Constraint Integration for Efficient Multiview Pose Estimation with Self-Occlusions

Authors:
Abhinav Gupta;Anurag Mittal;Larry S. Davis
Affiliations:
-;-;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2008

Citing 0
Cited 16

State-of-the-art on spatio-temporal information-based video retrieval

Pattern Recognition
Active Contour Tracking of Moving Objects Using Edge Flows and Ant Colony Optimization in Video Sequences

PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Recovery of upper body poses in static images based on joints detection

Pattern Recognition Letters
A Study of Parts-Based Object Class Detection Using Complete Graphs

International Journal of Computer Vision
A Study on Smoothing for Particle-Filtered 3D Human Body Tracking

International Journal of Computer Vision
Quasi Monte Carlo partitioned filtering for visual human motion capture

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Wireless smart camera network for real-time human 3D pose reconstruction

Computer Vision and Image Understanding
Self-occlusion handling for human body motion tracking from 3D ToF image sequence

Proceedings of the 1st international workshop on 3D video processing
Real time multiple people tracking and pose estimation

Proceedings of the 1st ACM international workshop on Multimodal pervasive video analysis
Integrating multiple uncalibrated views for human 3D pose estimation

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
Finding human poses in videos using concurrent matching and segmentation

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

Applied Intelligence
Multiple people tracking and pose estimation with occlusion estimation

Computer Vision and Image Understanding
Adaptive occlusion state estimation for human pose tracking under self-occlusions

Pattern Recognition
Tracking in action space

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Tracking in object action space

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.14

Visualization

Abstract

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