RS-YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images

TL;DR

RS-YOLOX is an improved high-precision object detection model tailored for satellite remote sensing images, integrating attention mechanisms and advanced fusion techniques to outperform existing methods in accuracy.

Contribution

The paper introduces RS-YOLOX, combining ECA, ASFF, and Varifocal Loss, and utilizes SAHI framework to enhance detection accuracy in remote sensing images.

Findings

Achieved highest accuracy on DOTA-v1.5, TGRS-HRRSD, and RSOD datasets.

Enhanced feature learning with ECA and ASFF modules.

Demonstrated superior detection performance over baseline models.

Abstract

Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS-YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high-performance remote sensing object detector, we combined the trained model with an open-source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA-v1.5, TGRS-HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets.