CN102589808A - Large-scale tunnel seepage point measuring method - Google Patents
Large-scale tunnel seepage point measuring method Download PDFInfo
- Publication number
- CN102589808A CN102589808A CN2012100122230A CN201210012223A CN102589808A CN 102589808 A CN102589808 A CN 102589808A CN 2012100122230 A CN2012100122230 A CN 2012100122230A CN 201210012223 A CN201210012223 A CN 201210012223A CN 102589808 A CN102589808 A CN 102589808A
- Authority
- CN
- China
- Prior art keywords
- tunnel
- image
- dolly
- tunnel wall
- infiltration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a large-scale tunnel seepage point measuring method. The method mainly adopts the image processing and image recognition methods. The characteristics of seepage points are extracted by collecting an image of the tunnel wall and using the image recognition method, so that the detection and positioning of the seepage points are completed. The method mainly comprises the following procedures of image collection, image fusion, image preprocessing, image segmentation, image recognition, seepage point positioning and detection report representation. With the measuring method, the seepage situation of the tunnel can be accurately measured, engineers are instructed to prevent hidden tunnel seepage dangers in advance and reinforce the tunnel base. Meanwhile, the measuring method is convenient and quick and has low cost, and early warning information can be given accurately and timely.
Description
Technical field
The present invention relates to a kind of large tunnel infiltration point measurement method.
Background technology
Along with development of modern science and technology; In life, the utilization in tunnel is more and more, especially at the bottom of seabed, lakebed, river etc. below the water body; Large-scale tunnel seeps water in construction and use easily, and the automatic measurement of infiltration point is a difficult problem.In conventional art, the method for measuring the infiltration point is fewer, needs to rely on the method for artificial observation under a lot of situation, and this method needs manpower and consuming time more, and efficient is not high.The infrared radiation method as the term suggests be exactly to detected object irradiation infrared ray, utilizes the decay of its reflected light special spectrum to detect infiltration point position.The electrode detection method then is to utilize when electrode contact interelectrode change in resistance to detect infiltration point.The quality of also with good grounds ph test paper ph contact wetting detects infiltration point position.
Yet it is bigger that the infrared radiation method is influenced by object material and surface tinted, during the detection error it arranged.But also there is huge, the problem of ultra-high price of pick-up unit.
For the electrode detection method, if there is not water droplet in the tunnel wall, water droplet is perhaps arranged but water droplet when also littler than electrode interbody spacer, this method just can not detect.And, because being contact, this method detects, so can there be the problem on surface, damage measured point.
And for the detection method of service test paper, if the outside no water droplet of tunnel wall, this method can not be used.
Top several different methods is more suitable for detecting small pipeline or the minitunnel infiltration detects, and for large tunnel, these detection method workloads are very big, are not easy to implement.
Summary of the invention
The technical matters that the present invention will solve is: to the problems referred to above; A kind of large tunnel infiltration point measurement method is provided, and this method can be measured the infiltration situation in tunnel accurately, instructs the engineering staff to prevent tunnel infiltration hidden danger in advance; Reinforce the tunnel matrix; This measuring method is convenient and swift simultaneously, and cost is low, can accurately and timely give early warning information.
Technical scheme of the present invention is: large tunnel infiltration point detecting method of the present invention may further comprise the steps:
Step 1, in tunnel to be detected, arrange the dolly that in the tunnel, to advance, will be installed on this dolly by the image collecting device that camera, camera lens and lighting lamp group are dressed up;
The position of step 2, adjustment camera and the position of focal length and illuminating lamp make the phase function collect the clear pictures of tunnel wall;
Step 3, dolly is advanced in the tunnel, and the dolly certain distance of whenever advancing just stays for some time, dolly stop during this period of time in, gather the photo of tunnel wall with camera, until the IMAQ of accomplishing whole tunnel wall;
Step 4, each photo that will gather import computing machine, utilize software that these photos are carried out image co-registration and image length is demarcated, and obtain the complete image of the whole tunnel wall after the amalgamation;
Step 5, the whole tunnel wall complete image of amalgamation is carried out noise reduction, filtering and image binaryzation handle, weed out duct shade and crack on the tunnel wall in the image;
Step 6, according to the whole tunnel wall complete image after step 5 is handled; The whole tunnel wall complete image that step 4 is obtained carries out dividing processing; Extract the zone of similar water mark, and note boundary characteristic, shape characteristic and the gray feature in the zone of these similar water marks;
Step 7, many characteristics in the zone of similar water mark are discerned, determined real water mark zone through artificial neural network;
The location positioning in step 8, the real water mark zone that will determine is in the whole tunnel wall complete image that step 4 obtains, according to the dimension of the image point location that seeps water;
Step 9, the water mark that provides whole tunnel and infiltration spot check observe and predict announcement, and the content of this examining report comprises the size and the position in infiltration number of spots, each water mark zone.
