The traditional railway survey adopts a manual observation method, such as a total station measuring system. This method has high precision, but the amount of data is small, and the measurement efficiency is low. Manual measurement cannot meet the requirements of dynamic continuous high-precision holographic measurement during railway outages. Mobile laser scanning is a mobile mapping system based mainly on a laser scanner, inertial measurement unit (IMU) and panoramic camera. Mobile laser scanning has the advantages of high efficiency, high precision and automation. However, integrating inertial navigation data and mobile laser scanning data to obtain real 3D information about railways has always been an urgent problem to be solved. Therefore, a point cloud reconstruction method is proposed based on trajectory filtering for a mobile laser scanning system. This paper corrects the odometer data by identifying railway feature points through deep learning and uses Rauch–Tung–Striebel (RTS) filtering to optimize the trajectory results. Combined with the railway experimental track data, the maximum difference in the east and north coordinate direction can be controlled within 7 cm, and the average elevation error is 2.39 cm. This paper applies a multi-sensor integrated mobile detection system to railway detection. It is of great significance to the healthy development of the intelligent railway system.

Aiming at the problems of low positioning accuracy and poor robustness of traditional odometers, this paper proposes a mileage positioning method based on subway feature recognition. First, use the YOLOv3 target detection method to identify the characteristics of the track fasteners, and obtain the position information of the characteristic points. Then, distance clustering and Lagrangian interpolation are used to complete the feature points that are not detected by deep learning. Finally, the initial mileage value is obtained according to the mileage constraint, and the speed filter method is used to correct the mileage result. In order to verify the reliability of the mileage positioning method, a mobile laser scanning experiment was carried out in Xi'an Metro. Experimental results show that this method has good positioning accuracy and stability. After Kalman speed filter preprocessing, the mileage positioning error is about 7cm, and the standard error is 5.05 × 10-3, which provides accurate mileage results for subway inspections.