深层卷积神经网络的目标检测算法综述  

Survey of Object Detection Algorithm Based on Deep Convolutional Neural Networks

作　　者：张泽苗 霍欢[1,2] 赵逢禹 ZHANG Ze-miao;HUO Huan;ZHAO Feng-yu(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai Key Laboratory of Data Science,Fudan University,Shanghai 201203,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093 [2]复旦大学上海市数据科学重点实验室,上海201203

出　　处：《小型微型计算机系统》2019年第9期1825-1831,共7页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61003031)资助;上海重点科技攻关项目(14511107902)资助;上海市工程中心建设项目(GCZX14014)资助;上海市一流学科建设项目(XTKX2012)资助;上海市数据科学重点实验室(201609060003)资助;沪江基金研究基地专项项目(C14001)资助

摘　　要：随着深度学习的发展,卷积神经网络在目标检测中取得了一系列研究成果.相比基于人工特征构造的传统的目标检测算法,基于深层卷积神经网络的算法具有特征自动提取,泛化能力强的优点,有较好的鲁棒性.本文首先介绍了卷积神经网络在目标检测基础任务图像分类上的进展,然后按照目标检测算法评价指标、算法框架以及公共数据集三个方面重点分析和比较近年来基于深度学习模型的目标检测算法的研究情况,最后对目标检测算法未来的发展进行展望.With the development of deep learning,convolutional neural networks have led to remarkable success in object detection.Compared with the traditional object detection algorithms based on artificial features construction,the algorithms based on deep convolutional neural network have the advantages of automatic feature extraction,strong generalization ability and good robustness. This paper firstly introduces the progress of convolutional neural network on the classification which is the base of object detection task,and then analyzes and compares the object detection algorithms based on deep learning model in recent years according to three aspects of object detection,including algorithm evaluation metric,algorithm frameworks and public datasets. Finally,this paper forecasts the future development of the object detection algorithms.

关 键 词：图像分类 深度学习 卷积神经网络 目标检测 

分 类 号：TP389[自动化与计算机技术—计算机系统结构]