摘要
深度卷积神经网络以多层次的特征学习与丰富的特征表达能力,在目标检测领域取得了突破进展。概括了卷积神经网络在目标检测领域的研究进展,首先回顾传统目标检测的发展及存在的问题,引出卷积神经网络的目标检测基本原理和基本训练方法;然后分析了以R-CNN为代表的基于区域建议的目标检测框架,介绍以YOLO算法为代表的将目标检测归结为回归问题的目标检测框架;最后,对目前目标检测的一些问题进行简要总结,对未来深度卷积神经网络在目标检测的发展进行了展望。
Deep convolutional Neural Networks（DNNs） have made breakthroughs in object detection, because of its more powerful ability of feature learning and feature representation. In this paper, the research progress of convolutional neural networks has been expounded in object detection. Firstly, the development and existing problems of traditional object detection are reviewed. It introduces the principles of the DNNs and the improvement of common techniques.Then, object detection framework which combines region proposal is introduced. It introduces YOLO algorithm, which aims at object detection as regression problem. Finally, some existing problems in the present study are briefly summarized and the new directions for future development are expected.
作者
姚群力
胡显
雷宏
YAO Qunli;HUXian;LEI Hong(Institute of Electronics,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《计算机工程与应用》
CSCD
北大核心
2018年第17期1-9,共9页
Computer Engineering and Applications
关键词
深度卷积神经网络
目标检测
特征表达
特征提取
DeepconvolutionalNeuralNetworks （DNNs）
objectdetection
featurerepresentations
featureextraction
