A system and method for detecting rotating targets in remote sensing images.

By introducing an attention mechanism and a multi-angle channel module into the YOLOv5 model, the problem of low target detection accuracy in remote sensing images is solved, enabling fast and accurate detection and angle prediction of rotating targets, and improving the ability to identify targets and perform data statistics in remote sensing images.

CN120032221BActive Publication Date: 2026-06-30UNIT 32002 OF THE CHINESE PEOPLES LIBERATION ARMY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
UNIT 32002 OF THE CHINESE PEOPLES LIBERATION ARMY
Filing Date
2024-12-31
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing remote sensing image target detection models struggle to effectively handle situations where objects in remote sensing images have a wide range of scales, extreme aspect ratios, arbitrary target distribution angles, and dense targets when using horizontal bounding boxes, resulting in low detection accuracy and the inability to obtain physical attributes.

Method used

We employ the attention mechanism module and multi-angle channel module from the YOLOv5 model, combined with the angle loss function, to construct a feature extraction and fusion network for rotating target detection. We improve detection accuracy by rotating anchor boxes and angle prediction.

Benefits of technology

It enables rapid and accurate detection of targets of different sizes and orientations in remote sensing images, improves the model's ability to identify dense targets, and obtains the rotation angle information of the targets, which is beneficial for subsequent data statistics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120032221B_ABST
    Figure CN120032221B_ABST
Patent Text Reader

Abstract

This invention provides a system and method for detecting rotating targets in remote sensing images, belonging to the field of remote sensing image processing technology. The detection system includes: a first construction module for constructing a feature extraction and fusion network; a second construction module for constructing a detection network; a third construction module for constructing a new YOLOv5 model; an acquisition module for acquiring a set of remote sensing images; a training module for training the new YOLOv5 model; a rotating target detection module for performing rotating target detection using the new YOLOv5 model to determine the labeling information of all predicted bounding boxes for each target category; and a post-processing module for deduplicating all predicted bounding boxes, determining the optimal predicted bounding box for each target category, and labeling it. This invention can quickly and accurately detect targets of different sizes and orientations in remote sensing image scenes, which is beneficial for subsequent data statistics and other work.
Need to check novelty before this filing date? Find Prior Art