Railway roadbed disease radar map real-time detection method based on convolutional neural network

Abstract

The invention discloses a railway roadbed disease radar map real-time detection method based on a convolutional neural network. The railway roadbed disease radar map real-time detection method comprises the following steps: marking and dividing roadbed disease radar images into a training set and a test set; and expanding the training set, sending the expanded training set to a convolutional neural network, outputting a disease type, a disease type, a disease position coordinate and a disease confidence coefficient, and carrying out iterative calculation through a gradient descent method to obtain a railroad bed disease detection model; and adopting mean value average precision and the frame number per second as indexes for evaluating the quality of the model. According to the railway roadbed disease radar map real-time detection method, the multi-scale prediction network is fully utilized, and no candidate region is generated in the whole process, so that the detection time is greatlyshortened while the precision is ensured, and real-time detection is realized.

Description

technical field [0001] The invention relates to the technical fields of railway subgrade disease detection and radar image intelligent recognition, in particular to a method for real-time detection of railway subgrade disease radar images based on a convolutional neural network. Background technique [0002] At the same time that my country's railways are undergoing high-speed development at this stage, due to the increase in operating mileage and time, the problem of railway subgrade diseases has begun to appear. Railway subgrade disease is a major safety problem in the field of railway transportation, which brings hidden dangers to the safe operation of railways. How to quickly and accurately identify potential roadbed disease risk sources from massive railway subgrade inspection data to ensure the safety of railway transportation has become an urgent technical problem to be solved. [0003] Vehicle-mounted geological radar detection technology has been rapidly promoted a...

AI Technical Summary

Problems solved by technology

The geological radar detection data of the railway subgrade belongs to massive data, and the geological radar data of about 23G is generated every 30 kilometers on average. High knowledge and experience requirements

Existing detection technologies mainly focus on the combination of artificially designed features and traditional machine learning methods such as support vector machines and shallow neural networks. Such methods are time-consuming and have low accuracy

The existing convolutional neural network recognition technology based on candidate regions cannot meet the real-time processing requirements, and it is difficult to afford the massive data detection task of geological radar

Images