Lightweight Context Awareness and Feature Enhancement for Anchor-Free Remote- Sensing Target Detection
- 12 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (7) , 10714-10726
Abstract
Optical remote sensing image target detection holds significant research significance in various domains, including disaster relief, ecological environment protection, and military surveillance. However, since remote sensing images have multi-scale targets, complex backgrounds and many small targets, the performance of the existing network models in remote sensing image target detection cannot reach what we expect. In addition, we note that current networks use complex computational mechanisms that make the models time-costly, which hinders its practicability in remote sensing target detection scenarios. In response to this challenge, we propose an anchor-free and efficient one-stage target detection method for optical remote sensing images. First, we propose the lightweight context-aware module GSelf-Attention, injected into the feature fusion network from top-to-bottom and bottom-to-top to enhance the feature information interaction. Secondly, we proposed ELAN-RSN uses an optimized residual shrinkage network (RSN) to eliminate background noise and conflicting information in the multi-scale feature fusion. Finally, we introduce the decoupled head fused with SPDConv to enhance the detection accuracy of small target objects further. The performance of the proposed algorithm is compared with that of other advanced methods on DIOR and RSOD datasets. The experimental results show that the proposed algorithm significantly improves object detection accuracy while ensuring detection efficiency and has high robustness. Code is available at https://github.com/FF-codeHouse/Object-Detection/tree/remote-sensing.Keywords
Funding Information
- National Natural Science Foundation of China (62066036, 82260359)
- Natural Science Foundation of Inner Mongolia Autonomous Region (2022LHMS06005)
- Central Government Guides Local Science and Technology Development Fund Project of China (2023ZY0017)
- Fundamental Research Funds for Inner Mongolia University of Science and Technology (2023QNJS195)
This publication has 41 references indexed in Scilit:
- YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors2023
- Improved YOLOX-X based UAV aerial photography object detection algorithmImage and Vision Computing, 2023
- Cavitation state identification of centrifugal pump based on CEEMD-DRSNNuclear Engineering and Technology, 2023
- GhostNet: More Features From Cheap Operations2020
- Object detection in optical remote sensing images: A survey and a new benchmarkISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Attention Augmented Convolutional Networks2019
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression2019
- The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking2018
- SSD: Single Shot MultiBox Detector2016
- You Only Look Once: Unified, Real-Time Object Detection2016