An Improved Adaptive Algorithm Based on Local-Searching for Color Object Tracking and Segmentation

摘要

Motion tracking and object segmentation are the most fundamental and critical problems in vision tasks such as video surveillance, object recognition, image retrieval and so on. Color segmentation is a very popular technique for real-time object tracking. Since the color cue is relatively invariant to scale, illumination and viewing direction while being computationally efficient. Several color image segmentation algorithms have been proposed; however, most of them are not suitable for real-time applications because of high computation load and many parameters needed to be set in advance. In, a fast tracking algorithm based on local-searching of color object was introduced. The algorithm relies on local information instead of scanning image row by row to improve the tracking speed. However, the segmentation thresholds of this method need to be set manually and always remain unchanged during the segmentation processing, which limits the application of this algorithm.