Constraint Loss for Rotated Object Detection in Remote Sensing Images

Remote Sensing

Haitao Wang¹  Qiang Liu¹  Xinyao Wang¹  Luyang Zhang¹  Lingfeng Wang²  Chunhong Pan³ 

[1] College of Automation Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China;College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China;

关键词: rotated object detection;    remote sensing image;    loss functions;    fast convergence;   

DOI  :  10.3390/rs13214291

来源: DOAJ

【 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 $L_1$ loss is used as the regression loss function. However, we argue that smooth $L_1$ 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.

【 授权许可】

Unknown