Segmentation and Tracking of Interacting Human Body Parts under Occlusion and Shadowing

Authors:
Sangho Park;J. K. Aggarwal
Affiliations:
-;-
Venue:
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
Year:
2002

Citing 0
Cited 13

Recognition of two-person interactions using a hierarchical Bayesian network

IWVS '03 First ACM SIGMM international workshop on Video surveillance
Segmentation and tracking of multiple video objects

Pattern Recognition
A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Robust Object Tracking Via Online Dynamic Spatial Bias Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Foreground Segmentation via Segments Tracking

ICCVG 2008 Proceedings of the International Conference on Computer Vision and Graphics: Revised Papers
Video retrieval of human interactions using model-based motion tracking and multi-layer finite state automata

CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Human motion tracking by combining view-based and model-based methods for monocular video sequences

ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartIII
Segmentation of human body parts using deformable triangulation

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
Performance Comparison of Back Propagation Neural Network and Self Organization Map for Face Detection

Proceedings of the 7th International Conference on Frontiers of Information Technology
Moving human detection and recognition in videos using adaptive method and support vector machine

Proceedings of the 7th International Conference on Frontiers of Information Technology
Adaptive model-based multi-person tracking

CIS'04 Proceedings of the First international conference on Computational and Information Science
Real time tracking of multiple persons on colour image sequences

ACIVS'05 Proceedings of the 7th international conference on Advanced Concepts for Intelligent Vision Systems
Intelligent tracking persons through non-overlapping cameras

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a system to segment and track multiple bodyparts of interacting humans in the presence of mutual occlusion andshadow. The color image sequence is processed at three levels: pixellevel, blob level, and object level. A Gaussian mixture model is used atthe pixel level to train and classify individual pixel colors. MarkovRandom Field (MRF) framework is used at the blob level to merge thepixels into coherent blobs and to register inter-blob relations. Acoarse model of the human body is applied at the object level asempirical domain knowledge to resolve ambiguity due to occlusionand to recover from intermittent tracking failures. A two-fold trackingscheme is used which consists of blob to blob matching in consecutiveframes and blob to body part association within a frame. The trackingscheme resembles a multi-target, multi-assignment framework. Theresult is a tracking system that simultaneously segments and tracksmultiple body parts of interacting people. Example sequences illustratethe success of the proposed paradigm.