Rotating object detection in remote-sensing environment

Deep learning models have become the mainstream algorithm for processing computer vision tasks. In the tasks of object detection, the detection box is usually set as a rectangular box aligned with the coordinate axis, so as to achieve the complete packaging of the object. However, when facing some objects with large aspect ratio and angle, the bounding box must be enlarged, which makes the bounding box contain a large amount of useless background information. In this study, a different approach based on YOLOv5 is adopted. By this means, the angle information dimension is added at the head, and angle regression is also added at the same time of the boundary regression. Then the loss of the boundary box is calculated by combining ciou and smoothl1, so that the obtained boundary box is more closely suitable for the actual object. At the same time, the original dataset tags are also pre-processed to calculate the angle information of interest. The purpose of these improvements is to realize object detection with angles in remote-sensing images, especially for objects with large aspect ratios, such as ships, airplanes, and automobiles. Compared with the traditional and other state-of-the-art arbitrarily oriented object detection model based on deep learning, experimental results show that the proposed method has a unique effect in detecting rotating objects.

Automated summary

This study proposes a different approach based on YOLOv5 for object detection with angles in remote-sensing images. By adding angle information dimension and angle regression, and calculating the loss of the boundary box using ciou and smoothl1, the obtained boundary box is more suitable for the actual object. Experimental results show that this method has a unique effect in detecting rotating objects.