Robust Real-Time Periodic Motion Detection, Analysis, and Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Trainable System for Object Detection
International Journal of Computer Vision - special issue on learning and vision at the center for biological and computational learning, Massachusetts Institute of Technology
The Recognition of Human Movement Using Temporal Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Detection and Tracking of Human Motion with a View-Based Representation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Learning and Recognizing Human Dynamics in Video Sequences
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Unsupervised Learning of Human Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Pedestrians Using Patterns of Motion and Appearance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Priors for People Tracking from Small Training Sets
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Unsupervised Bayesian Detection of Independent Motion in Crowds
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle
International Journal of Computer Vision
International Journal of Computer Vision
Human pose tracking using multi-level structured models
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Estimating pose of articulated objects using low-level motion
Computer Vision and Image Understanding
Hi-index | 0.00 |
We present an approach for articulated motion detection and pose estimation that uses only motion information. To estimate the pose and viewpoint we introduce a novel motion descriptor that computes the spatial relationships of motion vectors representing various parts of the person using the trajectories of a number of sparse points. A nearest neighbor search for the closest motion descriptor from the labeled training data of human walking poses in multiple views is performed. This observational probability is fed to a Hidden Markov Model defined over multiple poses and viewpoints to obtain temporally consistent pose estimates. Experimental results on various sequences of walking subjects with multiple viewpoints demonstrate the effectiveness of the approach. In particular, our purely motion-based approach is able to track people even when other visible cues are not available, such as in low-light situations.