摘要
介绍一种在复杂场景下进行多运动目标速度检测的技术方法。该方法综合了帧差法和差影法优点,并建立自适应背景更新模型以增加复杂场景下运动目标辨识的鲁棒性。利用最小外接矩形和灰度信息作为各目标的特征向量,匹配各目标对象,以求取各目标运动速度。
A method to detect the respective speed of multiple motion targets in complex scenes is presented. This method combines the advantages of frame difference and background subtraction. In order to strengthen the robustness of motion targets identification in complex scenes, a self- adaptive background updating model is proposed. The outer rectangular bounds and tonal -gradation information are employed to be eigenvectors to match respective targets, so as to get the speed of them.
出处
《计算机与数字工程》
2006年第11期167-171,共5页
Computer & Digital Engineering
关键词
图像处理
帧差法
差影法
速度检测
image processing, frame difference, background subtraction, motion -speed detection
