|
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1. YOLOv8模型结构图 Conv代表卷积层, Concat代表拼接层, Upsample代表上采样层, Detect代表检测头, C2f代表特征融合模块, SPPF代表快速空间金字塔池化层
|
Fig. 1. YOLOv8 model architecture diagram. Conv represents convolutional layer, Concat represents concatenation layer, Upsample represents upsampling layer, Detect represents detection head, C2f represents Cross Stage Partial Network with 2 convolutions, and SPPF represents Spatial Pyramid Pooling Fast layer |
|
 |
|
|