Efficient Stereo Matching Using Swin Transformer and Multilevel Feature Consistency in Autonomous Mobile Systems
文献类型：期刊论文
| 作者 | Su, Xiaojie1; Liu, Shimin1; Li, Rui2 ; Bing, Zhenshan3; Knoll, Alois3
|
| 刊名 | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
 |
| 出版日期 | 2024-03-06 |
| 页码 | 9 |
| 关键词 | Costs Feature extraction Transformers Computational modeling Task analysis Image reconstruction Unsupervised learning Disparity estimation feature consistency stereo matching transformer |
| ISSN号 | 1551-3203 |
| DOI | 10.1109/TII.2024.3367033 |
| 通讯作者 | Li, Rui(rui.li@ia.ac.cn) |
| 英文摘要 | In this article, we propose a Swin Transformer and multilevel Feature Consistency based Network (STFC-Net), which is a multilevel cascade stereo matching method to predict the disparity in a coarse-to-fine manner. 1) To alleviate the problem of the limited receptive field of existing convolutional neural network (CNN)-based methods, inspired by the capability of modeling the large-scale dependence of transformer, we adopt a multilevel feature extraction module combining CNN and Swin Transformer to capture long-range context information; a multiscale cascaded cost aggregation module is used to cover different image regions with less memory consumption. 2) To make full use of the hierarchical features, we checked the multilevel left-right feature consistency in an unsupervised manner to improve the disparity accuracy. The experimental results show that our method outperforms some previous CNN methods on the Scene Flow and KITTI datasets with lower computational time complexity. Moreover, it generalizes well in some unknown and challenging real-world scenarios. |
| 资助项目 | National Key Ramp;D Program of China |
| WOS研究方向 | Automation & Control Systems ; Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001185915600001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Ramp;D Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58041]  |
| 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 |
| 通讯作者 | Li, Rui |
| 作者单位 | 1.Chongqing Univ, Sch Automat, Chongqing 400044, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Tech Univ Munich, Dept Informat, D-85748 Munich, Germany |
| 推荐引用方式 GB/T 7714 | Su, Xiaojie,Liu, Shimin,Li, Rui,et al. Efficient Stereo Matching Using Swin Transformer and Multilevel Feature Consistency in Autonomous Mobile Systems[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2024:9. |
| APA | Su, Xiaojie,Liu, Shimin,Li, Rui,Bing, Zhenshan,&Knoll, Alois.(2024).Efficient Stereo Matching Using Swin Transformer and Multilevel Feature Consistency in Autonomous Mobile Systems.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,9. |
| MLA | Su, Xiaojie,et al."Efficient Stereo Matching Using Swin Transformer and Multilevel Feature Consistency in Autonomous Mobile Systems".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2024):9. |
入库方式： OAI收割
来源：自动化研究所
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。