Deep Learning Strong Parts for Pedestrian Detection
文献类型：会议论文
| 作者 | Yonglong Tian; Ping Luo; Xiaogang Wang; Xiaoou Tang |
| 出版日期 | 2015 |
| 会议名称 | ICCV2015 |
| 会议地点 | 智利圣地亚哥 |
| 英文摘要 | Recent advances in pedestrian detection are attained by transferring the learned features of Convolutional Neural Network (ConvNet) to pedestrians. This ConvNet is typically pre-trained with massive general object categories (e.g. ImageNet). Although these features are able to handle variations such as poses, viewpoints, and lightings, they may fail when pedestrian images with complex occlusions are present. Occlusion handling is one of the most important problem in pedestrian detection. Unlike previous deep models that directly learned a single detector for pedestrian detection, we propose DeepParts, which consists of extensive part detectors. DeepParts has several appealing properties. First, DeepParts can be trained on weakly labeled data, i.e. only pedestrian bounding boxes without part annotations are provided. Second, DeepParts is able to handle low IoU positive proposals that shift away from ground truth. Third, each part detector in DeepParts is a strong detector that can detect pedestrian by observing only a part of a proposal. Extensive experiments in Caltech dataset demonstrate the effectiveness of DeepParts, which yields a new state-of-the-art miss rate of 11:89%, outperforming the second best method by 10%. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6705]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | Yonglong Tian,Ping Luo,Xiaogang Wang,et al. Deep Learning Strong Parts for Pedestrian Detection[C]. 见:ICCV2015. 智利圣地亚哥. |
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。