EFSOD: Enhanced Feature based Small Object Detection Network in Remote Sensing Images

Due to the poor imaging quality of remote sensing images and the small size of targets, remote sensing small target detection has become a current research difficulty and hotspot. Recent years have seen many new algorithms. Remote sensing small target detection methods based on image super-resolution reconstruction have attracted many researchers due to their excellent performance. However, these algorithms still have problems such as weak feature extraction capability and insufficient feature fusion. Then, we propose Enhanced Feature based Small Target Detection Network in Remote Sensing Images (EFSOD), which includes a Edge Enhancement Super-Resolution Reconstruction Module (EESRM) and a Cross-Model Feature Fusion Module (CMFFM). EESRM enhances the recognizability of small target contours by fusing extracted edge features with the original features through residual connections, alleviating the constraints of feature blurring on detection performance. CMFFM achieves deep integration of the detailed features extracted by the EESRM network with the semantic features extracted by the target detection network, improving the model's sensitivity and accuracy in recognizing small targets in complex backgrounds. Additionally, considering the effects of blurring, noise, illumination changes, and atmospheric scattering on remote sensing images, a remote sensing image degradation simulation algorithm is proposed. This algorithm realistically simulates the generation process of low-resolution remote sensing images under natural conditions, providing more realistic training and testing data. The experimental results show that the proposed EFSOD significantly enhances the performance of small object detection in remote sensing.