Remote Sensing Target Detection Algorithm based on CBAM-YOLOv5

Abstract

With the continuous improvement of traditional target detection algorithms, remote sensing targets have become a research hotspot. Aiming at the problems of low recognition accuracy caused by small target size and high background complexity in remote sensing images taken from overhead view, this paper proposes a remote sensing aircraft detection algorithm based on CBAM-YOLOv5. By introducing the lightweight convolutional attention module CBAM module into the YOLOv5 network, the feature extraction capability of the algorithm is improved to solve the problem that the small-size remote sensing target has little or even lost information on the feature map after multiple downsampling operations. The mAP of the proposed algorithm reaches 93.1%, which is 1% higher than that of the original algorithm, and the recognition of small-size remote sensing targets has been significantly improved.