Urban rail train number image positioning method

Abstract

The invention discloses an urban rail train number image positioning method, which comprises the following steps of: preprocessing a train number image shot on site by adopting a single-scale Retinex algorithm based on brightness control to obtain a first train number image; extracting feature points of the first vehicle number image obtained through preprocessing by adopting an SURF algorithm; calculating the feature description of the extracted feature points; performing feature point registration by using a self-made vehicle number image and the first vehicle number image, and screening out a potential region of the vehicle number; and improving an SWT algorithm through a stroke width measurement operator SMO, and carrying out accurate positioning on the screened potential vehicle number area to obtain a vehicle number area. The urban rail train number image positioning method has the advantages of being high in practicability, simple in calculation and high in positioning accuracy, and automatic identification of train numbers can be achieved through expansion.

Description

technical field [0001] The invention belongs to the technical field of traffic safety engineering, in particular to a method for locating an image of an urban rail train number. Background technique [0002] In order to ensure the safe and reliable operation of the train, online monitoring of the key components and operating status of the vehicle system (for example, axle temperature, pantograph wear, horn status, etc.) is the focus of the current urban rail train system operation safety guarantee. As the unique identification information of the vehicle, its accurate and efficient identification is of great significance to the monitoring of train running status and fault location. [0003] The current identification technology of urban rail trains mostly relies on RFID technology. The identification system consists of two parts: an electronic tag installed at the bottom of the train and a reading device on the ground. Although the vehicle number recognition system has been ...

AI Technical Summary

Problems solved by technology

Due to the dim light in the tunnel and the high speed of the train, there is a certain distortion in the captured image of the car number

At the same time, in the urban rail train number image, there are many edge elements such as doors and windows, and the number image positioning algorithm that only uses edge detection cannot meet the requirements of on-site use.

Images