To solve the problems of small target,multi-scale and complex target background in remote sensing images,a Bottle-neck Transformer target detection network was proposed.On the YOLOv5s model,the CNN+Transformer architecture was used to replace the C3 convolution operation in the last residual block,and the dilated convolution was used.The multi-scale information was fused by setting different expansion rates to solve the problem of complex remote sensing image background.The EIOU bounding box loss function was used.Verified on the NWPU VHR-10 dataset,the mAP reaches 94.5％,which is 1.2％higher than that of the original YOLOv5s.Small targets detection such as ports and vehicles have corresponding increases of 1.3％and 4.5％.The effectiveness of the algorithm for small target recognition and complex background recognition is veri-fied.
关键词
遥感图像/目标检测/瓶颈变压器/特征融合/卷积神经网络/空洞卷积/损失函数
Key words
remote sensing images/object detection/bottleneck transformer/feature fusion/convolutional neural networks/ASPP/loss function
维普
万方数据