Marco Pedersoli, Jordi Gonzàlez, Xu Hu, and Xavier Roca

Slides:



Advertisements
Similar presentations
Presenter: Duan Tran (Part of slides are from Pedro’s)
Advertisements

Ľubor Ladický1 Phil Torr2 Andrew Zisserman1
Classification using intersection kernel SVMs is efficient Joint work with Subhransu Maji and Alex Berg Jitendra Malik UC Berkeley.
Fitting: The Hough transform. Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not.
Large Scale Visual Recognition Challenge (ILSVRC) 2013: Detection spotlights.
Lecture 31: Modern object recognition
LPP-HOG: A New Local Image Descriptor for Fast Human Detection Andy Qing Jun Wang and Ru Bo Zhang IEEE International Symposium.
Many slides based on P. FelzenszwalbP. Felzenszwalb General object detection with deformable part-based models.
Presenter: Hoang, Van Dung
Steerable Part Models Hamed Pirsiavash and Deva Ramanan
AdaBoost & Its Applications
Face detection Many slides adapted from P. Viola.
EE462 MLCV Lecture 5-6 Object Detection – Boosting Tae-Kyun Kim.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Detecting Pedestrians by Learning Shapelet Features
Vision-Based Analysis of Small Groups in Pedestrian Crowds Weina Ge, Robert T. Collins, R. Barry Ruback IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE.
More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb.
Student: Yao-Sheng Wang Advisor: Prof. Sheng-Jyh Wang ARTICULATED HUMAN DETECTION 1 Department of Electronics Engineering National Chiao Tung University.
Fitting: The Hough transform
Recognition using Regions CVPR Outline Introduction Overview of the Approach Experimental Results Conclusion.
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Generic Object Detection using Feature Maps Oscar Danielsson Stefan Carlsson
Ensemble Tracking Shai Avidan IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE February 2007.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Fast Human Detection Using a Novel Boosted Cascading Structure With Meta Stages Yu-Ting Chen and Chu-Song Chen, Member, IEEE.
Presenter: Stefan Zickler
1 REAL-TIME IMAGE PROCESSING APPROACH TO MEASURE TRAFFIC QUEUE PARAMETERS. M. Fathy and M.Y. Siyal Conference 1995: Image Processing And Its Applications.
Generic object detection with deformable part-based models
Face Alignment Using Cascaded Boosted Regression Active Shape Models
A coarse-to-fine approach for fast deformable object detection Marco Pedersoli Andrea Vedaldi Jordi Gonzàlez.
Olga Zoidi, Anastasios Tefas, Member, IEEE Ioannis Pitas, Fellow, IEEE
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
A General Framework for Tracking Multiple People from a Moving Camera
“Secret” of Object Detection Zheng Wu (Summer intern in MSRNE) Sep. 3, 2010 Joint work with Ce Liu (MSRNE) William T. Freeman (MIT) Adam Kalai (MSRNE)
Face detection Slides adapted Grauman & Liebe’s tutorial
Object Detection with Discriminatively Trained Part Based Models
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
Pedestrian Detection and Localization
Deformable Part Model Presenter : Liu Changyu Advisor : Prof. Alex Hauptmann Interest : Multimedia Analysis April 11 st, 2013.
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Deformable Part Models (DPM) Felzenswalb, Girshick, McAllester & Ramanan (2010) Slides drawn from a tutorial By R. Girshick AP 12% 27% 36% 45% 49% 2005.
Perceptual and Sensory Augmented Computing Discussion Session: Sliding Windows Sliding Windows – Silver Bullet or Evolutionary Deadend? Alyosha Efros,
Recognition II Ali Farhadi. We have talked about Nearest Neighbor Naïve Bayes Logistic Regression Boosting.
Learning Object Representation Andrej Lúčny Department of Applied Informatics Faculty of Mathematics, Physics and Informatics Comenius University, Bratislava.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Project 3 Results.
Training and Evaluating of Object Bank Models Presenter : Changyu Liu Advisor : Prof. Alex Interest : Multimedia Analysis May 16 th, 2013.
Histograms of Oriented Gradients for Human Detection(HOG)
Jiu XU, Axel BEAUGENDRE and Satoshi GOTO Computer Sciences and Convergence Information Technology (ICCIT), th International Conference on 1 Real-time.
Human Detection Method Combining HOG and Cumulative Sum based Binary Pattern Jong Gook Ko', Jin Woo Choi', So Hee Park', Jang Hee You', ' Electronics and.
CS 1699: Intro to Computer Vision Detection II: Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 12, 2015.
Object Detection Overview Viola-Jones Dalal-Triggs Deformable models Deep learning.
Pictorial Structures and Distance Transforms Computer Vision CS 543 / ECE 549 University of Illinois Ian Endres 03/31/11.
Face Detection Using Neural Network By Kamaljeet Verma ( ) Akshay Ukey ( )
776 Computer Vision Jan-Michael Frahm Spring 2012.
More sliding window detection: Discriminative part-based models
A Discriminatively Trained, Multiscale, Deformable Part Model Yeong-Jun Cho Computer Vision and Pattern Recognition,2008.
Cascade for Fast Detection
Object detection with deformable part-based models
Performance of Computer Vision
Lit part of blue dress and shadowed part of white dress are the same color
Yun-FuLiu Jing-MingGuo Che-HaoChang
Object detection as supervised classification
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
A Tutorial on HOG Human Detection
An HOG-LBP Human Detector with Partial Occlusion Handling
“The Truth About Cats And Dogs”
University of Central Florida
Presentation transcript:

