CAJ | 학술논문

序列图像的运动目标识别与跟踪是计算机视觉主要研究方向之一.研究的重点是要建立一个准确可靠的跟踪系统.针对此问题,传统的帧间差分法进行了改进,并研究了粒子滤波算法.在改进的帧间差分法和粒子滤波的基础上,提出了序列图像运动目标跟踪方法.实验实验表明,这种方法能够在目标被背景云彩遮挡的情况下,实现目标的可靠跟踪.
서렬도상적운동목표식별여근종시계산궤시각주요연구방향지일.연구적중점시요건립일개준학가고적근종계통.침대차문제,전통적정간차분법진행료개진,병연구료입자려파산법.재개진적정간차분법화입자려파적기출상,제출료서렬도상운동목표근종방법.실험실험표명,저충방법능구재목표피배경운채차당적정황하,실현목표적가고근종.
Moving object recognition and tracking based on sequence image is the one of major research directions in computer vision.The research emphasis is to build an exact and reliable tracking system.Aiming to this problem,the traditional inter-frame difference method is improved,and combined with particle filter algorithm.A new sequence image moving object tracking method based on the improved inter-frame difference method and particle filter is proposed.The experiment result indicates that the method can realize reliable object tracking under the condition of object shelved from background clouds.