摘要
为了防止驾驶员因注意力分散而导致的行人交通事故,提出了一种基于ZYNQ的车载行人检测系统设计方案。方案在FPGA部分完成图像采集、缓存和显示,在ARM部分运行梯度方向直方图和支持向量机算法对图像进行行人检测,获取行人的位置,并根据行人位置给出相应的预警信息。该系统实现了行人检测的目的,具有准确度高、体积小、功耗低等特点。
In order to prevent pedestrian traffic accidents caused by distraction of the driver,this paper presents a design scheme of vehicle pedestrian detection system based on ZYNQ. The project completes the image capture,cache and display in the FPGA section and runs Histogram of Oriented Gradient and Support Vector Machine algorithm to detect pedestrian and get the location of pedestrians,then according to the pedestrian position to give the corresponding warning information in the ARM section. This system achieves the purpose of pedestrian detection and has the characteristics of high accuracy,small size,and low power consumption.
作者
邓健峰
谢云
Deng Jianfeng;Xie Yun(School of Automation, Guangdong University of Technology, Guangzhou 510006, China)
出处
《信息技术与网络安全》
2018年第3期91-95,共5页
Information Technology and Network Security
关键词
行人检测
梯度方向直方图
支持向量机
FPGA
ARM
pedestrian detection
Histogram of Oriented Gradient (HOG)
Support Vector Machine(SVM)
FPGA
ARM