The invention discloses a wWater leakage area detection and identification methodrecognition method based on deep learning and a view field projection model

A deep learning and recognition method technology, applied in the field of image processing, can solve problems such as occlusion, lighting, and shadows, and achieve the effect of improving work efficiency

Active Publication Date: 2019-04-12
SHANGHAI UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, there are big laws, regional growth methods, watershed methods, etc., but the disadvantage is that tr...

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
  • The invention discloses a wWater leakage area detection and identification methodrecognition method based on deep learning and a view field projection model
  • The invention discloses a wWater leakage area detection and identification methodrecognition method based on deep learning and a view field projection model
  • The invention discloses a wWater leakage area detection and identification methodrecognition method based on deep learning and a view field projection model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The technical solution of the present invention will be further specifically described below in conjunction with the accompanying drawings and specific embodiments,

[0056] Such as figure 1 As shown, a tunnel water leakage area identification method based on deep learning and field of view projection model includes the following steps:

[0057] a. Use unmanned vehicles for tunnel wall video and point cloud data collection, in which the anti-shake camera is used for video collection, and the 3D laser scanner is used for point cloud data collection;

[0058] b. Perform data enhancement on the training pictures in the collected video;

[0059] c. Make labels for the pictures after data enhancement in step b, and mark the real leakage areas as the reference for the algorithm. Such as figure 2 shown;

[0060] d. By setting the basic parameters of initialization weight, learning rate, batch size and number of iterations, a deep learning network framework suitable for im...

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 discloses a water leakage area detection and identification method based on deep learning and a view field projection model. The method specifically comprises the following steps: 1) collecting video data and point cloud data of a to-be-detected area; 2) detecting the video data acquired in the step 1) through a water leakage image recognition neural network to obtain a water leakagearea picture; 3) identifying the point cloud data acquired in the step 1) to obtain a curved surface shape; A; and 4) performing corresponding curved surface shape projection on the water leakage area picture obtained in the step 2) according to the curved surface shape obtained in the step 3), and calculating the actual area of the water leakage area after projection. Manual participation is notneeded for subway tunnel leakage water area measurement, t, the working efficiency is improved, curved surface projection conversion can be carried out on the detected leakage water area, and the more accurate leakage water area is obtained. Therefore, t, the detection algorithm is high in efficiency and accurate in detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to a method for accurately detecting and identifying water leakage area based on deep learning and a field of view projection model, which is often used in tunnels, houses and other buildings. Background technique [0002] Tunnel water leakage is very common in operational tunnels, and it is a common disease. If it is not repaired in time, the strength of the segment structure will be reduced, and it will cause corrosion of steel bars and bolts, segment cracking and concrete spalling, etc. Other diseases will seriously endanger the operation of the tunnel and may lead to safety accidents. [0003] Traditional inspections of leaking water structures in tunnels mainly use manual inspections, visual inspections, manual records, and photographs for data collection. However, due to the influence of subjective factors, misjudgments, Omissions and other errors are time...

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
IPC IPC(8): G06T7/62G06T7/136G06T7/194G06K9/62G01B11/28
CPCG06T7/136G06T7/194G06T7/62G01B11/28G06T2207/10016G06T2207/10028G06T2207/20068G06T2207/20081G06T2207/20084G06F18/241Y02A20/00
Inventor 高新闻金邦洋胡珉喻钢周丽
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap