SlideShare ist ein Scribd-Unternehmen logo
1 von 31
Digest of Human Detection
from CVPR 2015
Jan. 27th, 2016, Daichi SUZUO
Digest of Human Detection from CVPR2015
Features
1. Combination Features and Models for Human Detection - Y. Jiang et al.
2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al.
Training
3. Learning Scene-Specific Pedestrian Detectors without Real Data - H.Hattori et al.
4. Taking a Deeper Look at Pedestrians - J. Hosang et al.
5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al.
Dataset / Benchmark
6. Multispectral Pedestrian Detection :
Benchmark Dataset and Baseline - S. Hwang et al.
Fundamentals of Human Detection
• Machine learning based bi-class classifier
• Sliding window search
Negative class
Positive class Convert to
image feature
Training Classifier
Classifier
Crop Feature
extraction
Human?
Not human?
Image features
1. Combination Features and Models for Human Detection
- Y. Jiang et al.
2. Filtered Channel Features for Pedestrian Detection
- S. Zhang et al.
θ
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
• Popular HOG feature[Dalal05]
Input image Edge-image
Edge
extraction
(“cell”)
pixel-wise
gradient
power
Histogram
θ
• Popular HOG feature[Dalal05]: 1st order feature
power
Input image 1st derivative
Differentiate
Histogram
(“cell”)
pixel-wise
gradient
idea: How about extending to 0-th/2nd order?
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
• 2nd order: HOB – “bar” shape
• Same as HOG, just using 2nd derivative
• 0th order: HOC – color feature
• Using HSI color space; H as θ, S as power
ignore I
convert to HSI
R
G
V
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
• Combine them into one vector: HOG-III feature
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
• Train different classifiers from the same HOG-IIIs
• Detect individually, and fuse into one result
Input
image
HOG-III
features
Detection by
Grammar model[Girshick11]
Detection by
Poselet model[Bourdev10]
Fusion
Final
result
(This is one of the key process of the method
Please refer the original paper for more details)
1. Combination Features and Models
for Human Detection - Y. Jiang et al.
Effect of HOG-III
Effect of Fusion
Feature AP
HOG 45.8%
HOC+HOG+HOB 50.1%
HOG-III 51.3%
Classifier AP
Single use of Grammer 45.8%
Single use of Poselet 47.0%
Fusion 52.3% Combining HOG-III and Fusion
performs best
2. Filtered Channel Features
for Pedestrian Detection - S. Zhang et al.
• Extension of “Integral Channel Features” [Dollár09]
• ChnFtrs: Extension of “Viola-Jones method” [Viola02]
(Viola-Jones method)
…
…
…
Input image
Learn decision-tree
by AdaBoost
Extract “Haar-like”
Features (scalar)
※Sum of difference between
white and black region
2. Filtered Channel Features
for Pedestrian Detection - S. Zhang et al.
• Extension of “Integral Channel Features” [Dollár09]
• ChnFtrs: Extension of “Viola-Jones method” [Viola02]
(Integral Channel Features)
…
…
…
Input image
Learn decision-tree
by AdaBoost
“channel”
Extract sum
of rectangle
※Unlike
Haar-like
Transform
2. Filtered Channel Features
for Pedestrian Detection - S. Zhang et al.
• Extension of “Integral Channel Features” [Dollár09]
• ChnFtrs: Extension of “Viola-Jones method” [Viola02]
(Filtered Channel Features)
…
…
…
Learn decision-tree
by AdaBoost
“channel” Apply various
filters
(convolution)
…
*
*
Pick-up
pixel value
as a feature
…
2. Filtered Channel Features
for Pedestrian Detection - S. Zhang et al.
Using 50 filters
performs bestAchieved the highest accuracy
Training
3. Learning Scene-Specific Pedestrian Detectors
without Real Data - H. Hattori et al.
4. Taking a Deeper Look at Pedestrians
- J. Hosang et al.
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
• Train detector by CG-based training datasets
3. Learning Scene-Specific Pedestrian Detectors
without Real Data - H. Hattori et al.
Real background
(static image)
annotate
CG-based human
composite
Simulated scene
• Not only scene-specific, but also location-specific!
3. Learning Scene-Specific Pedestrian Detectors
without Real Data - H. Hattori et al.
…
Classifier
Classifier
…
Grid with overwrap
(102~105 patches)
Training images
(~103 pos, ~103 neg
for each patch)
Joint
Classifier
Ensemble
Training
Scene-specific
Location-specific
detectors
3. Learning Scene-Specific Pedestrian Detectors
without Real Data - H. Hattori et al.
Patch size # detectors Avg. Precision
8x8 371 .802
16x16 102 .798
32x32 30 .764
Effect of location-specific detection
Example of the detection result
Comparison
“convnet still underperforms state-of-the-arts”
…Really?
Enhance know-how of convnet based detector
4. Taking a Deeper Look at Pedestrians - J. Hosang et al.
• Small network (CifarNet) / Big network (AlexNet)
• Window size
• How to collect training images
• Fine-tuning
• Number and Type of layers
• …
4. Taking a Deeper Look at Pedestrians - J. Hosang et al.
Convnet with the best configuration outperforms!
Interesting points:
• Ratio of pos/neg does not affect
to the accuracy so much
• Data-augumentation is effective
• Network size should be chosen
by the amount of training samples
• ...
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
Binary-classification is sometimes insufficient…
Human
Not human
(Hard negatives)
It is necessary to use semantic information jointly
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
Classify pedestrian and Recognize semantic at once!
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
Classify pedestrian and Recognize semantic at once!
Also recognizes current scene semantics
• Pedestrian attribute (e.g. wearing backpack)
• Background attribute (e.g. road, sky, …)
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
Classify pedestrian and Recognize semantic at once!
Difficult to collect various (annotated) negs from one dataset…
Transfer from other annotated datasets by TA-CNN
(Please refer the original and related papers for more details about TA-CNN…)
5. Pedestrian Detection aided by
Deep Learning Semantic Tasks - Y. Tian et al.
Comparison with CNN-based methods
Example of detection results
Benchmark / Dataset
6. Multispectral Pedestrian Detection :
Benchmark Dataset and Baseline - S. Hwang et al.
• Dataset of visible-light and thermal image
6. Multispectral Pedestrian Detection :
Benchmark Dataset and Baseline - S. Hwang et al.
Contributions:
• Color and thermal images
• Both test/training data
• Temporally-corresponded tag
• Large enough
• …
Takeaways
• Human detection is still challenging
• Deep learning does not necessarily solve
every problems at this moment 
• There are several knowledge that might be helpful
for your research/hobby/…
Takeaways
References / Supplemental materials
1. Filtered channel features for pedestrian detection
4. Taking a Deeper Look at Pedestrians
• Author's website: http://rodrigob.github.io/
3. Learning Scene-Specific Pedestrian Detectors without Real Data
• Project: http://vishnu.boddeti.net/projects/detection-by-synthesis.html
• YouTube: https://youtu.be/2Jf7faozHUs
5. Pedestrian Detection aided by Deep Learning Semantic Tasks
• Project: http://mmlab.ie.cuhk.edu.hk/projects/TA-CNN/
6. Multispectral Pedestrian Detection: Benchmark Dataset and Baseline
• Lab: http://rcv.kaist.ac.kr/v2/
And all the papers of CVPR2015 are available at cv-foundation.org
See also

Weitere ähnliche Inhalte

Was ist angesagt?

Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsManish Khare
 
Object tracking a survey
Object tracking a surveyObject tracking a survey
Object tracking a surveyHaseeb Hassan
 
Occlusion and Abandoned Object Detection for Surveillance Applications
Occlusion and Abandoned Object Detection for Surveillance ApplicationsOcclusion and Abandoned Object Detection for Surveillance Applications
Occlusion and Abandoned Object Detection for Surveillance ApplicationsEditor IJCATR
 
Moving object detection
Moving object detectionMoving object detection
Moving object detectionManav Mittal
 
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCEHUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCEAswinraj Manickam
 
Object tracking presentation
Object tracking  presentationObject tracking  presentation
Object tracking presentationMrsShwetaBanait1
 
Object video tracking using a pan tilt-zoom system
Object video tracking using a pan tilt-zoom systemObject video tracking using a pan tilt-zoom system
Object video tracking using a pan tilt-zoom systemMohammed Abdalhakam Taha
 
multiple object tracking using particle filter
multiple object tracking using particle filtermultiple object tracking using particle filter
multiple object tracking using particle filterSRIKANTH DANDE
 
Object Detection and tracking in Video Sequences
Object Detection and tracking in Video SequencesObject Detection and tracking in Video Sequences
Object Detection and tracking in Video SequencesIDES Editor
 
Object tracking survey
Object tracking surveyObject tracking survey
Object tracking surveyRich Nguyen
 
Object detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forObject detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forVESIT,Chembur,Mumbai
 
Overview Of Video Object Tracking System
Overview Of Video Object Tracking SystemOverview Of Video Object Tracking System
Overview Of Video Object Tracking SystemEditor IJMTER
 
Multiple Object Tracking
Multiple Object TrackingMultiple Object Tracking
Multiple Object TrackingRainakSharma
 
A Survey on Approaches for Object Tracking
A Survey on Approaches for Object TrackingA Survey on Approaches for Object Tracking
A Survey on Approaches for Object Trackingjournal ijrtem
 
Video Surveillance Systems For Traffic Monitoring
Video Surveillance Systems For Traffic MonitoringVideo Surveillance Systems For Traffic Monitoring
Video Surveillance Systems For Traffic MonitoringMeridian Media
 
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION  DETECTION AND TRACKING FOR VIDEO SURVEILLANCEHUMAN MOTION  DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCENEHA THADEUS
 

Was ist angesagt? (20)

Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objects
 
Object tracking a survey
Object tracking a surveyObject tracking a survey
Object tracking a survey
 
Occlusion and Abandoned Object Detection for Surveillance Applications
Occlusion and Abandoned Object Detection for Surveillance ApplicationsOcclusion and Abandoned Object Detection for Surveillance Applications
Occlusion and Abandoned Object Detection for Surveillance Applications
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
 
A350111
A350111A350111
A350111
 
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCEHUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
 
Object tracking presentation
Object tracking  presentationObject tracking  presentation
Object tracking presentation
 
Object video tracking using a pan tilt-zoom system
Object video tracking using a pan tilt-zoom systemObject video tracking using a pan tilt-zoom system
Object video tracking using a pan tilt-zoom system
 
multiple object tracking using particle filter
multiple object tracking using particle filtermultiple object tracking using particle filter
multiple object tracking using particle filter
 
Object Detection and tracking in Video Sequences
Object Detection and tracking in Video SequencesObject Detection and tracking in Video Sequences
Object Detection and tracking in Video Sequences
 
Object tracking
Object trackingObject tracking
Object tracking
 
Object tracking survey
Object tracking surveyObject tracking survey
Object tracking survey
 
Moving object detection1
Moving object detection1Moving object detection1
Moving object detection1
 
Object detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forObject detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm for
 
Overview Of Video Object Tracking System
Overview Of Video Object Tracking SystemOverview Of Video Object Tracking System
Overview Of Video Object Tracking System
 
Object tracking final
Object tracking finalObject tracking final
Object tracking final
 
Multiple Object Tracking
Multiple Object TrackingMultiple Object Tracking
Multiple Object Tracking
 
A Survey on Approaches for Object Tracking
A Survey on Approaches for Object TrackingA Survey on Approaches for Object Tracking
A Survey on Approaches for Object Tracking
 
Video Surveillance Systems For Traffic Monitoring
Video Surveillance Systems For Traffic MonitoringVideo Surveillance Systems For Traffic Monitoring
Video Surveillance Systems For Traffic Monitoring
 
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION  DETECTION AND TRACKING FOR VIDEO SURVEILLANCEHUMAN MOTION  DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
HUMAN MOTION DETECTION AND TRACKING FOR VIDEO SURVEILLANCE
 

Andere mochten auch

Efficient exploration of region hierarchies for semantic segmentation
Efficient exploration of region hierarchies for semantic segmentationEfficient exploration of region hierarchies for semantic segmentation
Efficient exploration of region hierarchies for semantic segmentationUniversitat Politècnica de Catalunya
 
Positioning And Orientation In Indoor Environments Using Camera 2003
Positioning And Orientation In Indoor Environments Using Camera 2003Positioning And Orientation In Indoor Environments Using Camera 2003
Positioning And Orientation In Indoor Environments Using Camera 2003Pradeep Thomas Thundiyil
 
Face Detection using Multi-view HOGs
Face Detection using Multi-view HOGsFace Detection using Multi-view HOGs
Face Detection using Multi-view HOGsFederico D'Amato
 
Non maxima-suppression
Non maxima-suppressionNon maxima-suppression
Non maxima-suppressionAyaelshiwi
 
Non-maximum suppression using fewer than two comparison per pixels
Non-maximum suppression using fewer than two comparison per pixelsNon-maximum suppression using fewer than two comparison per pixels
Non-maximum suppression using fewer than two comparison per pixelsTuan Q. Pham
 
3D Reality Tracking in Realtime - Team Hendy-Sigit
3D Reality Tracking in Realtime - Team Hendy-Sigit3D Reality Tracking in Realtime - Team Hendy-Sigit
3D Reality Tracking in Realtime - Team Hendy-SigitHendy Irawan
 
Through the wall human detection
Through the wall human detectionThrough the wall human detection
Through the wall human detectionmanumohan007
 
A Proposed Framework for Robust Face Identification System
A Proposed Framework for Robust Face Identification SystemA Proposed Framework for Robust Face Identification System
A Proposed Framework for Robust Face Identification SystemAhmed Gad
 
Passenger Counting / People Counting Applications and Devices
Passenger Counting / People Counting Applications and DevicesPassenger Counting / People Counting Applications and Devices
Passenger Counting / People Counting Applications and DevicesEurotech
 
Customer Churn Analytics using Microsoft R Open
Customer Churn Analytics using Microsoft R OpenCustomer Churn Analytics using Microsoft R Open
Customer Churn Analytics using Microsoft R OpenPoo Kuan Hoong
 
Human detection iccv09
Human detection iccv09Human detection iccv09
Human detection iccv09fanghuaxue
 
Estimating Human Pose from Occluded Images (ACCV 2009)
Estimating Human Pose from Occluded Images (ACCV 2009)Estimating Human Pose from Occluded Images (ACCV 2009)
Estimating Human Pose from Occluded Images (ACCV 2009)Jia-Bin Huang
 
Masonic regalia craft provincial jewels
Masonic regalia craft provincial jewelsMasonic regalia craft provincial jewels
Masonic regalia craft provincial jewelsSialkot Regalia Center
 
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...Martin Olmedo Zarate
 
Informe de gestión
Informe de gestión Informe de gestión
Informe de gestión ENTRERRIOS
 

Andere mochten auch (20)

Efficient exploration of region hierarchies for semantic segmentation
Efficient exploration of region hierarchies for semantic segmentationEfficient exploration of region hierarchies for semantic segmentation
Efficient exploration of region hierarchies for semantic segmentation
 
Binary code-based Human Detection
Binary code-based Human DetectionBinary code-based Human Detection
Binary code-based Human Detection
 
Positioning And Orientation In Indoor Environments Using Camera 2003
Positioning And Orientation In Indoor Environments Using Camera 2003Positioning And Orientation In Indoor Environments Using Camera 2003
Positioning And Orientation In Indoor Environments Using Camera 2003
 
Face Detection using Multi-view HOGs
Face Detection using Multi-view HOGsFace Detection using Multi-view HOGs
Face Detection using Multi-view HOGs
 
Non maxima-suppression
Non maxima-suppressionNon maxima-suppression
Non maxima-suppression
 
Non-maximum suppression using fewer than two comparison per pixels
Non-maximum suppression using fewer than two comparison per pixelsNon-maximum suppression using fewer than two comparison per pixels
Non-maximum suppression using fewer than two comparison per pixels
 
3D Reality Tracking in Realtime - Team Hendy-Sigit
3D Reality Tracking in Realtime - Team Hendy-Sigit3D Reality Tracking in Realtime - Team Hendy-Sigit
3D Reality Tracking in Realtime - Team Hendy-Sigit
 
Through the wall human detection
Through the wall human detectionThrough the wall human detection
Through the wall human detection
 
A Proposed Framework for Robust Face Identification System
A Proposed Framework for Robust Face Identification SystemA Proposed Framework for Robust Face Identification System
A Proposed Framework for Robust Face Identification System
 
Passenger Counting / People Counting Applications and Devices
Passenger Counting / People Counting Applications and DevicesPassenger Counting / People Counting Applications and Devices
Passenger Counting / People Counting Applications and Devices
 
Customer Churn Analytics using Microsoft R Open
Customer Churn Analytics using Microsoft R OpenCustomer Churn Analytics using Microsoft R Open
Customer Churn Analytics using Microsoft R Open
 
Human detection iccv09
Human detection iccv09Human detection iccv09
Human detection iccv09
 
Background subtraction
Background subtractionBackground subtraction
Background subtraction
 
Estimating Human Pose from Occluded Images (ACCV 2009)
Estimating Human Pose from Occluded Images (ACCV 2009)Estimating Human Pose from Occluded Images (ACCV 2009)
Estimating Human Pose from Occluded Images (ACCV 2009)
 
Masonic regalia craft provincial jewels
Masonic regalia craft provincial jewelsMasonic regalia craft provincial jewels
Masonic regalia craft provincial jewels
 
Cmp 104
Cmp 104Cmp 104
Cmp 104
 
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...
Diseño sísmico de la conexión losa columna en losas planas postensadas aliger...
 
Posostek
PosostekPosostek
Posostek
 
Informe de gestión
Informe de gestión Informe de gestión
Informe de gestión
 
Nuevo documento de texto (2)
Nuevo documento de texto (2)Nuevo documento de texto (2)
Nuevo documento de texto (2)
 

Ähnlich wie Digest of Human Detection from CVPR2015

A survey on moving object tracking in video
A survey on moving object tracking in videoA survey on moving object tracking in video
A survey on moving object tracking in videoijitjournal
 
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
 
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTS
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTSMULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTS
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTSsipij
 
Wang midterm-defence
Wang midterm-defenceWang midterm-defence
Wang midterm-defenceZhipeng Wang
 
When Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial IntelligenceWhen Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial IntelligenceWahyuRahmaniar2
 
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...tino
 
Soundarya m.sc
Soundarya m.scSoundarya m.sc
Soundarya m.scsowfi
 
An improved particle filter tracking
An improved particle filter trackingAn improved particle filter tracking
An improved particle filter trackingijcsit
 
Symbolic representation and recognition of gait an approach based on lbp of ...
Symbolic representation and recognition of gait  an approach based on lbp of ...Symbolic representation and recognition of gait  an approach based on lbp of ...
Symbolic representation and recognition of gait an approach based on lbp of ...sipij
 
Object Detection An Overview
Object Detection An OverviewObject Detection An Overview
Object Detection An Overviewijtsrd
 
An analysis of_machine_and_human_analytics_in_classification
An analysis of_machine_and_human_analytics_in_classificationAn analysis of_machine_and_human_analytics_in_classification
An analysis of_machine_and_human_analytics_in_classificationSubhashis Hazarika
 
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
 
To identify the person using gait knn based approach
To identify the person using gait   knn based approachTo identify the person using gait   knn based approach
To identify the person using gait knn based approacheSAT Journals
 
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...Hirokatsu Kataoka
 
Fast Human Detection in Surveillance Video
Fast Human Detection in Surveillance VideoFast Human Detection in Surveillance Video
Fast Human Detection in Surveillance VideoIOSR Journals
 
