Wajima, Naoya (Department of Intelligent Mechanical Systems Engineering,Kagawa), Takahashi, Satoru (Kagawa Univ.), Itoh, Masaya (Hitachi Res. Lab. Hitachi, Ltd.), Satoh, Yutaka (National Inst. of Advanced Industrial Science and Tech. (AIST)), Kaneko, Shun'ichi (Hokkaido Univ.)

Radial Reach Filter and Its Application to Object Tracking

Scheduled for presentation during the Regular Session "Neural Networks II" (ThA12), Thursday, July 27, 2006, 11:40−12:05, Room 104b

17th International Symposium on Mathematical Theory of Networks and Systems, July 24-28, 2006, Kyoto, Japan

This information is tentative and subject to change. Compiled on May 19, 2024

Abstract

In the filed of image processing, developing a method which can detect a moving object from time series images is one of important researches. In the past, many methods which separate a moving object from the background have been developed. Recently, Kaneko and his collaborators have studied the method of object detection based on Radial Reach Filter (RRF). RRF can extract a moving object without the affection of changes of brightness. However, this method has the various problems. For example, when the change of brightness on the image and the change of background image arise, it is not easy to detect the moving objects. Therefore, we propose new method which solves the problems above. Then, we introduce the method of object tracking by using the feature of RRF, and experiment the validity of our method using the real image data.