Aircraft Remote Sensing Image Target Detection Based on Improved Mask-RCNN Algorithm

In this paper, an improved Mask-RCNN algorithm is proposed for target detection of airplanes in remote sensing images. The method introduces multi-scale feature fusion and attention mechanism to improve the accuracy and robustness of target detection. By conducting experiments on DOTA dataset and comparing with other similar algorithms, the experimental results show that the algorithm achieves an average detection accuracy of 91.22% with a small number of additional parameters and an FPS of 22.56. This indicates that the improved Mask-RCNN algorithm has excellent performance and generalization ability for aircraft detection in remote sensing images.