| 基于部位检测和子结构组合的行人检测方法 |
| |
| 引用本文： | 胡斌,王生进,丁晓青.基于部位检测和子结构组合的行人检测方法[J].计算机科学,2009,36(11):242-246. |
| |
| 作者姓名： | 胡斌 王生进 丁晓青 |
| |
| 作者单位： | 智能技术与系统国家重点实验室,清华信息科学与技术国家实验室,清华大学电子工程系,北京,100084 |
| |
| 基金项目： | 863国家重点基金项目，973国家重点基金项目 |
| |
| 摘 要： | 提出了一种基于部位检测和子结构组合的、可用于辅助驾驶或视频监控系统中行人检测的方法.首先使用头部分类器在整幅图像中检测,得到感兴趣区域;然后在每个感兴趣区域内使用头部、躯干、腿部以及左臂和右臂5个人体部位检测器分别检测并使用基于子结构的检测组合方法对部位检测结果进行组合,以得到最终结果.在不同数据库上的实验结果表明,本方法可以有效地用于移动或静止摄像机所拍摄的视频图像中的多姿态及部分遮挡的行人检测.
|
| 关 键 词： | 视频图像 行人检测 部位检测器 子结构组合 |
| 收稿时间： | 2008/12/11 0:00:00 |
| 修稿时间： | 2009/3/24 0:00:00 |
Pedestrian Detection Method Based on Part Detector and Substructure Assemble |
| |
| HU Bin,WANG Sheng-jin,DING Xiao-qing.Pedestrian Detection Method Based on Part Detector and Substructure Assemble[J].Computer Science,2009,36(11):242-246. |
| |
| Authors: | HU Bin WANG Sheng-jin DING Xiao-qing |
| |
| Affiliation: | (State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Tethnology, Department of Electronic Engineering,Tsinghua University,Beijing 100084,China) |
| |
| Abstract: | We presented a pedestrian detection method based on part detector and substructure assemble which can be used for driving assistant system or video surveillance system. Firstly we used the head classifier to search the whole image in order to get the ROI(Region of Interesting).Then in each ROI five part detectors including head, torso, leg,left arm and right arm were used individually. Finally we verified the detection result through part detector assemble method based on substructure. Experiments on different database show that our method has high performance in detecting pedestrians with numerous poses and partial occlusion in cluttered background. |
| |
| Keywords: | Video images Pedestrian detection Part detector Substructure assemble |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机科学》浏览原始摘要信息 |
|
点击此处可从《计算机科学》下载全文 |
|
