Motion segmentation and tracking using normalized cuts
Jianbo Shi, Jitendra Malik · International Conference on Computer Vision · 2002
We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. A weighted graph is constructed on the image sequence by connecting pixels that are in the spatiotemporal neighborhood of each other. At each pixel, we define motion profile vectors which capture the probability distribution of the image velocity. The distance between motion profiles is used to assign a weight on the graph edges. Using normalised cuts we find the most salient partitions of the spatiotemporal graph formed by the image sequence. For segmenting long image sequences, we have developed a recursive update procedure that incorporates knowledge of segmentation in previous frames for efficiently finding the group correspondence in the new frame.
Cited by 336 works. doi:10.1109/iccv.1998.710861
Authors
References
- Maximum Likelihood from Incomplete Data Via the EM Algorithm
- An Iterative Image Registration Technique with an Application to Stereo Vision
- Determining optical flow
- Maximum likelihood estimation from incomplete data via the EM algorithm
- Determining Optical Flow
- Good features to track
- Normalized cuts and image segmentation
- Spatiotemporal energy models for the perception of motion
- A computational framework and an algorithm for the measurement of visual motion
- Laws of organization in perceptual forms.