinects
 
Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)
 
Human Action Recognition Based on Spacio-temporal features
Human Action Recognition Based on Spacio-temporal featuresHuman Action Recognition Based on Spacio-temporal features
Human Action Recognition Based on Spacio-temporal features
 
Stereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
Stereo Vision Human Motion Detection and Tracking in Uncontrolled EnvironmentStereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
Stereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
 
Motion Human Detection & Tracking Based On Background Subtraction
Motion Human Detection & Tracking Based On Background SubtractionMotion Human Detection & Tracking Based On Background Subtraction
Motion Human Detection & Tracking Based On Background Subtraction
 
Human Action Recognition Based on Spacio-temporal features-Poster
Human Action Recognition Based on Spacio-temporal features-PosterHuman Action Recognition Based on Spacio-temporal features-Poster
Human Action Recognition Based on Spacio-temporal features-Poster
 
SSII2020TS: Event-Based Camera の基礎と ニューラルネットワークによる信号処理 〜 生き物のように「変化」を捉えるビジョンセ...
SSII2020TS: Event-Based Camera の基礎と ニューラルネットワークによる信号処理 〜 生き物のように「変化」を捉えるビジョンセ...SSII2020TS: Event-Based Camera の基礎と ニューラルネットワークによる信号処理 〜 生き物のように「変化」を捉えるビジョンセ...
SSII2020TS: Event-Based Camera の基礎と ニューラルネットワークによる信号処理 〜 生き物のように「変化」を捉えるビジョンセ...
 
Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014
 
Lec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable RegistrationLec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable Registration
 
C0365025029
C0365025029C0365025029
C0365025029
 
Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...
 
SSII2021 [OS3-01] 設備や環境の高品質計測点群取得と自動モデル化技術
SSII2021 [OS3-01] 設備や環境の高品質計測点群取得と自動モデル化技術SSII2021 [OS3-01] 設備や環境の高品質計測点群取得と自動モデル化技術
SSII2021 [OS3-01] 設備や環境の高品質計測点群取得と自動モデル化技術
 
Variational formulation of unsupervised deep learning for ultrasound image ar...
Variational formulation of unsupervised deep learning for ultrasound image ar...Variational formulation of unsupervised deep learning for ultrasound image ar...
Variational formulation of unsupervised deep learning for ultrasound image ar...
 
Ph.D. Research
Ph.D. ResearchPh.D. Research
Ph.D. Research
 
CHARACTERIZING HUMAN BEHAVIOURS USING STATISTICAL MOTION DESCRIPTOR
CHARACTERIZING HUMAN BEHAVIOURS USING STATISTICAL MOTION DESCRIPTORCHARACTERIZING HUMAN BEHAVIOURS USING STATISTICAL MOTION DESCRIPTOR
CHARACTERIZING HUMAN BEHAVIOURS USING STATISTICAL MOTION DESCRIPTOR
 
Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)
 
Real Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth SensorsReal Time Human Posture Detection with Multiple Depth Sensors
Real Time Human Posture Detection with Multiple Depth Sensors
 
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
 
Automatic identification of animal using visual and motion saliency
Automatic identification of animal using visual and motion saliencyAutomatic identification of animal using visual and motion saliency
Automatic identification of animal using visual and motion saliency
 
Lec7: Medical Image Segmentation (I) (Radiology Applications of Segmentation,...
Lec7: Medical Image Segmentation (I) (Radiology Applications of Segmentation,...Lec7: Medical Image Segmentation (I) (Radiology Applications of Segmentation,...
Lec7: Medical Image Segmentation (I) (Radiology Applications of Segmentation,...
 

Viewers also liked

Viewers also liked (11)

【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
【CVPR2016_LAP】Dominant Codewords Selection with Topic Model for Action Recogn...
 
ILSVRC2015 手法のメモ
ILSVRC2015 手法のメモILSVRC2015 手法のメモ
ILSVRC2015 手法のメモ
 
【慶應大学講演】なぜ、博士課程に進学したか?
【慶應大学講演】なぜ、博士課程に進学したか?【慶應大学講演】なぜ、博士課程に進学したか?
【慶應大学講演】なぜ、博士課程に進学したか?
 
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
【論文紹介】Fashion Style in 128 Floats: Joint Ranking and Classification using Wea...
 
