CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Biologically Inspired Deep Stereo Model
Kong, Qingqun1; Zeng, Yi1; Dong, Qiulei2
2015
会议名称The 2015 IEEE International Conference on Image Processing (ICIP 2015)
会议录名称Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP 2015)
会议日期September 27-30, 2015
会议地点Québec City, Canada
摘要The human stereo vision process begins in primary visual cortex where complex cells are deemed as disparity detectors. Besides correct matches, complex cells could also respond to false matches which cause ambiguous depth perception. This reveals that there exist some inherent mechanisms in the higher visual processing areas for eliminating false matches and thus recovering true disparity. Due to the least understanding of this hierarchical process, this paper aims to investigate this problem by proposing a deep stereo vision model. There are three characteristics of the proposed model: 1) the obtained disparity maps become more accurate from lower layers to higher layers; 2) it tends to promote neural responses of correct matches while inhibiting those of incorrect matches; 3) it generalizes well to unseen data.
关键词Stereo Vision
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12473
专题模式识别国家重点实验室_机器人视觉
通讯作者Dong, Qiulei
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
第一作者单位中国科学院自动化研究所
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Kong, Qingqun,Zeng, Yi,Dong, Qiulei. Biologically Inspired Deep Stereo Model[C],2015.
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
Biologically Inspire(4002KB)会议论文 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
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
[Dong, Qiulei]的文章
百度学术
百度学术中相似的文章
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
[Dong, Qiulei]的文章
必应学术
必应学术中相似的文章
[Kong, Qingqun]的文章
[Zeng, Yi]的文章
[Dong, Qiulei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Biologically Inspired Deep Stereo Model.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。