Integrated sensing and communication (ISAC) is emerged as a research hotspot of key technologies in future wireless communication systems with the purpose of achieving environment sensing within a wireless communication framework. To achieve complete and accurate sensing of the large-scale complex environment, multiple views from different user equipments (UEs) and base stations (BSs) in a wireless network should be fully and cooperatively exploited. In this project, some centralized and distributed machine learning method should be designed. There are three kinds of fusion process for multiple UEs and BSs views, including pixel fusion, feature fusion and result fusion. Based on these fusion ideas, some machine learning networks should be designed. The code is mainly programed by Pytorch and Matlab is used to generate the training data. The project duration is expected to 12 months.