CAJ | 학술논문

为解决交通测试系统中车辆实时跟踪和分割的问题,以数字图像处理方法为手段,针对采集到的交通路况信息,重点研究了背景差分算法提取运动车辆,并提出了一种计算量较小的自适应背景更新算法；采用一种工作在HSV( Hue, Saturation, Valve)空间非基于模型的车辆阴影检测算法,并提出设置阈值参数的方法,在去除车辆阴影的同时也滤除了行人、自行车及摩托车等干扰；针对车辆阴影检测后的二值化图像,采用适合的形态学方法进行后期处理。对实际交通环境下的大量视频和图像进行测试的结果表明,该方法可以有效地实现运动车辆的检测。
위해결교통측시계통중차량실시근종화분할적문제,이수자도상처리방법위수단,침대채집도적교통로황신식,중점연구료배경차분산법제취운동차량,병제출료일충계산량교소적자괄응배경경신산법；채용일충공작재HSV( Hue, Saturation, Valve)공간비기우모형적차량음영검측산법,병제출설치역치삼수적방법,재거제차량음영적동시야려제료행인、자행차급마탁차등간우；침대차량음영검측후적이치화도상,채용괄합적형태학방법진행후기처리。대실제교통배경하적대량시빈화도상진행측시적결과표명,해방법가이유효지실현운동차량적검측。
In order to solve the problems of real-time vehicle tracking and separation in the traffic test system, using digital image processing method, a moving vehicles detection algorithm based on transportation videos is proposed. For the obtained traffic test information, the research focuses on the background subtraction algorithm to extract moving vehicles. A method of adaptive background updating algorithm with smaller amount of calculation is proposed and a nonmodel-based approach working in HSV( Hue, Saturation, Valve) space is used to detect vehicle shadow. Through setting the proper threshold parameters, we can remove vehicle shadow and remove disturbances of pedestrian, bicycle and motorcycle vehicle at the same time. After the shadow detection, some suitable morphological methods are used for post processing. Based on large number tests of real traffic environment video and images, the proposed method is proved to be effective for moving vehicles detection.