101. Object tracking using SIFT features and mean shift
- Author
-
Yuan Yuan, Huiyu Zhou, and Chunmei Shi
- Subjects
Color histogram ,business.industry ,Scale-invariant feature transform ,Pattern recognition ,Tracking (particle physics) ,Histogram ,Video tracking ,Signal Processing ,Expectation–maximization algorithm ,Probability distribution ,Computer vision ,Computer Vision and Pattern Recognition ,Mean-shift ,Artificial intelligence ,business ,Software ,Mathematics - Abstract
A scale invariant feature transform (SIFT) based mean shift algorithm is presented for object tracking in real scenarios. SIFT features are used to correspond the region of interests across frames. Meanwhile, mean shift is applied to conduct similarity search via color histograms. The probability distributions from these two measurements are evaluated in an expectation-maximization scheme so as to achieve maximum likelihood estimation of similar regions. This mutual support mechanism can lead to consistent tracking performance if one of the two measurements becomes unstable. Experimental work demonstrates that the proposed mean shift/SIFT strategy improves the tracking performance of the classical mean shift and SIFT tracking algorithms in complicated real scenarios.
- Published
- 2009