パーティクルフィルタを用いた進入検出と物体追跡

Object detection and tracking using particle filter

Creators Matsumura Ryo

Creators Okamura Kenshiro

Object tracking is an important role in many areas of engineering such as surveillance and computer vision. Over the last few years, particle filters have been proved to be powerful tools for object tracking. To adopt particle filters, the number of tracking objects is very important. In this paper, we propose a method of entrance detection in the specific areas using two-state particle filters. We demonstrate the algorithm on a set of real object targets whose image contains a number of peoples, bicycles and cars.

[ISSN]0387-9232

[NCID]AN00031668