High-speed train bottom foreign matter recognition method based on deep learning

Abstract

The invention discloses a high-speed train bottom foreign matter recognition method based on deep learning. The method is carried out according to the following steps: shooting bottom images of high-speed train, screening out images containing foreign matters; expanding the number of images by using a data enhancement method; aiming at the defects of YOLO-V3 network precision design, designing a DenseNet-based network as a feature extraction network, and inserting a spatial pyramid network into a multi-scale prediction layer, so that the precision of a YOLO network framework is improved, and meanwhile, the defect of low small object detection precision is improved; and training the improved YOLO-V3 model by using a stochastic gradient descent method to obtain a vehicle bottom foreign matter detection model, inputting a vehicle bottom foreign matter picture into the model, and outputting the recognition result of the picture. The method can achieve the intelligent detection of the foreign matters at the bottom of the high-speed train, is high in recognition rate, high in detection speed, high in detection efficiency and high in practicality, is obvious in advantages compared with aconventional detection method, and has the potential of being applied to other fields.

Description

technical field [0001] The invention belongs to the field of image recognition of foreign objects on the bottom of high-speed trains, and in particular relates to a method for recognizing foreign objects on the bottom of high-speed trains based on deep learning. Background technique [0002] With the rapid development of the world's economy and science, railway transportation has made great progress in technology and has become one of the most popular modern transportation methods. In my country, as of the end of the first quarter of 2019, more than 10 billion passengers chose to travel by high-speed rail, and high-speed rail has become an important type of railway transportation. The rapid increase in the number of passengers has made safety the top priority of railway operations; when the high-speed railway is running at high speed, external foreign objects such as plastic bags can easily enter the gap between the bottom bogie, cables and equipment, and it is easy to gener...

AI Technical Summary

Problems solved by technology

However, in the TEDS system, there are defects such as high false alarm rate and low precision in the detection of foreign objects under the vehicle.

Therefore, engineers still need to detect foreign objects one by one in the TEDS monitoring center, which is inefficient, time-consuming, and labor-intensive. Moreover, false detections and missed detections may affect the safety of high-speed railways

Images