Unlock instant, AI-driven research and patent intelligence for your innovation.

Dynamic visual monitoring method for railway shunting

A shunting and dynamic technology, applied in the field of visual recognition, can solve the problems of the influence of the locomotive docking accuracy, low ranging accuracy, and lack of precision, and achieve the effects of accurate locomotive positioning, enlarged detection angle, and less lack of precision.

Inactive Publication Date: 2021-08-06
TIANJIN DEV ZONE WENBO ELECTRONICS
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the distance measurement accuracy of this method is low. Since the laser rangefinder is a single-point distance measurement, it cannot be combined with the algorithm and the monocular camera to achieve accurate positioning of the front of the vehicle. Therefore, this distance measurement method has a certain lack of accuracy. It will have a certain impact on the accuracy of the docking of the train head

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dynamic visual monitoring method for railway shunting
  • Dynamic visual monitoring method for railway shunting
  • Dynamic visual monitoring method for railway shunting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The invention provides a dynamic visual monitoring method for railway shunting, which is characterized in that: its specific operation method is:

[0040] Step 1: Use the Zhang Zhengyou calibration method to complete the calibration of the monocular camera:

[0041] A calibration plate with a square of 52mm and a length and width of 9×6 is selected, and the images of the calibration plate at different positions are calibrated using the calibrator application in the Matlab software, and the calibration results of 4 basic magnifications are obtained. Finally, the internal parameter matrix such as the focal length and optical axis offset of the monocular camera is obtained;

[0042] Step 2: Installation and calibration of millimeter wave radar:

[0043] Use a small-sized level ruler to calibrate the pitch angle and roll angle of the millimeter-wave radar to be horizontal. When yaw angle is calibrated, use the angle ruler to determine that the inverse coordinate of the met...

Embodiment 2

[0067] The present invention mainly realizes the distance measurement problem of the locomotive during the docking process of the train through the fusion of two millimeter-wave radars, a monocular vision camera and a laser range finder. The present invention utilizes the fusion of multiple sensors to play each Each sensor has its own detection advantages, and finally realizes accurate identification and distance measurement of the front of the vehicle.

[0068] (1) The millimeter-wave radar is mainly responsible for the medium and long-distance measurement tasks of the target. The purpose of setting up two millimeter-wave radars is to increase the accuracy of the measurement results and the robustness of the fault diagnosis.

[0069] (2) The monocular vision camera is mainly responsible for the recognition and detection task of the docking locomotive, using the deep learning algorithm and the track detection algorithm of the station to comprehensively obtain the image informat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a dynamic visual monitoring method for railway shunting, which comprises the following steps of: comparing a pixel coordinate identified by a millimeter-wave radar with a locomotive position identified by a monocular camera through the millimeter-wave radar and a coordinate conversion algorithm, and taking a pixel coordinate of a point closest to a locomotive position datum point in Euclidean distance as a final target point. Compared with a single-point laser range finder, middle and long distance range finding can assist a monocular camera to carry out vehicle head positioning operation through auxiliary information positioning and an algorithm of the millimeter wave radar, so that vehicle head positioning is more accurate, precision loss is less, and when the vehicle head distance is less than 30m, the millimeter wave radar is turned off, and the laser range finder is used as a range finding device. The short-distance distance measurement laser range finder is more accurate, and the distance measurement accuracy of short-distance vehicle head butt joint is improved.

Description

technical field [0001] The invention relates to the field of visual recognition, in particular to a dynamic visual monitoring method for railway shunting. Background technique [0002] Railway shunting generally involves the docking of train vehicles. The original docking method is to estimate the distance between the vehicles by the staff, and judge whether the front of the train is docked through experience and intuition. With the development of visual technology, the existing train docking The work has been replaced by the vision and ranging system, which obtains the image information of the target through vision, uses machine learning, deep learning and other visual image processing algorithms to obtain the specific shape and position information of the target, and then measures the distance between the docking vehicle through the ranging system , to complete the docking of the train, the existing laser rangefinder and monocular camera are usually used to achieve the dis...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/80G06T7/70G06N3/04G06K9/00
CPCG06T7/80G06T7/70G06V20/54G06N3/045
Inventor 纪书利
Owner TIANJIN DEV ZONE WENBO ELECTRONICS