Human detection with EOH-OLBP-based multi-level features
文献类型：会议论文
| 作者 | Yingdong Ma; Liang Deng |
| 出版日期 | 2013 |
| 会议名称 | 3rd International Conference on Multimedia Technology, ICMT 2013 |
| 会议地点 | Guangzhou, China |
| 英文摘要 | In this work we aim to develop an onboard monocular pedestrian detection system by employing a classifier based on multi-level features. Different from most state-of-the-art detectors, our system employs a set of multi-level features to ensure high detection rate. More specifically, a set of EOH and OLBP based multi-level features is used to describe cell-level and block-level structure information. Multi-level features capture larger scale structure information which is more informative for pedestrian localization. Experiments on the INRIA dataset and the Caltech pedestrian detection benchmark demonstrate that the new pedestrian detection system is not only comparable to the existing pedestrian detectors but it also performs at a faster speed. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/5108]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 作者单位 | 2013 |
| 推荐引用方式 GB/T 7714 | Yingdong Ma,Liang Deng. Human detection with EOH-OLBP-based multi-level features[C]. 见:3rd International Conference on Multimedia Technology, ICMT 2013. Guangzhou, China. |
入库方式： OAI收割
来源：深圳先进技术研究院
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。