中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Constraint Loss for Rotated Object Detection in Remote Sensing Images

文献类型：期刊论文

作者Zhang, Luyang2; Wang, Haitao2; Wang, Lingfeng1,3; Pan, Chunhong1; Liu, Qiang2; Wang, Xinyao2
刊名REMOTE SENSING
出版日期2021-11-01
卷号13期号:21页码:19
关键词rotated object detection remote sensing image loss functions fast convergence
DOI10.3390/rs13214291
通讯作者Wang, Lingfeng(lfwang@mail.buct.edu.cn)
英文摘要Rotated object detection is an extension of object detection that uses an oriented bounding box instead of a general horizontal bounding box to define the object position. It is widely used in remote sensing images, scene text, and license plate recognition. The existing rotated object detection methods usually add an angle prediction channel in the bounding box prediction branch, and smooth L1 loss is used as the regression loss function. However, we argue that smooth L1 loss causes a sudden change in loss and slow convergence due to the angle solving mechanism of open CV (the angle between the horizontal line and the first side of the bounding box in the counter-clockwise direction is defined as the rotation angle), and this problem exists in most existing regression loss functions. To solve the above problems, we propose a decoupling modulation mechanism to overcome the problem of sudden changes in loss. On this basis, we also proposed a constraint mechanism, the purpose of which is to accelerate the convergence of the network and ensure optimization toward the ideal direction. In addition, the proposed decoupling modulation mechanism and constraint mechanism can be integrated into the popular regression loss function individually or together, which further improves the performance of the model and makes the model converge faster. The experimental results show that our method achieves 75.2% performance on the aerial image dataset DOTA (OBB task), and saves more than 30% of computing resources. The method also achieves a state-of-the-art performance in HRSC2016, and saved more than 40% of computing resources, which confirms the applicability of the approach.
资助项目National Natural Science Foundation of China[61773377] ; Key Laboratory of Ministry of Industry and Information Technology ; Fundamental Research Funds for the Central Universities ; Nondestructive Detection and Monitoring Technology for High Speed Transportation Facilities
WOS研究方向Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000719069000001
出版者MDPI
资助机构National Natural Science Foundation of China ; Key Laboratory of Ministry of Industry and Information Technology ; Fundamental Research Funds for the Central Universities ; Nondestructive Detection and Monitoring Technology for High Speed Transportation Facilities
源URL[http://ir.ia.ac.cn/handle/173211/46509]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Wang, Lingfeng
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Nanjing Univ Aeronaut & Astronaut, Coll Automat Engn, Nanjing 210016, Peoples R China
3.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Luyang,Wang, Haitao,Wang, Lingfeng,et al. Constraint Loss for Rotated Object Detection in Remote Sensing Images[J]. REMOTE SENSING,2021,13(21):19.
APA Zhang, Luyang,Wang, Haitao,Wang, Lingfeng,Pan, Chunhong,Liu, Qiang,&Wang, Xinyao.(2021).Constraint Loss for Rotated Object Detection in Remote Sensing Images.REMOTE SENSING,13(21),19.
MLA Zhang, Luyang,et al."Constraint Loss for Rotated Object Detection in Remote Sensing Images".REMOTE SENSING 13.21(2021):19.

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。