A study on automatic filter construction for feature extraction with feature reconstruction

Real-time tracking of moving objects in natural scenes has taken a great role in computer vision. In order to track the targets, we have to determine the object models. But, it is hard to determine them in advance. Moreover, to realize real-time operations, each frame operation should be done in short time. In this paper, we propose a filter processing for tracking and an automatic filter construction system. No specific hardware is used. The filters are designed by the system itself in each environment, and are able to extract their color features which are not contained in other areas. The proposed system generates color filters which can derive feature segments using clustering process. After that, it re-assembles the filter to obtain better performance by genetic algorithm. We show how the filters are effective for object detection and tracking a target.