基于YoloV3的实时视频行人检测算法  

Real-time Video Pedestrian Detection Algorithm Based on YoloV3

作　　者：张梦鸽 李健[1] 陈慧雯 Zhang Mengge;Li Jian;Chen Huiwen(China Electronics Technology Group Corporation No.32 Research Institute,Shanghai 201800,China)

机构地区：[1]中国电子科技集团公司第三十二研究所,上海201800

出　　处：《单片机与嵌入式系统应用》2022年第6期29-32,共4页Microcontrollers & Embedded Systems

摘　　要：本文提出一种基于YoloV3的视频检测算法,使用Mobile Net的思想优化模型,并采用基于三帧差分法和粒子滤波的视频运动自适应推理算法,充分利用视频前后帧之间的目标关联性,将其部署在VisionSeed上。实验结果表明,在COCO数据集上实现了0.331 s的单帧检测速率,速度提升了31.9%,满足了嵌入式平台的运行要求。In the paper,a video detection algorithm based on YoloV3 is proposed,which uses the idea of mobile net to optimize the model,and adopts the video motion adaptive reasoning algorithm based on three frame difference method and particle filter,makes full use of the target correlation between the front and back frames of the video,and finally deploys it on visionfeed.The experimental results show that the single frame detection rate of 0.331 s is realized on the COCO data set,and the speed is increased by 31.9%,which meets the operation requirements of the embedded platform.

关 键 词：深度学习 目标检测 YoloV3算法 VisionSeed Mobile-Net 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]