Deep Reinforcement Learning With Visual Attention for Vehicle Classification
Zhao, Dongbin1,2; Chen, Yaran1; Lv, Le1
发表期刊IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
2017-12-01
卷号9期号:4页码:356-367
文章类型Article
摘要Automatic vehicle classification is crucial to intelligent transportation system, especially for vehicle-tracking by police. Due to the complex lighting and image capture conditions, image-based vehicle classification in real-world environments is still a challenging task and the performance is far from being satisfactory. However, owing to the mechanism of visual attention, the human vision system shows remarkable capability compared with the computer vision system, especially in distinguishing nuances processing. Inspired by this mechanism, we propose a convolutional neural network (CNN) model of visual attention for image classification. A visual attention-based image processing module is used to highlight one part of an image and weaken the others, generating a focused image. Then the focused image is input into the CNN to be classified. According to the classification probability distribution, we compute the information entropy to guide a reinforcement learning agent to achieve a better policy for image classification to select the key parts of an image. Systematic experiments on a surveillance-nature dataset which contains images captured by surveillance cameras in the front view, demonstrate that the proposed model is more competitive than the large-scale CNN in vehicle classification tasks.
关键词Convolutional Neural Network (Cnn) Reinforcement Learning Vehicle Classification Visual Attention
WOS标题词Science & Technology ; Technology ; Life Sciences & Biomedicine
DOI10.1109/TCDS.2016.2614675
关键词[WOS]OBJECT RECOGNITION ; FEATURES ; REPRESENTATION ; REGRESSION ; SALIENCY ; ROBOTS ; SCENES
收录类别SCI ; SSCI
语种英语
项目资助者National Natural Science Foundation of China(61273136 ; National Key Research and Development Plan(2016YFB0101000) ; 61573353 ; 61533017)
WOS研究方向Computer Science ; Robotics ; Neurosciences & Neurology
WOS类目Computer Science, Artificial Intelligence ; Robotics ; Neurosciences
WOS记录号WOS:000418069600006
引用统计
被引频次:121[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/14474
专题复杂系统管理与控制国家重点实验室_深度强化学习
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhao, Dongbin,Chen, Yaran,Lv, Le. Deep Reinforcement Learning With Visual Attention for Vehicle Classification[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2017,9(4):356-367.
APA Zhao, Dongbin,Chen, Yaran,&Lv, Le.(2017).Deep Reinforcement Learning With Visual Attention for Vehicle Classification.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,9(4),356-367.
MLA Zhao, Dongbin,et al."Deep Reinforcement Learning With Visual Attention for Vehicle Classification".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 9.4(2017):356-367.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
07580631.pdf(3192KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhao, Dongbin]的文章
[Chen, Yaran]的文章
[Lv, Le]的文章
百度学术
百度学术中相似的文章
[Zhao, Dongbin]的文章
[Chen, Yaran]的文章
[Lv, Le]的文章
必应学术
必应学术中相似的文章
[Zhao, Dongbin]的文章
[Chen, Yaran]的文章
[Lv, Le]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07580631.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。