As preferably, the present invention is equipped with motion controller on said dolly.In said tunnel, be furnished with and be convenient to the track that dolly is advanced.Said track is arranged in the centre position of tunnel width direction as far as possible.
The present invention has mainly adopted the method for Flame Image Process and image recognition, through gathering the image of tunnel wall, utilizes the method for image recognition to extract infiltration point characteristic, detects and the location thereby accomplish the infiltration point, has the following advantages:
1, this method is simple to operation, and robotization detects the infiltration point position and the whole infiltration situation in tunnel, can improve tunnel infiltration early warning and crisis processing power greatly.
2, this method has adopted the optical non-contact measurement mode, and infiltration situation and infiltration point position through a series of tunnel wall graphical analyses of taking being calculated the tunnel need not artificial the interference, and reliable measurement property is high.
3, the detection method of the present invention's proposition does not receive surrounding environment influence, and efficient is high, and price is honest and clean.
Description of drawings
Fig. 1 is the process flow diagram of embodiment of the invention large tunnel deformation measurement method.
Embodiment
With reference to shown in Figure 1, present embodiment large tunnel deformation measurement method comprises following nine steps, and wherein step 1 to step 3 is " IMAQ "; Step 4 is " image co-registration ", and step 5 is " image pre-service ", and step 6 is " image segmentation "; Step 7 is " image recognition "; Step 8 is " an infiltration point location ", and step 9 is " providing examining report ", and these nine steps are specially:
Step 1, in tunnel to be detected, arrange the dolly that in the tunnel, to advance; To be installed in by the image collecting device that camera, camera lens and lighting lamp group are dressed up on this dolly (according to measuring distance in the measuring process select lens parameters, camera resolution size, pixel is big or small and the illuminating lamp of moderate brightness); So that dolly is when advancing in the tunnel; Camera can be gathered the image of tunnel wall at any time, is used for subsequent analysis.
For the ease of advancing of dolly, this example has also been installed motion controller on dolly, in the tunnel, arranged track.Wherein: motion controller may command dolly advancing in the tunnel, the sports rule of dolly can artificially be set on this motion controller according to the measurement needs; The subway rail of the similar of track in subway tunnel, and should guarantee the centre position of this orbital arrangement in the tunnel width direction as far as possible, the distance of tunnel wall is about equally around arriving with the camera on the assurance dolly.
The move distance of dolly is by being installed in dolly on the dolly with the shaft encoder record, and this distance parameter will carry out image co-registration and the image length timing signal uses follow-up.
In order to obtain reasonable shooting effect, to following requirement is arranged as this step 1:
To the selected camera lens focal length of the distance of tunnel wall, should guarantee that the visual field of taking is enough big according to camera, guarantee that again the photo distortion of taking is little.If shooting distance is about 2m, preferably select 20mm or 24mm camera lens.Because the space is limited in the tunnel; The sighting distance of images acquired is little, the visual field is big, and problems such as image border distortion that causes and difference in exposure bring the image pretreating effect poor; Possibly influence the later stage cuts apart recognition effect, needs hardware such as the high camera of performance, camera lens and light source to this problem.
The position and the focal length of step 2, adjustment camera are adjusted the position of illuminating lamp simultaneously, make the phase function collect the clear pictures of tunnel wall.Generally camera parameter does not change to reduce measuring error in the process of taking pictures.
During above-mentioned adjustment illuminating lamp position, require on the tunnel wall of the dark that camera institute will take, to form the moderate illumination of uniform brightness, the sharpness and the brightness of the photo of taking with camera suit to be as the criterion.
Step 3, startup moving of car controller are advanced dolly in the tunnel; Dolly is advanced and is stopped behind the segment distance; Dolly stop during this period of time in; Gather the photo (camera can rotate, and revolution moves an angle shot once, thereby obtains image around the dolly dwell regions tunnel) of tunnel wall on dolly with camera; Control dolly then and advance again and stop again behind the segment distance, gather the tunnel wall photo at another place with camera; Successively down, until the IMAQ of accomplishing whole tunnel wall.
The most handy high-powered LED lamp illumination is clear available to guarantee the tunnel wall photo that collects in this process.
