摘要
为了实现高速场景下的智能实时目标检测,设计了一种基于ZYNQ7000系列FPGA的高速相机平台,并利用该平台进行目标检测算法实现,形成了一套高帧频实时目标检测系统样机。该系统将高速CMOS图像信号直接接入FPGA,在本地FPGA中进行数据处理,实现目标检测算法,最终实时输出目标位置序列。FPGA设计采用流水线结构,对高速视频流图像逐级进行背景差分、二值化、质心解算的流水操作,实现了图像获取与目标检测同步进行。测试结果表明,该系统在560×480分辨率下可以实现大于1 100 f/s的实时目标检测,并输出目标位置,检测精度可达3个像素。
In order to achieve intelligent real-time target detection in high-speed scenes,a high-speed camera platform is designed based on FPGA of ZYNQ7000 and target detection algorithm is implemented on it.As a result,one prototype of integrated high frame rate real-time target detection system was created.This system connects the high-speed CMOS signal to the FPGA directly,doing data processing and implementing target detection algorithm through native FPGA,and outputs real-time target position sequence eventually.This system performed pipeline operation of background differencing,binarization,and centroid detection on high-speed video stream images by using a pipeline structure of FPGA design.Due to this operation,the system achieved the synchronization of image acquisition and target detection.The experimental results show that this system can achieve real-time target detection and output target position greater than 1 100 f/s at 560×480 resolution,meanwhile,the detection accuracy can be up to 3 pixels.
作者
杨鲁新
董文博
Yang Luxin;Dong Wenbo(Key Laboratory of Space Utilization,Technology and Engineering Center for Space Utilization,Chinese Academy of Sciences,Beijing 100094,China;School of Computer and Control Engineering,University of Chinese Academy of Sciences,Beijing 101408,China)
出处
《电子技术应用》
2019年第4期109-112,117,共5页
Application of Electronic Technique