A Scale and Rotation Invariant Approach to Tracking Human Body Part Regions in Videos Yihang BoHao Jiang Institute of Automation, CAS Boston College.

Slides:



Advertisements
Similar presentations
Shape Context and Chamfer Matching in Cluttered Scenes
Advertisements

1 Hierarchical Part-Based Human Body Pose Estimation * Ramanan Navaratnam * Arasanathan Thayananthan Prof. Phil Torr * Prof. Roberto Cipolla * University.
CVPR2013 Poster Modeling Actions through State Changes.
Learning Shared Body Plans Ian Endres University of Illinois work with Derek Hoiem, Vivek Srikumar and Ming-Wei Chang.
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
Analysis of Contour Motions Ce Liu William T. Freeman Edward H. Adelson Computer Science and Artificial Intelligence Laboratory Massachusetts Institute.
Motion Coherent Tracking with Multi-Label MRF Optimization David Tsai Matthew Flagg James M. Rehg Computational Perception Lab School of Interactive Computing.
Shape Sharing for Object Segmentation
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
- Recovering Human Body Configurations: Combining Segmentation and Recognition (CVPR’04) Greg Mori, Xiaofeng Ren, Alexei A. Efros and Jitendra Malik -
Face Alignment with Part-Based Modeling
3/5/2002Phillip Saltzman Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997.
2.Our Framework 2.1. Enforcing Temporal Consistency by Post Processing  Human Detection from Yang and Ramanan [1] Articulated Pose Estimation using Flexible.
Silhouette Lookup for Automatic Pose Tracking N ICK H OWE.
Face Alignment at 3000 FPS via Regressing Local Binary Features
Convex Quadratic Programming for Object Location Hao Jiang, Mark S. Drew and Ze-Nian Li School of Computing Science Simon Fraser University.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
Robust Object Tracking via Sparsity-based Collaborative Model
2D Human Pose Estimation in TV Shows Vittorio Ferrari Manuel Marin Andrew Zisserman Dagstuhl Seminar July 2008.
Enhancing Exemplar SVMs using Part Level Transfer Regularization 1.
Student: Yao-Sheng Wang Advisor: Prof. Sheng-Jyh Wang ARTICULATED HUMAN DETECTION 1 Department of Electronics Engineering National Chiao Tung University.
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
Tracking Objects with Dynamics Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 04/21/15 some slides from Amin Sadeghi, Lana Lazebnik,
Segmentation and Tracking of Multiple Humans in Crowded Environments Tao Zhao, Ram Nevatia, Bo Wu IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,
CS335 Principles of Multimedia Systems Content Based Media Retrieval Hao Jiang Computer Science Department Boston College Dec. 4, 2007.
Detecting and Tracking Moving Objects for Video Surveillance Isaac Cohen and Gerard Medioni University of Southern California.
High-Quality Video View Interpolation
CVPR 2006 New York City Granularity and Elasticity Adaptation in Visual Tracking Ming Yang, Ying Wu NEC Laboratories America Cupertino, CA 95014
MSRI University of California Berkeley 1 Recovering Human Body Configurations using Pairwise Constraints between Parts Xiaofeng Ren, Alex Berg, Jitendra.
Linear Solution to Scale and Rotation Invariant Object Matching Professor: 王聖智 教授 Student : 周 節.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
REALTIME OBJECT-OF-INTEREST TRACKING BY LEARNING COMPOSITE PATCH-BASED TEMPLATES Yuanlu Xu, Hongfei Zhou, Qing Wang*, Liang Lin Sun Yat-sen University,
Generic object detection with deformable part-based models
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
I. Making Observations- Observations can be made several different ways. Observations can be put into two different categories; qualitative and quantitative.
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
Motion Object Segmentation, Recognition and Tracking Huiqiong Chen; Yun Zhang; Derek Rivait Faculty of Computer Science Dalhousie University.
Vision System for Wing Beat Analysis of Bats in the Wild 1 Boston University Department of Computer Science 2 Boston University Department of Biology Mikhail.
Characterizing activity in video shots based on salient points Nicolas Moënne-Loccoz Viper group Computer vision & multimedia laboratory University of.
Object Based Video Coding - A Multimedia Communication Perspective Muhammad Hassan Khan
13 th International Fall Workshop VISION, MODELING, AND VISUALIZATION 2008 October 8-10, 2008 Konstanz, Germany Strike a Pose Image-Based Pose Synthesis.
Multiscale Symmetric Part Detection and Grouping Alex Levinshtein, Sven Dickinson, University of Toronto and Cristian Sminchisescu, University of Bonn.
Meeting 12, Th 7:20PM-10PM Image Processing with Applications-CSCI567/MATH563/MATH489 Meeting 12 Continuation meeting 11: Theoretical derivation of the.
Detecting Curved Symmetric Parts using a Deformable Disc Model Tom Sie Ho Lee, University of Toronto Sanja Fidler, TTI Chicago Sven Dickinson, University.
Learning Collections of Parts for Object Recognition and Transfer Learning University of Illinois at Urbana- Champaign.
Qiaochu Li, Qikun Guo, Saboya Yang and Jiaying Liu* Institute of Computer Science and Technology Peking University Scale-Compensated Nonlocal Mean Super.
Template matching and object recognition. CS8690 Computer Vision University of Missouri at Columbia Matching by relations Idea: –find bits, then say object.
Tracking People by Learning Their Appearance Deva Ramanan David A. Forsuth Andrew Zisserman.
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
DETECTING AND TRACKING TRACTOR-TRAILERS USING VIEW-BASED TEMPLATES Masters Thesis Defense by Vinay Gidla Apr 19,2010.
Pictorial Structures and Distance Transforms Computer Vision CS 543 / ECE 549 University of Illinois Ian Endres 03/31/11.
Category Independent Region Proposals Ian Endres and Derek Hoiem University of Illinois at Urbana-Champaign.
1 Scale and Rotation Invariant Matching Using Linearly Augmented Tree Hao Jiang Boston College Tai-peng Tian, Stan Sclaroff Boston University.
Journal of Visual Communication and Image Representation
Using decision trees to build an a framework for multivariate time- series classification 1 Present By Xiayi Kuang.
Linear Solution to Scale and Rotation Invariant Object Matching Hao Jiang and Stella X. Yu Computer Science Department Boston College.
Stereo Video 1. Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos 2. Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral.
Tracking Objects with Dynamics
LOCUS: Learning Object Classes with Unsupervised Segmentation
Nonparametric Semantic Segmentation
Paper Presentation: Shape and Matching
Dynamical Statistical Shape Priors for Level Set Based Tracking
A New Approach to Track Multiple Vehicles With the Combination of Robust Detection and Two Classifiers Weidong Min , Mengdan Fan, Xiaoguang Guo, and Qing.
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Brief Review of Recognition + Context
Online Graph-Based Tracking
Liyuan Li, Jerry Kah Eng Hoe, Xinguo Yu, Li Dong, and Xinqi Chu
Presentation transcript:

