In this paper, we present an approach for kernel-based object tracking using the HSV color space as the feature space and fuzzy color histograms as feature vectors. These histograms are more robust to illumination changes and quantization errors than common histograms. To avoid a significant increase in the computational complexity, a simple fuzzy membership function is used. The efficiency of this approach is demonstrated using videos from the PETS database and comparing the results using the fuzzy color histogram and the common color histogram.
展开▼
