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

A gauge detection method and device

A detection method and gauge technology, applied in the detection field, can solve problems such as image detection errors, high cost, and low gauge detection accuracy

Active Publication Date: 2019-05-10
WATRIX TECH CORP LTD
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the cost of using a lidar sensor or a binocular camera for detection is relatively high; and, for the detection at the track interface, since the existing technology can only distinguish the track, but not which track it is, it is possible It will lead to detection errors for images containing multiple tracks, which will lead to low accuracy in track gauge detection

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
  • A gauge detection method and device
  • A gauge detection method and device
  • A gauge detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] See figure 2 As shown, a schematic flow chart of a method for detecting a gauge provided by an embodiment of this application includes the following steps:

[0074] Step 201: Obtain a track image.

[0075] In specific implementation, when acquiring the orbit image, the orbit image can be captured by a camera. The track image may include at least two tracks. For example, the track image may be a track image of a track intersection including multiple tracks, or a track image of a non-track intersection including two tracks.

[0076] Step 202: Input the track image into the pre-trained instance segmentation image prediction model, and execute the prediction process to obtain the instance segmentation image corresponding to the track image.

[0077] Specifically, the example segmented image is marked with two track edge lines belonging to the same track area.

[0078] In a possible implementation, the instance segmentation image prediction model may include an encoding-decoding net...

Embodiment 2

[0121] This embodiment provides a gauge detection device, such as Picture 9 As shown, a schematic structural diagram of a track gauge detection device 900 provided in an embodiment of this application includes an acquisition module 901 and a prediction module 902. The prediction module 902 includes an extraction unit 9021, a first determination unit 9022, and a second determination unit 9023. , And the gauge determination module 903, specifically:

[0122] The obtaining module 901 is used to obtain a track image;

[0123] The prediction module is used to input the orbit image into a pre-trained instance segmentation image prediction model to perform the prediction process; wherein the prediction module includes:

[0124] The extraction unit 9021 is configured to extract feature information of the track image to obtain the feature image of the track image; and,

[0125] The first determining unit 9022 is configured to determine the semantic segmentation image of the track image and th...

Embodiment 3

[0148] Based on the same technical concept, an embodiment of the present application also provides an electronic device. Reference Picture 10 As shown, a schematic structural diagram of an electronic device 1000 provided by an embodiment of this application includes a processor 1001, a memory 1002, and a bus 1003. Among them, the memory 1002 is used to store execution instructions, including a memory 10021 and an external memory 10022; here, the memory 10021 is also called an internal memory, which is used to temporarily store arithmetic data in the processor 1001 and data exchanged with an external memory 10022 such as a hard disk. The processor 1001 exchanges data with the external memory 10022 through the memory 10021. When the computer device 1000 is running, the processor 1001 and the memory 1002 communicate through the bus 1003, so that the processor 1001 executes the following instructions:

[0149] Get track image;

[0150] The track image is input into the pre-trained i...

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 track gauge detection method and device. The track gauge detection method comprises the steps of obtaining a track image; inputting the track image into a pre-trained instancesegmentation image prediction model, and executing a prediction process; the prediction process comprises the following steps: firstly, extracting feature information of a track image to obtain a feature image of the track image; determining a semantic segmentation image of the track image and a feature vector of each pixel point in the feature image according to the feature image; furthermore, based on the feature image, the feature vector of each pixel in the feature image and the semantic segmentation image, determining an instance segmentation image; and finally, based on the instance segmentation image and a preset parameter matrix, determining the gauge between the two track edge lines belonging to the same track area. Through the method, the track gauge detection cost can be reduced, and the track gauge detection accuracy is improved.

Description

Technical field [0001] This application relates to the field of detection technology, and in particular to a method and device for track gauge detection. Background technique [0002] In order to ensure the safety of rail vehicles, the track needs to be inspected regularly, and the gauge inspection is an indispensable inspection item for track inspection. [0003] In the prior art, an image of the track is mainly obtained by a lidar sensor or a binocular camera, and then the track distance is detected by the obtained image. However, the cost of detection using lidar sensors or detection through binocular cameras is relatively high; and for the detection at the track interface, because the prior art can only distinguish the track, but not which track it is, it may It will lead to errors in the detection of images containing multiple tracks, which will result in lower accuracy in track gauge detection. Summary of the invention [0004] In view of this, the purpose of the present app...

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): G06K9/34E01B35/02
Inventor 黄永祯童仁玲王洋
Owner WATRIX TECH CORP LTD