Information Fusion Based on Radar and Infrared Sensor Under Missing Data

Aiming at the problem of data fusion between radar and infrared sensor with missing data, an extended Kalman filter sensor fusion method based on generative adversarial network is proposed. Considering the particularity of sensor data, some missing data cannot be simply abandoned, and the missing data is interpolated by generative adversarial networks. Considering that two heterogeneous sensor information is fused by weighted fusion algorithm, the experimental results show that the sensor data has higher estimation accuracy in the case of missing data.