针对复杂交通场景中运动车辆检测方法存在的局限性,本文提出了一种基于中值模型和自适应阈值的运动检测算法。利用自适应阈值对差分图像的三个颜色通道进行二值化处理,实现了运动目标的精确检测,采用中值更新策略实现背景图像的实时更新。实验结果表明,算法可以从复杂交通场景图像序列中有效地检测出运动目标,且算法计算量小,具有良好的鲁棒性与实时性。%In order to improve the performance of motion vehicle detection in complicated traffic situations,this thesis puts forward an algorithm for motion detection based on median background model and adaptive threshold value.Three color channels of difference i
展开▼