Multi-Sensor Information Fusion Algorithm Based on Adaptive Background Information

Urban rail transit has been widely popularized in major cities due to its many advantages, such as large traffic volume, fast speed, and effective traffic congestion relief. However, the rapid development has also brought many disadvantages, mainly reflected in the deformation of tracks and tunnels. A single sensor can no longer meet the demand. The performance of data fusion system is usually affected by many factors such as sensor characteristics, environment and target characteristics, fusion model, fusion process and so on. The sensors cannot be effectively combined, resulting in a waste of information resources, and possibly even making mistakes in decision-making. The information data of each sensor complements each other’s advantages, learns from each other’s strengths, and effectively integrates them, which can overcome the uncertainty and limitations of a single sensor and obtain more accurate track and tunnel status information. At the same time, it is necessary to adopt a self-suitable data fusion algorithm to eliminate redundant information and reduce the amount of data transmission, thereby effectively saving energy and prolonging the life of the network.