《计算机应用研究》|Application Research of Computers

基于两种分类标准的目标检测算法综述

Survey of object detection algorithms based on two classification standards

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李平,喻洪流
机构 1.上海理工大学 康复工程与技术研究所,上海 200093;2.长治医学院 生物医学工程系,山西 长治 046000
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)09-003-2582-08
DOI 10.19734/j.issn.1001-3695.2021.01.0003
摘要 随着大数据、算力、深度学习的发展,基于深度学习的目标检测算法成为该领域主流算法,其性能远超传统算法。为了梳理算法发展脉络、跟踪最新研究成果、促进目标检测领域的研究,分别从两阶段/单阶段和anchor-based/anchor-free两个维度,对这两种不同分类标准下实现矩形框或近似矩形框标注的代表性目标检测算法进行综述,分析了算法流程、特点、演进及其性能,并对其重要改进版本进行了归类分析。最后总结了算法的优缺点、局限性及适用场景,并展望了未来目标检测领域的发展趋势,提出了几个重要的研究方向。
关键词 目标检测; 深度卷积神经网络; 两阶段; 单阶段; anchor-based; anchor-free
基金项目 国家自然科学基金资助项目(62073224)
本文URL http://www.arocmag.com/article/01-2021-09-003.html
英文标题 Survey of object detection algorithms based on two classification standards
作者英文名 Li Ping, Yu Hongliu
机构英文名 1.Institute of Rehabilitation Engineering & Technology,University of Shanghai for Science & Technology,Shanghai 200093,China;2.Dept. of Biomedical Engineering,Changzhi Medical College,Changzhi Shanxi 046000,China
英文摘要 With the development of big data, computational power and deep learning, the object detection algorithm based on deep learning becomes the mainstream algorithm in this field, and its performance is far superior to the traditional algorithms. In order to review the development of algorithms, track the latest research results, and promote the research in the field of object detection, this paper summarized the representative object detection algorithms from two dimensions: two-stage /one-stage and anchor-based/anchor-free, and realized the rectangular box or approximate rectangular box annotation under these two different classification standards. This paper discussed the process, characteristic, evolution and performance of the algorithms, and made the classification and analysis on the important improved versions. Finally, this paper summarized the advantages and disadvantages, limitations and applicable scenarios of the algorithms, and looked forward to the development trend in the field of object detection, and put forward several important research directions in the future.
英文关键词 object detection; deep convolutional neural network; two-stage; one-stage; anchor-based; anchor-free
参考文献 查看稿件参考文献
 
收稿日期 2021/1/12
修回日期 2021/3/5
页码 2582-2589
中图分类号 TP389.1
文献标志码 A