Knowledge Commons of Institute of Automation,CAS
Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection | |
Lu Zhang1,3; Xiangyu Zhu2,3; Xiangyu Chen4; Xu Yang1,3; Zhen Lei2,3; Zhiyong Liu1,3,4; Lu Zhang5,7; Xiangyu Zhu6,7; Xiangyu Chen8; Xu Yang5,7; Zhen Lei6,7; Zhiyong Liu5,7,8 | |
2019 | |
会议名称 | IEEE International Conference on Computer Vision |
会议日期 | 2019.10.27-2019.11.02 |
会议地点 | Seoul, Korea |
摘要 | Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position shift problem, i.e. the color-thermal image pairs are not strictly aligned, making one object has different positions in different modalities. In deep learning based methods, this problem makes it difficult to fuse the feature maps from both modalities and puzzles the CNN training. In this paper, we propose a novel Aligned Region CNN (AR-CNN) to handle the weakly aligned multispectral data in an end-to-end way. Firstly, we design a Region Feature Alignment (RFA) module to capture the position shift and adaptively align the region features of the two modalities. Secondly, we present a new multimodal fusion method, which performs feature re-weighting to select more reliable features and suppress the useless ones. Besides, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns of different devices and system settings. Finally, since our method depends on a new kind of labelling: bounding boxes that match each modality, we manually relabel the KAIST dataset by locating bounding boxes in both modalities and building their relationships, providing a new KAIST-Paired Annotation. Extensive experimental validations on existing datasets are performed, demonstrating the effectiveness and robustness of the proposed method. Code and data are available at: https://github.com/luzhang16/AR-CNN. |
收录类别 | EI |
七大方向——子方向分类 | 多模态智能 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/25840 |
专题 | 多模态人工智能系统全国重点实验室_机器人理论与应用 |
作者单位 | 1.SKL-MCCS, Institute of Automation, Chinese Academy of Sciences 2.CBSR & NLPR, Institute of Automation, Chinese Academy of Sciences 3.University of Chinese Academy of Sciences 4.CEBSIT, Chinese Academy of Sciences 5.SKL-MCCS, Institute of Automation, Chinese Academy of Sciences 6.CBSR & NLPR, Institute of Automation, Chinese Academy of Sciences 7.University of Chinese Academy of Sciences 8.CEBSIT, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Lu Zhang,Xiangyu Zhu,Xiangyu Chen,et al. Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Zhang 等。 - 2019 - We(1154KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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