Using middle level features for robust shape tracking
Pattern Recognition Letters
Articulated Model Based People Tracking Using Motion Models
ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Tracking of deformable human hand in real time as continuous input for gesture-based interaction
Proceedings of the 12th international conference on Intelligent user interfaces
3D shape-encoded particle filter for object tracking and its application to human body tracking
Journal on Image and Video Processing - Anthropocentric Video Analysis: Tools and Applications
Applications of a simple characterization of human gait in surveillance
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on gait analysis
Augmenting video surveillance footage with virtual agents for incremental event evaluation
Pattern Recognition Letters
| Hi-index | 0.00 |
Extracting human representations from video has vast applications. In this paper, we present a knowledge-based framework to capture metarepresentations for real-life video with human walkers. The system models the human body as an articulated object and the human walking as a cyclic activity with highly correlated temporal patterns. We extract for each of the body parts its motion, shape, and texture. Once available, this structural information can be used to manipulate or synthesize the original video sequence, or animate the walker with a different motion in a new synthesized video