期刊文献+

高帧频视觉实时目标检测系统 被引量:2

High-frame-rate visual real-time target detection system
下载PDF
导出
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
关键词 ZYNQ7000 智能相机 高速相机 FPGA实时图像处理 并行计算 质心检测算法 ZYNQ7000 intelligent camera high-speed camera FPGA real-time image processing parallel computing centroid de tection algorithm
  • 相关文献

参考文献7

二级参考文献53

共引文献34

同被引文献30

引证文献2

二级引证文献7

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部