CAJ | 학술논문

在智能交通视频监控系统中,由于交通路口车辆多、车速不定且外界环境光线变化等诸多因素造成不能很好地检测到运动目标.将W~4算法应用到道路交叉口的视频监测中,该算法首先利用中值法进行初始化选出静止像素集合,并利用静止像素构建背景参数模型,同时建立基于像素级和基于目标级的背景更新模式.通过仿真验证该算法能够在路口比较复杂的情况下很好地检测到车辆,与传统的方法相比检测的准确度有了较大的改进.
재지능교통시빈감공계통중,유우교통로구차량다、차속불정차외계배경광선변화등제다인소조성불능흔호지검측도운동목표.장W~4산법응용도도로교차구적시빈감측중,해산법수선이용중치법진행초시화선출정지상소집합,병이용정지상소구건배경삼수모형,동시건립기우상소급화기우목표급적배경경신모식.통과방진험증해산법능구재로구비교복잡적정황하흔호지검측도차량,여전통적방법상비검측적준학도유료교대적개진.
For many uncertain factors of intersection video surveillance such as more vehicles,uncertain speed and the changing environment and so on.So it is difficult to detect moving objects efficiently from video sequences.W~4 algorithm is used in intersection video surveillance system.W~4 algorithm first uses a pixelwise median filter to distinguish the stationary pixels from the video and uses these stationary pixels to form the background parametric model.At the same time according to the conditions to choose the updming methods pixel-based or object-based.Experimental results show that the W~4 algorithm possesses higher performance on intersection video surveillance under complex environments.