YOLO物体检测算法研究综述  

Review of YOLO Object Detection Algorithms

作　　者：周晋伟 王建平[1] ZHOU Jinwei;WANG Jianping(School of Mechanical Engineering,Anhui Polytechnic University,Wuhu 241000)

机构地区：[1]安徽工程大学机械工程学院,安徽芜湖241000

出　　处：《常州工学院学报》2023年第1期18-23,88,共7页Journal of Changzhou Institute of Technology

基　　金：安徽省科学技术厅科技重大专项项目(202103a05020033)。

摘　　要：在计算机视觉领域中,物体检测技术近年来备受关注。YOLO(you only look once)是一种将物体检测概括为回归问题的检测算法,由于采用了端到端的训练和检测方法,保证了良好的速度与精度,近几年被成功地应用到众多领域。文章对YOLO系列算法的重要应用进行详细调研,并与已有物体检测算法进行对比,在此基础上总结了YOLO的特点,指出了YOLO算法未来的发展趋势。In the field of computer vision, the object detection technology has attracted much attention in recent years. YOLO(you only look once) is a detection algorithm that summarizes object detection as a regression problem. It has been successfully applied to many different fields in recent years as it uses end-to-end training and detection methods to ensure good speed and accuracy. The important applications of YOLO series algorithms are investigated in detail, and are then compared with the existing object detection algorithms, based on which the characteristics of YOLO are summarized, and the future development trend of YOLO algorithm is pointed out.

关 键 词：YOLO 物体检测与识别 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]