|
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 Tailong 1(  ), XIE Tao 1,2,3,4(  ), LI Jian 1,3,4, WANG Chao 1,5, ZHANG Xuehong 1,3,4
|
|
|
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 |
|
 |
|
|