Multiple Vehicle Tracking Algorithm Using Kalman Filter

칼만 필터를 이용한 다중 차량 추적 알고리즘

  • 김형태 (부산대학교 전자공학과) ;
  • 설성욱 (부산대학교 전자공학과 양산대학 동의공업대학)
  • Published : 1998.10.01

Abstract

This paper describes the algorithm which extracts moving vehicles from sequential images and tracks those vehicles using Kalman filter. This work is composed of a motion segmentation stage which extracts moving objects from sequential images and gets features of objects, and a motion estimation stage which estimates the position and the motion of moving objects using Kalman filter. In the motion estimation stage, applying to affine motion model we divided the Kalman filter into position filter and velocity filter to employ linear Kalman filter. Multi-target tracking requires a data association component that decides which measurement to use for updating the state of which object. We use pattern recognition method to solve this problem.

Keywords