Co-evolution based feature selection for pedestrian detection
文献类型：会议论文
| 作者 | Guo, Y.P. ; Cao, X.B.; Xu, Y.W.; Hong, Q.
|
| 出版日期 | 2007 |
| 会议名称 | 2007 IEEE International Conference on Control and Automation, ICCA 2007 |
| 会议日期 | 30 May-1 June 2007 |
| 会议地点 | Guangzhou, China |
| 关键词 | automated highways / object detection / road safety / AdaBoost algorithm / coevolution based feature selection / pedestrian detection system / Automatic control / Automation / Communication system software / Computer science |
| 通讯作者 | Guo, Y.P. |
| 英文摘要 | In a pedestrian detection system, the most critical requirement is to quickly and reliably determine whether a candidate region contains a pedestrian. The detection ability of whole system determines directly upon quality of chosen features. However, due to the large number and various types of available features, it is difficult to find an optimal feature subset and acquire the proper feature proportion at the same time for most traditional methods including AdaBoost Algorithm. This paper presents a co-evolutionary method with sub-population size adjusting strategy for the feature selection problem in pedestrian detection system. Our method is able to find an optimal feature subset and adjust feature proportion to a proper state in the mean time. Experiments show that our method performs better than AdaBoost Algorithm. |
| 会议录 | 2007 IEEE International Conference on Control and Automation, ICCA 2007
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12823]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
| 作者单位 | Dept. of Comput. Sci. & Technol., Univ. of Sci. & Technol. of China |
| 推荐引用方式 GB/T 7714 | Guo, Y.P.,Cao, X.B.,Xu, Y.W.,et al. Co-evolution based feature selection for pedestrian detection[C]. 见:2007 IEEE International Conference on Control and Automation, ICCA 2007. Guangzhou, China. 30 May-1 June 2007. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。