首页 | 本学科首页   官方微博 | 高级检索  
     

卷积神经网络在目标检测中的应用综述
引用本文:于进勇,丁鹏程,王超.卷积神经网络在目标检测中的应用综述[J].计算机科学,2018,45(Z11):17-26.
作者姓名:于进勇  丁鹏程  王超
作者单位:海军航空大学控制工程系 山东 烟台264001,海军航空大学研究生五队 山东 烟台264001,海军航空大学控制工程系 山东 烟台264001
摘    要:深度学习作为机器学习的一个分支,在各个领域的应用越来越广,已经成为语音识别、自然语言处理、信息检索等方面的一个主要发展方向;其在图像分类、目标检测等方面更是不断取得新的突破。文中首先梳理了卷积神经网络在目标检测中的典型应用;其次,对几种典型卷积神经网络的结构进行了对比,并总结了各自的优缺点;最后,讨论了深度学习现阶段存在的问题以及未来的发展方向。

关 键 词:计算机视觉  目标检测  深度学习  卷积神经网络

Overview:Application of Convolution Neural Network in Object Detection
YU Jin-yong,DING Peng-cheng and WANG Chao.Overview:Application of Convolution Neural Network in Object Detection[J].Computer Science,2018,45(Z11):17-26.
Authors:YU Jin-yong  DING Peng-cheng and WANG Chao
Affiliation:Department of Control Engineering,Naval Aeronautical University,Yantai,Shandong 264001,China,Postgraduate Team No.5,Naval Aeronautical University,Yantai,Shandong 264001,China and Department of Control Engineering,Naval Aeronautical University,Yantai,Shandong 264001,China
Abstract:As a branch of machine learning,deep learning has obtained wide application in various fields,and has become a major development direction of speech recognition,natural language processing,information retrieval and other aspects.Especially in image classification and object detection,it has made new breakthroughs.This paper first sorted out the typical applications of convolution neural network in object detection.Secondly,this paper compared several typical convolutional neural network structures,and summed up their advantages and disadvantages.Finally,the existing problems and the future development direction of deep learning were discussed.
Keywords:Computer vision  Object detection  Deep learning  Convolutional neural networks
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号