Remote sensing image thick cloud region detection method based on neural network

• Main Authors: YU WEIXUE, LI GUANQUN
• Format: Patent
• Language: Chinese; English
• Published: 30.05.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention relates to the technical field of image data processing, and discloses a neural network-based remote sensing image thick cloud region detection method, which comprises the following steps of: acquiring a cloud remote sensing image, determining a branch according to a position to obtain a position feature, perfecting a branch according to an edge to obtain an edge feature, fusing the position feature and the edge feature to obtain a fusion feature, and inputting the fusion feature into a U-shaped convolutional neural network to obtain a thick cloud region detection result. According to the method, the parallel U-shaped convolutional neural network is utilized, the position determination branch and the edge improvement branch are adopted to carry out thick cloud region overall detection and cloud region edge refinement respectively, and the features extracted by the two branches are merged and fused, so that a remote sensing image thick cloud region detection result with accurate detection and com