A Scale and Rotation Invariant Approach to Tracking Human Body Part Regions in Videos Yihang BoHao Jiang Institute of Automation, CAS Boston College

Challenges

Previous Rectangular Part Methods Templates with Different scales Templates with Different rotations If the target scale and rotation are unknown, local part extraction becomes a very slow process.

Solution: Finding Body Part Regions

Overview of the Method  We track human body part regions (arm, leg and torso) in videos.  Our model considers spatial and temporal coupling among parts.  It is invariant to scale and rotation.

Tracking Body Part Regions

The Non-tree Model Body part coupling between two successive video frames

Part Region Candidates Object class independent Region Proposals Object class independent Region Proposals Superpixels Ian Endres, and Derek Hoiem, “Category Independent Object Proposals”, ECCV P.F. Felzenszwalb and D.P. Huttenlocher, Efficient Graph-Based Image Segmentation International Journal of Computer Vision, Volume 59, Number 2, September 2004.

3D Superpixels Video segmentation (3D superpixels) usually do not directly give human part regions.

Partial Background Removal (Optional) warping ……

Criteria Shape Matching Part Distance Part Overlap Relative Ratio Shape Changes Position Changes Appearance Changes

Distance Term

Overlap Region Overlap Region Overlap

Size Ratio Part Size Ratio

Shape Consistency Across Frames Shape Consistency

Motion Smoothness Motion Continuity

Color Consistency Appearance Consistency

Inference on a Loopy Graph … We assign region candidates to each of the body part node so that the objective function is minimized.

Convert to a Chain … … Linear meta-graph

Convert to a Chain … … Unfortunately, there are too many whole body configurations in each video frame.

Convert to a Chain … … Solution: we find the best-N whole body configurations in each video frame.

Cycle Removal

Cycle Breaking

Find Best-N Body Configurations on a Cycle Best-N (with torso1) Best-N (with torso2) + Best-N (with torso1,2) Best-N (with torso3) + Best-N (with torso1,2,3) … Best-N (with torso M) + Best-N (with torso1..M)

Region Tracking on a Trellis Frame 1Frame 2Frame k Best-N Body configurations

Sample Results on Five Test Videos V1 V2 V3 V4 V5

Comparison Result [N-best] D. Park, D. Ramanan. "N-Best Maximal Decoders for Part Models”, ICCV 2011.

Quantitative results Comparison Result

Conclusion By tracking body part regions, we can achieve efficient scale and rotation invariant human pose tracking. This method can be used for human tracking in complex sports videos.

Thank You