A novel enhanced algorithm for efficient human tracking
A novel enhanced algorithm for efficient human trackingA novel enhanced algorithm for efficient human tracking
A novel enhanced algorithm for efficient human trackingIJICTJOURNAL
 

Ähnlich wie Digest of Human Detection from CVPR2015 (20)

A survey on moving object tracking in video
A survey on moving object tracking in videoA survey on moving object tracking in video
A survey on moving object tracking in video
 
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
 
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTS
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTSMULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTS
MULTIPLE OBJECTS TRACKING IN SURVEILLANCE VIDEO USING COLOR AND HU MOMENTS
 
Wang midterm-defence
Wang midterm-defenceWang midterm-defence
Wang midterm-defence
 
When Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial IntelligenceWhen Remote Sensing Meets Artificial Intelligence
When Remote Sensing Meets Artificial Intelligence
 
O180305103105
O180305103105O180305103105
O180305103105
 
Kb gait-recognition
Kb gait-recognitionKb gait-recognition
Kb gait-recognition
 
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
 
Content based video summarization into object maps
Content based video summarization into object mapsContent based video summarization into object maps
Content based video summarization into object maps
 
Soundarya m.sc
Soundarya m.scSoundarya m.sc
Soundarya m.sc
 
An improved particle filter tracking
An improved particle filter trackingAn improved particle filter tracking
An improved particle filter tracking
 
Symbolic representation and recognition of gait an approach based on lbp of ...
Symbolic representation and recognition of gait  an approach based on lbp of ...Symbolic representation and recognition of gait  an approach based on lbp of ...
Symbolic representation and recognition of gait an approach based on lbp of ...
 
Object Detection An Overview
Object Detection An OverviewObject Detection An Overview
Object Detection An Overview
 
Launching into machine learning
Launching into machine learningLaunching into machine learning
Launching into machine learning
 
An analysis of_machine_and_human_analytics_in_classification
An analysis of_machine_and_human_analytics_in_classificationAn analysis of_machine_and_human_analytics_in_classification
An analysis of_machine_and_human_analytics_in_classification
 
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
 
To identify the person using gait knn based approach
To identify the person using gait   knn based approachTo identify the person using gait   knn based approach
To identify the person using gait knn based approach
 
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...
【ISVC2015】Evaluation of Vision-based Human Activity Recognition in Dense Traj...
 
Fast Human Detection in Surveillance Video
Fast Human Detection in Surveillance VideoFast Human Detection in Surveillance Video
Fast Human Detection in Surveillance Video
 
A novel enhanced algorithm for efficient human tracking
A novel enhanced algorithm for efficient human trackingA novel enhanced algorithm for efficient human tracking
A novel enhanced algorithm for efficient human tracking
 

Kürzlich hochgeladen

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
 
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
 
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
 
🐬 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
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
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
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
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
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
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
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
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
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 

Kürzlich hochgeladen (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
 
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
 
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
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
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...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
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...
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
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
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
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
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 

Digest of Human Detection from CVPR2015

  • 1. Digest of Human Detection from CVPR 2015 Jan. 27th, 2016, Daichi SUZUO
  • 2. Digest of Human Detection from CVPR2015 Features 1. Combination Features and Models for Human Detection - Y. Jiang et al. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al. Training 3. Learning Scene-Specific Pedestrian Detectors without Real Data - H.Hattori et al. 4. Taking a Deeper Look at Pedestrians - J. Hosang et al. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Dataset / Benchmark 6. Multispectral Pedestrian Detection : Benchmark Dataset and Baseline - S. Hwang et al.
  • 3. Fundamentals of Human Detection • Machine learning based bi-class classifier • Sliding window search Negative class Positive class Convert to image feature Training Classifier Classifier Crop Feature extraction Human? Not human?
  • 4. Image features 1. Combination Features and Models for Human Detection - Y. Jiang et al. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al.
  • 5. θ 1. Combination Features and Models for Human Detection - Y. Jiang et al. • Popular HOG feature[Dalal05] Input image Edge-image Edge extraction (“cell”) pixel-wise gradient power Histogram
  • 6. θ • Popular HOG feature[Dalal05]: 1st order feature power Input image 1st derivative Differentiate Histogram (“cell”) pixel-wise gradient idea: How about extending to 0-th/2nd order? 1. Combination Features and Models for Human Detection - Y. Jiang et al.
  • 7. 1. Combination Features and Models for Human Detection - Y. Jiang et al. • 2nd order: HOB – “bar” shape • Same as HOG, just using 2nd derivative • 0th order: HOC – color feature • Using HSI color space; H as θ, S as power ignore I convert to HSI R G V
  • 8. 1. Combination Features and Models for Human Detection - Y. Jiang et al. • Combine them into one vector: HOG-III feature
  • 9. 1. Combination Features and Models for Human Detection - Y. Jiang et al. • Train different classifiers from the same HOG-IIIs • Detect individually, and fuse into one result Input image HOG-III features Detection by Grammar model[Girshick11] Detection by Poselet model[Bourdev10] Fusion Final result (This is one of the key process of the method Please refer the original paper for more details)
  • 10. 1. Combination Features and Models for Human Detection - Y. Jiang et al. Effect of HOG-III Effect of Fusion Feature AP HOG 45.8% HOC+HOG+HOB 50.1% HOG-III 51.3% Classifier AP Single use of Grammer 45.8% Single use of Poselet 47.0% Fusion 52.3% Combining HOG-III and Fusion performs best
  • 11. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al. • Extension of “Integral Channel Features” [Dollár09] • ChnFtrs: Extension of “Viola-Jones method” [Viola02] (Viola-Jones method) … … … Input image Learn decision-tree by AdaBoost Extract “Haar-like” Features (scalar) ※Sum of difference between white and black region
  • 12. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al. • Extension of “Integral Channel Features” [Dollár09] • ChnFtrs: Extension of “Viola-Jones method” [Viola02] (Integral Channel Features) … … … Input image Learn decision-tree by AdaBoost “channel” Extract sum of rectangle ※Unlike Haar-like Transform
  • 13. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al. • Extension of “Integral Channel Features” [Dollár09] • ChnFtrs: Extension of “Viola-Jones method” [Viola02] (Filtered Channel Features) … … … Learn decision-tree by AdaBoost “channel” Apply various filters (convolution) … * * Pick-up pixel value as a feature …
  • 14. 2. Filtered Channel Features for Pedestrian Detection - S. Zhang et al. Using 50 filters performs bestAchieved the highest accuracy
  • 15. Training 3. Learning Scene-Specific Pedestrian Detectors without Real Data - H. Hattori et al. 4. Taking a Deeper Look at Pedestrians - J. Hosang et al. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al.
  • 16. • Train detector by CG-based training datasets 3. Learning Scene-Specific Pedestrian Detectors without Real Data - H. Hattori et al. Real background (static image) annotate CG-based human composite Simulated scene
  • 17. • Not only scene-specific, but also location-specific! 3. Learning Scene-Specific Pedestrian Detectors without Real Data - H. Hattori et al. … Classifier Classifier … Grid with overwrap (102~105 patches) Training images (~103 pos, ~103 neg for each patch) Joint Classifier Ensemble Training Scene-specific Location-specific detectors
  • 18. 3. Learning Scene-Specific Pedestrian Detectors without Real Data - H. Hattori et al. Patch size # detectors Avg. Precision 8x8 371 .802 16x16 102 .798 32x32 30 .764 Effect of location-specific detection Example of the detection result Comparison
  • 19. “convnet still underperforms state-of-the-arts” …Really? Enhance know-how of convnet based detector 4. Taking a Deeper Look at Pedestrians - J. Hosang et al. • Small network (CifarNet) / Big network (AlexNet) • Window size • How to collect training images • Fine-tuning • Number and Type of layers • …
  • 20. 4. Taking a Deeper Look at Pedestrians - J. Hosang et al. Convnet with the best configuration outperforms! Interesting points: • Ratio of pos/neg does not affect to the accuracy so much • Data-augumentation is effective • Network size should be chosen by the amount of training samples • ...
  • 21. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Binary-classification is sometimes insufficient… Human Not human (Hard negatives) It is necessary to use semantic information jointly
  • 22. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Classify pedestrian and Recognize semantic at once!
  • 23. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Classify pedestrian and Recognize semantic at once! Also recognizes current scene semantics • Pedestrian attribute (e.g. wearing backpack) • Background attribute (e.g. road, sky, …)
  • 24. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Classify pedestrian and Recognize semantic at once! Difficult to collect various (annotated) negs from one dataset… Transfer from other annotated datasets by TA-CNN (Please refer the original and related papers for more details about TA-CNN…)
  • 25. 5. Pedestrian Detection aided by Deep Learning Semantic Tasks - Y. Tian et al. Comparison with CNN-based methods Example of detection results
  • 26. Benchmark / Dataset 6. Multispectral Pedestrian Detection : Benchmark Dataset and Baseline - S. Hwang et al.
  • 27. • Dataset of visible-light and thermal image 6. Multispectral Pedestrian Detection : Benchmark Dataset and Baseline - S. Hwang et al. Contributions: • Color and thermal images • Both test/training data • Temporally-corresponded tag • Large enough • …
  • 29. • Human detection is still challenging • Deep learning does not necessarily solve every problems at this moment  • There are several knowledge that might be helpful for your research/hobby/… Takeaways
  • 31. 1. Filtered channel features for pedestrian detection 4. Taking a Deeper Look at Pedestrians • Author's website: http://rodrigob.github.io/ 3. Learning Scene-Specific Pedestrian Detectors without Real Data • Project: http://vishnu.boddeti.net/projects/detection-by-synthesis.html • YouTube: https://youtu.be/2Jf7faozHUs 5. Pedestrian Detection aided by Deep Learning Semantic Tasks • Project: http://mmlab.ie.cuhk.edu.hk/projects/TA-CNN/ 6. Multispectral Pedestrian Detection: Benchmark Dataset and Baseline • Lab: http://rcv.kaist.ac.kr/v2/ And all the papers of CVPR2015 are available at cv-foundation.org See also

