Vision-based track turnout identification method
A track and turnout technology, which is applied in the field of vision-based track turnout identification, can solve the problems of track turnout identification difficulties, large changes in illumination differences, and complex track crossings, and achieve reduced detection time and complexity, high accuracy, and high efficiency. sticky effect
Active Publication Date: 2020-10-30
BEIHANG UNIV
View PDF6 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in the track environment where trains run, various problems such as large differences in illumination, complex track intersections, and multiple combinations make it difficult to identify track turnouts using traditional track turnout identification technology.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The present invention will be further described below in conjunction with the accompanying drawings and examples. It should be understood that the following examples are intended to facilitate the understanding of the present invention, and have no limiting effect on it.
[0046] The invention provides a vision-based track switch identification method, such as figure 1 shown, including the following steps:
[0047] S1: Take pictures from the camera video to form a sample set; use manual labeling to divide the scenes with turnouts in the sample set and the scenes without turnouts into two categories, and set corresponding training parameters. The training parameters include learning rate and gradient descent; divide the marked pictures into a training set and a test set at a ratio of 8:2 and perform training and testing, and finally build a switch classification network model.
[0048] S2: Use manual labeling to mark the track where the current train is located in pixel...
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
Login to View More Abstract
The invention belongs to the field of automatic driving and computer vision, and relates to a vision-based track turnout identification method, which comprises the following steps: constructing a turnout classification network model; constructing a monorail segmentation network model; judging whether the current frame of track scene is a turnout scene or not by utilizing a turnout classification network model; segmenting the turnout scene by using a monorail segmentation network model to obtain a monorail region image with a bifurcation point; and utilizing a fork center point detection algorithm to carry out track fork center point identification on the monorail area image, and outputting a fork center point coordinate. According to the invention, pure vision is used for track turnout recognition, color information and image distribution conditions can be obtained, visual scene understanding is easy, and track forks can be positioned on images in advance.
Description
technical field [0001] The invention belongs to the field of automatic driving and computer vision, in particular to a vision-based track switch identification method. Background technique [0002] In recent years, people have gradually paid attention to the safety perception in the train driving scene, and the positional relationship between the train track at the turnout and the train is one of the necessary scene information understandings. During the running of the train, the dispatch center contacts the railway workers to control the fork, and the train does not need to control the direction of the fork. At present, based on the track switch identification technology, the possible safety risks can be evaluated in advance, or the trajectory of the train can be recorded, which is of great value to the safe operation of the train. However, in the track environment where trains run, various problems such as large illumination differences, complex track intersections, and m...
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
Login to View More IPC IPC(8): G06K9/00G06K9/62G06T7/70B61L25/06
CPCG06T7/70B61L25/06G06V20/588G06F18/214
Inventor 余贵珍付子昂王章宇王朋成周彬
Owner BEIHANG UNIV