Detection of articulated objects such as humans is an important task in computer vision. We present a system that incorporates a variety of constraints in a unified multiview framework to automatically detect humans in possibly crowded scenes. These constraints include the kinematic constraints, the occlusion of one part by another and the high correlation between the appearance of parts such as the two arms. The graphical structure (non-tree) obtained is optimized in a nonparametric belief propagation framework using prior based search. © 2006 IEEE.

Anurag Mittal

Department of Computer Science and Engineering

Abhinav Gupta

Larry S. Davis

Data visualization

Object detection

Three dimensional computer graphics

Visualization

ARTICULATED OBJECT

GRAPHICAL STRUCTURES

Kinematic constraints

MULTI-VIEWS

NON-PARAMETRIC BELIEF PROPAGATION

ONE PARTS

Pose estimation

SELF OCCLUSION

Data handling

IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Constraint Integration for Multiview Pose Estimation of Humans with Self-Occlusions

Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

Automatic initialization and tracking of human pose is an important task in visual surveillance. We present a part-based approach that incorporates a variety of constraints in a unified framework. These constraints include the kinematic constraints between parts that are physically connected to each other, the occlusion of one part by another and the high correlation between the appearance of certain parts, such as the arms. The location probability distribution of each part is determined by evaluating appropriate likelihood measures. The graphical (non-tree) structure representing the interdependencies between parts is utilized to "connect" such part distributions via nonparametric belief propagation. Methods are also developed to perform this optimization efficiently in the large space of pose configurations. © 2008 IEEE.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Constraint integration for efficient multiview pose estimation with self-occlusions

Development of multiple camera based vision systems for analysis of dynamic objects such as humans is challenging due to occlusions and similarity in the appearance of a person with the background and other people- visual "confusion". Since occlusion and confusion depends on the presence of other people in the scene, it leads to a dependency structure where there are often loops in the resulting Bayesian network. While approaches such as loopy belief propagation can be used for inference, they are computationally expensive and convergence is not guaranteed in many situations. We present a unified approach, COST, that reasons about such dependencies and yields an order for the inference of each person in a group of people and a set of cameras to be used for inferences for a person. Using the probabilistic distribution of the positions and appearances of people, COST performs visibility and confusion analysis for each part of each person and computes the amount of information that can be computed with and without more accurate estimation of the positions of other people. We present an optimization problem to select set of cameras and inference dependencies for each person which attempts to minimize the computational cost under given performance constraints. Results show the efficiency of COST in improving the performance of such systems and reducing the computational resources required. ©2007 IEEE.

Proceedings of the IEEE International Conference on Computer Vision

COST: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes

Constraint integration for multiview pose estimation of humans with self-occlusions

Journal	Data powered by TypesetProceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Publisher	Data powered by TypesetIEEE Computer Society
Open Access	No