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
Convolutional Neural Networks のトレンド @WBAFLカジュアルトーク#2
 
CVPR 2016 まとめ v1
CVPR 2016 まとめ v1CVPR 2016 まとめ v1
CVPR 2016 まとめ v1
 
Deep Residual Learning (ILSVRC2015 winner)
Deep Residual Learning (ILSVRC2015 winner)Deep Residual Learning (ILSVRC2015 winner)
Deep Residual Learning (ILSVRC2015 winner)
 
TensorFlowによるCNNアーキテクチャ構築
TensorFlowによるCNNアーキテクチャ構築TensorFlowによるCNNアーキテクチャ構築
TensorFlowによるCNNアーキテクチャ構築
 
ECCV 2016 速報
ECCV 2016 速報ECCV 2016 速報
ECCV 2016 速報
 
CVPR 2016 速報
CVPR 2016 速報CVPR 2016 速報
CVPR 2016 速報
 
【チュートリアル】コンピュータビジョンによる動画認識
【チュートリアル】コンピュータビジョンによる動画認識【チュートリアル】コンピュータビジョンによる動画認識
【チュートリアル】コンピュータビジョンによる動画認識
 

Similar to 【ITSC2015】Fine-grained Walking Activity Recognition via Driving Recorder Dataset

HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
lanaw86385
 
Improving the quality and cost effectiveness of multimodal travel behavior da...
Improving the quality and cost effectiveness of multimodal travel behavior da...Improving the quality and cost effectiveness of multimodal travel behavior da...
Improving the quality and cost effectiveness of multimodal travel behavior da...
Sean Barbeau
 

Similar to 【ITSC2015】Fine-grained Walking Activity Recognition via Driving Recorder Dataset (20)

IRJET- Pedestrian Walk Exposure System through Multiple Classifiers
IRJET- Pedestrian Walk Exposure System through Multiple ClassifiersIRJET- Pedestrian Walk Exposure System through Multiple Classifiers
IRJET- Pedestrian Walk Exposure System through Multiple Classifiers
 
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
 
HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
HOW TO WASTE YOUR TIME ON SIMPLE THINGS DONT JUST FEEL INSTEAD BLAME OTHERS A...
 
NCHRP Report 770: Estimating Bicycling and Walking for Planning and Project D...
NCHRP Report 770: Estimating Bicycling and Walking for Planning and Project D...NCHRP Report 770: Estimating Bicycling and Walking for Planning and Project D...
NCHRP Report 770: Estimating Bicycling and Walking for Planning and Project D...
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour Science
 
New Tools for Estimating Walking and Bicycling Demand
New Tools for Estimating Walking and Bicycling DemandNew Tools for Estimating Walking and Bicycling Demand
New Tools for Estimating Walking and Bicycling Demand
 
Presentation
PresentationPresentation
Presentation
 
Big data Europe the transport pilot in Thessaloniki - Josep Maria Salanova
Big data Europe the transport pilot in Thessaloniki - Josep Maria SalanovaBig data Europe the transport pilot in Thessaloniki - Josep Maria Salanova
Big data Europe the transport pilot in Thessaloniki - Josep Maria Salanova
 
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCVVEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
VEHICLES AND TOURIST FREQUENCY TRACKING USING OPENCV
 
Identification and classification of moving vehicles on road
Identification and classification of moving vehicles on roadIdentification and classification of moving vehicles on road
Identification and classification of moving vehicles on road
 
Networks of wearables and augmented reality for vulnerable user protection
Networks of wearables and augmented reality for vulnerable user protectionNetworks of wearables and augmented reality for vulnerable user protection
Networks of wearables and augmented reality for vulnerable user protection
 
Env. mon
Env. monEnv. mon
Env. mon
 
Improving the quality and cost effectiveness of multimodal travel behavior da...
Improving the quality and cost effectiveness of multimodal travel behavior da...Improving the quality and cost effectiveness of multimodal travel behavior da...
Improving the quality and cost effectiveness of multimodal travel behavior da...
 
PDR developlent and PDR Challenge in Warehouse Picking
PDR developlent and PDR Challenge in Warehouse PickingPDR developlent and PDR Challenge in Warehouse Picking
PDR developlent and PDR Challenge in Warehouse Picking
 
ITS development in Kajang city
ITS development in Kajang cityITS development in Kajang city
ITS development in Kajang city
 
TRAFFIC MANAGEMENT THROUGH SATELLITE IMAGING -- Part 1
TRAFFIC MANAGEMENT THROUGH SATELLITE IMAGING -- Part 1TRAFFIC MANAGEMENT THROUGH SATELLITE IMAGING -- Part 1
TRAFFIC MANAGEMENT THROUGH SATELLITE IMAGING -- Part 1
 
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
 
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
Network Based Kernel Density Estimation for Cycling Facilities Optimal Locati...
 
