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

Tunnel water stain detection system and method based on computer vision

A computer vision and detection system technology, applied in computer parts, computing, image data processing, etc., can solve the problems of unbalanced positive and negative samples, less water-stained areas, etc., to reduce false positives, facilitate learning, improve accuracy and The effect of reliability

Pending Publication Date: 2020-07-03
SHANGHAI JIAO TONG UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on image segmentation is another means to solve this kind of problem, but in the tunnel water damage image, the positive and negative samples are extremely unbalanced, the tunnel image is collected several kilometers long tunnel, but the water damage area is relatively small, the existing Segmentation techniques cannot overcome this problem very well

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
  • Tunnel water stain detection system and method based on computer vision
  • Tunnel water stain detection system and method based on computer vision
  • Tunnel water stain detection system and method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] Such as figure 1 As shown, a computer vision-based tunnel water stain detection system, the system includes:

[0047] Tunnel image acquisition module 1: Acquire 2D tunnel unfolded images, 2D tunnel unfolded images include but not limited to high-resolution images, as long as images containing tunnel information are applicable;

[0048] Image preprocessing module 2: cropping the 2D tunnel expansion image to obtain a segmented image with several features consistent with the original image, and saving the position information of the segmented image in the original image;

[0049] Water damage detection module 3: used to input segmented images and predict water damage areas to output water damage prediction maps;

[0050] Image re-matching module 4: Match the water damage prediction map to the 2D tunnel expansion image to obtain the prediction result.

[0051] Such as figure 2 As shown, the water damage detection module 3 includes:

[0052] Existence binary classificat...

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 relates to a tunnel water stain detection system and method based on computer vision. The system comprises a tunnel image acquisition module for acquiring a 2D tunnel expansion image; the image preprocessing module which is used for cutting the 2D tunnel expansion image to obtain a plurality of segmented images of which the characteristics are consistent with those of the original image, and storing the position information of the segmented images in the original image; the waterlogging disease detection module which is used for inputting the segmented image, predicting a waterlogging disease area and outputting a waterlogging disease prediction graph; and the image re-matching module which is used for matching the waterlogging disease prediction image into the 2D tunnel expansion image to obtain a prediction result. Compared with the prior art, the detection efficiency, the detection precision and the reliability of tunnel water stain diseases are greatly improved.

Description

technical field [0001] The invention relates to a tunnel water stain detection system and method, in particular to a tunnel water stain detection system and method based on computer vision. Background technique [0002] In recent years, with the development of technologies related to artificial intelligence and deep learning, the subject of object detection and image segmentation has also made great progress. On the other hand, water damage in tunnels has brought major safety hazards to road public safety. In current engineering practice, detection of water damage is completely done manually, which consumes a lot of time and financial resources. Relying on the intelligent technology based on computer vision to realize the intelligent detection of water damage is an effective means to improve the efficiency of the project. [0003] Existing target detection algorithms can usually be divided into two-stage methods and one-stage methods: the former often needs to assume the sc...

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): G06T7/00G06K9/34G06K9/62
CPCG06T7/0002G06V10/267G06F18/214
Inventor 陈攀谭鑫马利庄
Owner SHANGHAI JIAO TONG UNIV