Design and Use of Linear Models for Image Motion Analysis
International Journal of Computer Vision
Probabilistic Detection and Tracking of Motion Boundaries
International Journal of Computer Vision - Special issue on Genomic Signal Processing
Qualitative Spatiotemporal Analysis Using an Oriented Energy Representation
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Bayesian inference of visual motion boundaries
Exploring artificial intelligence in the new millennium
Motion Feature Detection Using Steerable Flow Fields
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
The paper presents a model of image segmentation that can distinguish foreground from background purely on the basis of motion information. The main processing steps involved are: detection of motion boundaries, and analysis of figure ground relationship. The proposed model utilizes the observation that in kinetic occlusion, motion boundaries typically display mixture motion information, and foreground surfaces tend to move with motion boundaries. Through distributed probabilistic modeling, these constraints can be embedded into computations with efficient network representations. The resulting networks use spatiotemporal Gabor filters as front ends, and are suitable for parallel distributed processing. We demonstrate the application of the model in the decomposition of moving images into surfaces according to depth.