The Assessment of More Suitable Image Spatial Resolutions for Offshore Aquaculture Areas Automatic Monitoring Based on Coupled NDWI and Mask R-CNN

Wide-scale automatic monitoring based on the Normalized Difference Water Index (NDWI) and Mask Region-based Convolutional Neural Network (Mask R-CNN) with remote sensing images is of great significance for management aquaculture areas. However, different spatial resolutions brought cost model performance. To find more suitable image offshore areas, seven resolution in Sandu’ao area China, from 2 m, 4 to 50 were compared. Results showed that a 15 m above can achieve corresponding recognition effect when no financial issues considered, F1 score over 0.75. By establishing cost-effectiveness evaluation formula comprehensively considers price effect, best scenes be found, thus providing most appropriate data scheme