基于深度学习的SAR图像海洋涡旋自动检测模型
刘太龙1(), 谢涛1,2,3,4(), 李建1,3,4, 王超1,5, 张雪红1,3,4
Deep learning-based automatic detection model for ocean eddies in SAR images
LIU Tailong1(), XIE Tao1,2,3,4(), LI Jian1,3,4, WANG Chao1,5, ZHANG Xuehong1,3,4

图2. EddyDetNet模型结构图

Conv代表卷积层, AFCM代表自适应特征融合模块, MFSP代表多尺度特征空间金字塔模块, Concat代表拼接层, Upsample代表上采样层, Detect代表检测头

Fig. 2. EddyDetNet model architecture diagram. Conv represents convolutional layer, AFCM represents adaptive feature compression module, MFSP represents multi-scale feature spatial pyramid module, Concat represents concatenation layer, Upsample represents upsampling layer, and Detect represents detection head