The visual analysis of human movement: a survey
Computer Vision and Image Understanding
Parametric Hidden Markov Models for Gesture Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Recognition of Human Movement Using Temporal Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning and Recognizing Human Dynamics in Video Sequences
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Motion synthesis from annotations
ACM SIGGRAPH 2003 Papers
Actions Sketch: A Novel Action Representation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A data-driven approach to quantifying natural human motion
ACM SIGGRAPH 2005 Papers
Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Learning dynamics for exemplar-based gesture recognition
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Unsupervised view and rate invariant clustering of video sequences
Computer Vision and Image Understanding
Object-object interaction affordance learning
Robotics and Autonomous Systems
Hi-index | 0.00 |
Common movements like reaching, striking, etc. observed during surveillance have highly variable target locations. This puts appearance-based techniques at a disadvantage for modelling and recognizing them. Psychological studies indicate that these actions are ballistic in nature. Their trajectories have simple structures and are determined to a great degree by the starting and ending positions. We present an approach for movement recognition that explicitly considers their ballistic nature. This enables the decoupling of recognition from the movement's trajectory, allowing generalization over a range of target-positions. A given movement is first analyzed to determine if it is ballistic. Ballistic movements are further classified into reaching, striking, etc. The proposed approach was tested with motion capture data obtained from the CMU MoCap database