摘要
为了实现对快速运动的目标实时检测和跟踪,搭建了一套高速视觉系统,提出一种基于YCBCr空间Cb分量的实时检测和跟踪算法,并通过质心预测和ROI更新来提高计算效率。实验结果表明该方法能够实时准确检测和跟踪1.3m距离下4m/s的乒乓球,对相似物体的干扰和运动模糊,具有良好的鲁棒性。对于分辨率为640x480的8位图像,采集和处理的速度最快能够达到3.2ms。
This paper builts a high-speed vision system and proposes a real-time detection and tracking algorithm based on Cb component of YCbCr space.Then reduces run time through centroid prediction and ROI update.The experimental results show that the method can accurately detect and track a fast moving ping-pong at 1.3 m distance in real time.It takes only 3.2 ms to capture and process a 8-bit image with a resolution of 640 x480.
出处
《工业控制计算机》
2019年第8期74-76,共3页
Industrial Control Computer
关键词
快速运动
高速视觉
检测与跟踪
实时
fast moving
high-speed vision
detection and tracking
real-time
