Not just select samples, but exploration[formula omitted] Genetic programming aided remote sensing target detection under deep learning

Abstract

Listen

Translate article

The data of target detection in remote sensing images are diverse, and the detection results of some categories with a small number of samples are poor. In order to solve this problem, most of the existing methods focus on the category with a small number of samples through data augmentation, but this will bring huge loss of original information, resulting in the decline of the effectiveness of some categories when improving the effectiveness. Additionally, since remote sensing image targets are small, numerous and densely distributed, the mixing degree of target and background is high, making them hardly distinguished. Therefore, a loss-based sample selection mechanism is proposed to enhance the category samples with low proportion. In the training process, we select between the original samples and enhanced samples through loss feedback, so as to retain the original sample information as much as possible and improve the detection performance. On this basis, an auxiliary feature detection module is proposed. First, the module detects the highly mixed area between the object to be detected and the background, and uses a series of image enhancement operations to build a genetic programming (GP) tree to separate the object from the background as much as possible, so that the detector can better extract and detect target features. Compared with other latest related algorithms, the loss-based sample selection mechanism and evolutionary auxiliary feature detection method proposed in this paper can improve the detection performance of low proportion categories through the sample selection mechanism, and improve the robustness to background clutter interference through evolutionary auxiliary feature detection. The proposed approach effectively improves the detection performance and performs well in remote sensing target detection.