Hinweis der Redaktion

  1. https://en.wikipedia.org/wiki/File:Lenna.png
  2. https://pixabay.com/en/newcastle-upon-tyne-england-road-594165/
  3. Then, let us go to the main topics. The first group is about image features, there are 2 papers. Why are features important? Good feature suppresses useless change of images, like lightning conditions, while keeping enough information. This is kind of a trade-off, where the difficulty comes from.
  4. The principle of good detector is; If the training dataset can be collected from exactly same scene as the detection time, the detector will surely outperform the general detector trained by common training data. But data-annotation is really heavy task, although it is necessary to create training dataset. The basic idea of the paper is generation of training data by combination of actual background and CG-generated people. This approach is called “generative learning”.
  5. https://twitter.com/hirokatukataoka/status/592874061170135040
  6. https://twitter.com/hirokatukataoka/status/592874061170135040 あと表2もはる。Location specificにするとよくなること。
  7. Then, let us go to the main topics. The first group is about image features, there are 2 papers. Why are features important? Good feature suppresses useless change of images, like lightning conditions, while keeping enough information. This is kind of a trade-off, where the difficulty comes from.
  8. ・色やサーマル単独だったらあるけど同時提供は初。などなど
  9. Then, let us go to the main topics. The first group is about image features, there are 2 papers. Why are features important? Good feature suppresses useless change of images, like lightning conditions, while keeping enough information. This is kind of a trade-off, where the difficulty comes from.
  10. ・色やサーマル単独だったらあるけど同時提供は初。などなど
  11. Then, let us go to the main topics. The first group is about image features, there are 2 papers. Why are features important? Good feature suppresses useless change of images, like lightning conditions, while keeping enough information. This is kind of a trade-off, where the difficulty comes from.