Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
文献类型:会议论文
作者 | Lu Zhang1,3; Xiangyu Zhu2,3; Xiangyu Chen4; Xu Yang1,3; Zhen Lei2,3; Zhiyong Liu1,3,4 |
出版日期 | 2019 |
会议日期 | 2019.10.27-2019.11.02 |
会议地点 | Seoul, Korea |
英文摘要 | 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. |
源URL | [http://ir.ia.ac.cn/handle/173211/25840] |
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 | 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 |
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]. 见:. Seoul, Korea. 2019.10.27-2019.11.02. |
入库方式: OAI收割
来源:自动化研究所
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。