期刊
COMPUTERS & ELECTRICAL ENGINEERING
卷 99, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compeleceng.2022.107781
关键词
Infrared pedestrian detection; Multi-task learning; U-Net; Domain adaptation; Swin Transformer; Semantic segmentation; Gradient inversion
类别
资金
- National Key Research and Development Program of China [2020YFB1807500]
- Aeronautical Science Foundation of China [2018ZC81001]
- National Natural Science Foundation of China [62072360, 61902292, 61971331, 62001357]
- Key Research and Development Plan of Shaanxi province [2020JQ-844, 2021ZDLGY02-09, 2019ZDLGY13-07, 2019ZDLGY13-04]
- Key Laboratory of Embedded System and Service Computing (Tongji University) [ESSCKF2019-05]
- Ministry of Education
- Xi'an Science and Technology Plan, China [20RGZN0005]
- Xi'an Key Laboratory of Mobile Edge Computing and Security [201805052-ZD3CG36]
This paper proposes a multi-task learning framework for improving infrared pedestrian detection by incorporating semantic segmentation and domain adaptation. The experimental results demonstrate that the proposed method outperforms other methods in terms of average precision on different datasets.
Benefiting from the capability of night viewing, infrared images has been widely applied to surveillance systems as an effective complement to visible-light images. However, the development of infrared pedestrian detection is still impeded by weak features and limited diversity of infrared images. Aiming at these two problems, we designed a multi-task learning framework for pedestrian detection by incorporating a semantic segmentation branch and a domain adaptation branch. Composed of UNet network with Swin Transformer, the semantic segmentation could apply spatial constraints to pedestrian detection. The domain adaptation branch aligns the features between infrared and visible-light images to improve the scene diversity. In addition, three tasks shared a basic feature extraction network to reduce computation cost. The experiment results show that the average precision (AP) of our method is superior to the EfficientDet network by 2.0% on the XDU-NIR2020 dataset and 2.2% on the CVC-09 dataset respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据