𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Motion segmentation based on feature selection from shape matrix

✍ Scribed by Naoyuki Ichimura; Fumiaki Tomita

Publisher
John Wiley and Sons
Year
2000
Tongue
English
Weight
565 KB
Volume
31
Category
Article
ISSN
0882-1666

No coin nor oath required. For personal study only.

✦ Synopsis

Motion segmentation using feature correspondences can be regarded as a combinatorial problem. In this paper, a motion segmentation method based on feature selection is proposed. Feature selection is carried out as construction of a basis of the linear space that represents the shape of objects. Features can be selected from each object without segmentation information by keeping the correspondence of the basis vectors to the features. Only four or less features of each object are used in segmentation; the combination in segmentation is reduced by feature selection. Thus, the combinatorial problem can be solved without optimization. Also, the proposed method can discriminate degenerate shape and estimate the number of objects. Experiments are done to consider the usefulness of the proposed method.

πŸ“œ SIMILAR VOLUMES

Fuzzy feature selection based on min–max
Fuzzy feature selection based on min–max learning rule and extension matrix
✍ Yun Li; Zhong-Fu Wu πŸ“‚ Article πŸ“… 2008 πŸ› Elsevier Science 🌐 English βš– 192 KB

In many systems, such as fuzzy neural network, we often adopt the language labels (such as large, medium, small, etc.) to split the original feature into several fuzzy features. In order to reduce the computation complexity of the system after the fuzzification of features, the optimal fuzzy feature