Bus Analytics Toolkit Demo
Bus Analytics Toolkit DemoBus Analytics Toolkit Demo
Bus Analytics Toolkit Demo
 
Techniques and Challenges in Autonomous Driving
Techniques and Challenges in Autonomous DrivingTechniques and Challenges in Autonomous Driving
Techniques and Challenges in Autonomous Driving
 

Recently uploaded

Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
PirithiRaju
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Lokesh Kothari
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
PirithiRaju
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
gindu3009
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
Areesha Ahmad
 

Recently uploaded (20)

High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
 
GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)GBSN - Microbiology (Unit 3)
GBSN - Microbiology (Unit 3)
 
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRLKochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
Kochi ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Kochi ESCORT SERVICE❤CALL GIRL
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxCOST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
9999266834 Call Girls In Noida Sector 22 (Delhi) Call Girl Service
 
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
 
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
❤Jammu Kashmir Call Girls 8617697112 Personal Whatsapp Number 💦✅.
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 

【ITSC2015】Fine-grained Walking Activity Recognition via Driving Recorder Dataset

  • 1. Fine-grained Walking Activity Recognition via Driving Recorder Dataset Hirokatsu KATAOKA, Yoshimitsu AOKI†, Yutaka SATOH Shoko, OIKAWA‡, Yasuhiro MATSUI‡ National Institute of Advanced Industrial Science and Technology (AIST) † Keio University ‡ National Traffic Safety and Environment Laboratory (NTSEL) http://www.hirokatsukataoka.net/
  • 2. Background •  ADAS; Advanced Driver Assistance Systems –  A large amount of technologies have been proposed –  The pedestrian deaths are on the rise –  Detection systems, environment, autonomous driving car @Pedestrian  and  vehicle  detec0on   @Lane  detec0on  (Environment  understanding)   @Autonomous  driving  in  Google   ADAS technologies are highly required!
  • 3. Pedestrian detection •  Vision-based detection is one of the important techniques –  Pedestrian detection survey [Benenson+, ECCVW2014] •  They implemented and compared 40+ detection approaches –  Deep Learning is applied to detect pedestrians [Sermanet+, CVPR2013] •  Convolutional neural networks (CNN) •  Automatic feature training and classifier Better Detection rate has been improving
  • 4. New step toward “pedestrian analysis” •  High-performance pedestrian localization –  Task-assistant CNN (TA-CNN) [Tian+, CVPR2015] •  The framework is consist of CNN feat. & attribute (e.g. background, location) •  Limitations of pedestrian safety systems –  Pedestrian detection at present –  Detection range: width of the vehicle Going to the next “pedestrian analysis” researches!
  • 5. Motivation •  Fine-grained pedestrian activity recognition in addition to pedestrian detection –  More detailed activity analysis –  Pedestrian activity intention understanding Probabilitymapofdanger 1.0 second is crucial time in ADAS Why fine-grained? Walking along a sidewalk Turning Crossing a roadway
  • 6. Process flow •  Fine-grained walking activity recognition 1.  Pedestrian localization 2.  Activity analysis Improved dense trajectories (iDT) Pedestrian detection x x x x x x x x x x x x x x x x x x Trajectory (in t + L frames) Feature extraction (HOG, HOF, MBH, Traj.) Bag-of-words (BoW) iDT
  • 7. Detection system •  Per-frame CNN feature and NMS –  Region of interesting (ROI) –  VGGNet feature in the detection problem –  Non-maximum suppression for combining detection windows ・・・~   ~・・・   NMS
  • 8. Activity Recognition •  Improved Dense Trajectories (iDT) [Wang+, ICCV2013] –  Pyramidal image sequences and flow tracking –  Feature descriptors on trajectories –  Feature representation with bag-of-words (BoW) WalkingCrossing Turning
  • 9. Experiments •  Fine-grained walking activity recognition –  Understanding small changes while people walking •  Walking along a side walk & Crossing a road way •  Walking straight & turning •  Walking & riding a bicycle (a)  crossing (b)  walking (c)  turning (d)  bicycle
  • 10. Datasets and implementations •  NTSEL dataset & Near-miss dataset •  Implementation –  Localization: VGGNet layer-pooling-5 –  Feature: IDT (HOG, HOF, MBH, Traj.) –  Classifier: Support vector machine (SVM) (a)  crossing (b)  walking (c)  turning (d)  bicycle NTSEL dataset Near-miss DR dataset http://www.jsae.or.jp/hiyari/0907/
  • 11. Results •  On the NTSEL and Near-miss DR dataset Descriptor % on NTSEL % on Near-miss DT (Traj.) 76.5 77.9 DT (HOF) 93.7 75.9 DT (HOG) 85.6 76.4 DT (MBHx) 87.7 59.3 DT (MBHy) 86.7 60.8 –  Outstanding performance rate with IDT 93.7% on NTSEL and 77.9% on Near- miss DR dataset
  • 12. Spatio-temporal analysis •  Using iDT, temporal direction is analyzed –  Fewer frames are better in the space-time –  Sudden motion should be recognized
  • 13. Demonstration •  Fine-grained ped. activity recognition on NTSEL dataset –  Improved Dense Trajectories (93.7%)
  • 14. Conclusion •  Fine-grained walking activity analysis for the new step of pedestrian intention understanding –  State-of-the-art motion analysis algorithms are implemented –  High-performance localization and recognition on the traffic datasets –  Pedestrian analysis are executed in detail •  More flexible models and intention understanding –  We need more data in learning step –  Transition model or more strong temporal feature should be implemented