| 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 |
| 第一作者单位 | 中国科学院自动化研究所 |
| 通讯作者单位 | 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。 | |||||
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。
修改评论