CAJ | 학술논문

利用双目视觉信息系统实现三维空间中运动物体实时跟踪与测距.当运动目标超出视野范围时,可通过控制摄像机云台转动搜索目标.此外,还研究了在摄像头运动情况下,无需重新标定,即可实现运动物体测距的算法.这里,自适应背景建模法与CamShift算法用于实现运动物体的辨识与跟踪.实验结果证明了所提出的算法能够有效地追踪物体,并同时准确地测量它的三维位置.
이용쌍목시각신식계통실현삼유공간중운동물체실시근종여측거.당운동목표초출시야범위시,가통과공제섭상궤운태전동수색목표.차외,환연구료재섭상두운동정황하,무수중신표정,즉가실현운동물체측거적산법.저리,자괄응배경건모법여CamShift산법용우실현운동물체적변식여근종.실험결과증명료소제출적산법능구유효지추종물체,병동시준학지측량타적삼유위치.
A binocular camera information system is used to track and measure a moving object in real time in 3D space. arithmetic without recalibration for moving object distance measuring is studied, in the condition of camera moving. Herein adaptive background modelling algorithm and CamShift algorithm are used respectively to identify and track moving objects. Experimental results are presented to demonstrate that the proposed method can track the moving object effectively and get its 3D location accurately.