Marco Pedersoli, Jordi Gonzàlez, Xu Hu, and Xavier Roca Toward Real-Time Pedestrian Detection Based on a Deformable Template Model Marco Pedersoli, Jordi Gonzàlez, Xu Hu, and Xavier Roca IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 15, NO. 1, FEBRUARY 2014 355

Outline Introduction Related work Methods Experiment Result Conclusion System Overview CtF Search(Course to Fine) Ctf Search With Deformations Small Pedestrians Experiment Result Conclusion

Introduction In this paper, we deal with pedestrian detection using a single camera mounted on the vehicle. Pedestrian is hard to detect because… Pedestrians have a much broader appearance variability than other objects. Pedestrian detection is much more error critical.

Introduction High accuracy techniques need plenty of time. Some speedups can be achieved by restricting detection.

Introduction We use a multiresolution representation and the coarse-to-fine (CtF) strategy to speed up the search. Add a binary variable to detect small pedestrian.

Related work In more recent years, object detection has shown great improvements. It is possible to detect pedestrians using single images. In the template matching(TM) model, an object is represented by a learned template. Recent examples of detectors based on this technique can be found in [5] and [20]–[22].

Related work [5] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627–1645, Sep. 2010. [20] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE CVPR, 2005, pp. 886–893. [21] A. Vedaldi and A. Zisserman, “Structured output regression for detection with partial occlusion,” in Proc. NIPS, 2009, pp. 1–9. [22] L. Zhu, Y. Chen, A. Yuille, and W. Freeman, “Latent hierarchical structural learning for object detection,” in Proc. IEEE CVPR, 2010, pp. 1062–1069.

Related work In [29], a cascade of parts to speed up deformable object detection is proposed. [29] P. F. Felzenszwalb, R. Girshick, and D. McAllester, “Cascade object detection with deformable part models,” in Proc. IEEE CVPR, 2010, pp. 2241–2248.

Related work In [30], the authors propose to use GPU computation and ground- plane constraints to also obtain a real-time system for pedestrian detection. [30] P. Sudowe and B. Leibe, “Efficient use of geometric constraints for sliding-window object detection in video,” in Proc. ICVS, 2011, pp. 11– 20.

Proposed methods - System Overview Given an image, we precompute the HOG features of the image at different resolutions, obtaining a pyramid of HOGs. 2. The pyramid is scanned at all resolutions in a CtF way, finding the locations that are the most similar to the template. 3. These locations are further processed by applying nonmaximum suppression (NMS) to the overlapping ones.

Proposed methods - System Overview

Course to Fine(CtF) Search The standard procedure to find an object in the image consists of evaluating the similarity between the object model and the image features at every location and scale in the image. M: Object Model , H: HOG feature x = (x, y, s), where x and y are the coordinates of the window and s is its scale

Course to Fine(CtF) Search The complete scan over positions and scales is very expensive. CtF search can save computation but still obtain results very similar to the complete search.

Course to Fine(CtF) Search The key idea is to decompose the search over multiple resolutions, i.e., from coarse and then fine.

Course to Fine(CtF) Search The score of the multiple-resolution detector is computed as sum over resolutions r of the object model Mr with the corresponding features H.

Course to Fine(CtF) Search

CtF Search With Deformations Object deformations may be produced by viewpoint changes or articulated movements such as limb movements. Adding moving parts allows the detector to better adapt to local object deformations.

CtF Search With Deformations In the object model, each resolution level is further divided into parts.

CtF Search With Deformations dx and dy that represent the displacement of a part p with respect to its father.

Small Pedestrians Detecting far pedestrian gives enough time for a proper action to avoid collision. Pedestrians far from the vehicle correspond to low-resolution pedestrians. When the number of pixels representing an object is low, the ability to recognize the object is highly reduced.

Small Pedestrians In CtF search a small instance object does not have fine-resolution features, but it still has the coarse representation. As the resolution goes high , the HOG feature may disappear, and the missing high resolution features are set to zero. In this way detections of small objects would have a score that is lower.

Small Pedestrians To overcome this, the score is computed as hr is a binary variable. When the corresponding HOG features H(xr,p) are missing and therefore set to 0. That makes scores of detections generated without high-resolution features.

Experiment Result We evaluate our method on the Computer Vision Center (CVC)-02 data set, which is a data set specific for pedestrian detection in the context of driving assistance.

Experiment Result CtF configuration with deformations and “resolution” feature activated. (False Positive Per Image)

Experiment Result- Rigid Versus Deformable Models Average precision ↑ but needs more time

Experiment Result - CtF Versus Complete Search Compared with complete search, the scan time ↓ and the average precision is almost the same.

Experiment result - Detection of Small Pedestrians

Conclusion This method is based on the combination of recent state-of-the art techniques for fast and accurate object detection. Three useful techniques mentioned make this method perform well.