CASIA OpenIR  > 智能感知与计算研究中心
Enhanced Biologically Inspired Model
Yongzhen Huang; Kaiqi Huang; Liangsheng Wang; Dacheng Tao; Tieniu Tan; Xuelong Li
2008
会议名称CVPR Workshop on Visual Surveillance
会议录名称IEEE Conference on Computer Vision & Pattern Recognition 2008
页码1-8
会议日期2008
会议地点Marseille , France
摘要It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feed-forward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 times 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.
关键词Feedback   image Recognition   object Detection
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12710
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Yongzhen Huang,Kaiqi Huang,Liangsheng Wang,et al. Enhanced Biologically Inspired Model[C],2008:1-8.
条目包含的文件
条目无相关文件。
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
[Yongzhen Huang]的文章
[Kaiqi Huang]的文章
[Liangsheng Wang]的文章
百度学术
百度学术中相似的文章
[Yongzhen Huang]的文章
[Kaiqi Huang]的文章
[Liangsheng Wang]的文章
必应学术
必应学术中相似的文章
[Yongzhen Huang]的文章
[Kaiqi Huang]的文章
[Liangsheng Wang]的文章
相关权益政策
暂无数据
收藏/分享
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。