Monitoring of floating structures using segmentation and object classification of remotely-sensed images

Abstract With the rapid development of Marine aquaculture, remote sensing monitoring of high space separation Marine floating raft aquaculture has become a key technology to ensure aquaculture efficiency and environmental sustainability. A novel multi-scale layered cascade capsule network (MSHCN) model is proposed to improve the accuracy and efficiency of remote sensing image analysis for high space separation Marine floating raft culture. Firstly, based on the basic principle of the capsule network, the traditional convolutional neural network is improved, and a multi-scale feature extraction mechanism is introduced to adapt to the diversity and complexity of images in the culture area. Secondly, by building a hierarchical cascade structure, the model can further improve its ability to capture small and large scale features, so as to better understand the spatial distribution characteristics of the farming environment. In addition, in the experimental part, we verified with real remote sensing data sets, and the results showed that the MSHCN model outperformed the current mainstream methods on several key performance indicators, including classification accuracy, detection speed and model generalization ability. Finally, the potential value of this model in practical application and future optimization direction is discussed, which provides a new idea and tool for the development of remote sensing monitoring technology for high space separation floating raft culture.