Rail transit obstacle detection method based on deep learning

Abstract

The invention discloses a rail transit obstacle detection method based on deep learning. The rail transit obstacle detection method comprises the following steps: screening out a part containing an obstacle according to a video stored by a vehicle-mounted camera when a train runs; making the video containing the obstacle part into a plurality of images; expanding the number of images by using a data enhancement method; and dividing a region of interest on an image, wherein a detection range is set near a track. As a YOLOv4 network is not sensitive to small object detection, a D-CSPDarknet feature extraction network is designed, the problem of gradient disappearance is effectively solved, and the purpose of feature reuse is achieved. In combination with a new feature fusion network provided with three feature pyramid pooling modules, a complete Improved-YOLOv4 obstacle detection model is formed. The model is trained by using previously made data to obtain a weight file for detection. An obstacle is detected by the weight file. Real-time detection of the obstacle in front of a train can be achieved, along with continuous expansion of data collected by the train camera, the detection precision is improved accordingly, the installation cost is low, and the efficiency is high.

Description

technical field [0001] The invention belongs to the technical field of urban rail transit image recognition, in particular relates to traffic fault detection and recognition technology, in particular to a method for detecting rail transit obstacles based on deep learning. Background technique [0002] With the rapid development of railway transportation, the degree of heavy-duty freight and high-speed passenger transportation has been further improved, and railway transportation has gradually transitioned and changed to the direction of comprehensive functions, information sharing and high automation, carrying the important mission of national mobility and cargo transportation . Especially in China, by the end of 2019, the number of passengers dispatched was 3.66 billion, the volume of freight dispatched was 4.389 billion tons, and the operating mileage of high-speed railways reached 35,000 kilometers. The urgent need for railway transportation safety makes the railway traf...

AI Technical Summary

Problems solved by technology

However, the operating mileage of the railway is long, and there are many accidents in the monitoring dead-end area

Track inspection methods include manual inspection and track inspection system. Manual inspection arranges a large number of inspectors to conduct inspections along the line, which is inefficient and time-consuming.

The track inspection system uses the inspection vehicle inspection method to realize monitoring, but this method cannot guarantee real-time monitoring

Images