Step 4, each photo that will gather import computing machine, utilize software that these photos are carried out image co-registration and image length is demarcated, and obtain the complete image of the whole tunnel wall after the amalgamation, so that water mark location is carried out in the back.
Image co-registration (Image Fusion) be meant the multi-source channel is collected about the view data of same target through Flame Image Process and computer technology etc.; Extract the favourable information in each self-channel to greatest extent; The high-quality image of last comprehensive one-tenth; With the utilization factor that improves image information, improve the spatial resolution and the spectral resolution of computing machine decipher precision and reliability, lifting original image, be beneficial to monitoring.
Step 5, the whole tunnel wall complete image of amalgamation is carried out the pre-service of noise reduction, filtering and image binaryzation, weed out duct shade and crack on the tunnel wall in the image, thereby eliminate the interference of duct shade and crack water mark characteristic.
Step 6, according to the whole tunnel wall complete image after handling through step 5; The whole tunnel wall complete image that step 4 is obtained carries out dividing processing; The zone that extracts the similar water mark is (in the zone of these similar water marks; A part is real water mark zone, and another part is not really to be water mark zone), and note boundary characteristic, shape characteristic and the gray feature in the zone of these similar water marks.
Step 7, through artificial neural network many characteristics (like boundary characteristic, shape characteristic, gray feature etc.) in similar water mark zone are discerned, which is determined is real water mark zone.
The location positioning in step 8, the real water mark zone that will determine is in the whole tunnel wall complete image that step 4 obtains, according to the dimension of the image point location that seeps water;
Step 9, the water mark that provides whole tunnel and infiltration spot check observe and predict announcement, and the content of this examining report comprises the size and the position in infiltration number of spots, each water mark zone.
Certainly, the foregoing description only is explanation technical conceive of the present invention and characteristics, and its purpose is to let people can understand content of the present invention and implements according to this, can not limit protection scope of the present invention with this.The all spirit of main technical schemes is done according to the present invention equivalent transformation or modification all should be encompassed within protection scope of the present invention.
Claims (4)
1. large tunnel infiltration point detecting method is characterized in that may further comprise the steps:
Step 1, in tunnel to be detected, arrange the dolly that in the tunnel, to advance, will be installed on this dolly by the image collecting device that camera, camera lens and lighting lamp group are dressed up;
The position of step 2, adjustment camera and the position of focal length and illuminating lamp make the phase function collect the clear pictures of tunnel wall;
Step 3, dolly is advanced in the tunnel, and the dolly certain distance of whenever advancing just stays for some time, dolly stop during this period of time in, gather the photo of tunnel wall with camera, until the IMAQ of accomplishing whole tunnel wall;
Step 4, each photo that will gather import computing machine, utilize software that these photos are carried out image co-registration and image length is demarcated, and obtain the complete image of the whole tunnel wall after the amalgamation;
Step 5, the whole tunnel wall complete image of amalgamation is carried out noise reduction, filtering and image binaryzation handle, weed out duct shade and crack on the tunnel wall in the image;
Step 6, according to the whole tunnel wall complete image after step 5 is handled; The whole tunnel wall complete image that step 4 is obtained carries out dividing processing; Extract the zone of similar water mark, and note boundary characteristic, shape characteristic and the gray feature in the zone of these similar water marks;
Step 7, many characteristics in the zone of similar water mark are discerned, determined real water mark zone through artificial neural network;
The location positioning in step 8, the real water mark zone that will determine is in the whole tunnel wall complete image that step 4 obtains, according to the dimension of the image point location that seeps water;
Step 9, the water mark that provides whole tunnel and infiltration spot check observe and predict announcement, and the content of this examining report comprises the size and the position in infiltration number of spots, each water mark zone.
2. large tunnel infiltration point detecting method according to claim 1 and 2 is characterized in that: on the said dolly motion controller is installed.
3. large tunnel infiltration point detecting method according to claim 1 and 2 is characterized in that: be furnished with in the said tunnel and be convenient to the track that dolly is advanced.
4. large tunnel infiltration point detecting method according to claim 3, it is characterized in that: said orbital arrangement is in the centre position of tunnel width direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100122230A CN102589808A (en) | 2012-01-16 | 2012-01-16 | Large-scale tunnel seepage point measuring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100122230A CN102589808A (en) | 2012-01-16 | 2012-01-16 | Large-scale tunnel seepage point measuring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102589808A true CN102589808A (en) | 2012-07-18 |
Family
ID=46478758
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012100122230A Pending CN102589808A (en) | 2012-01-16 | 2012-01-16 | Large-scale tunnel seepage point measuring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102589808A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105120224A (en) * | 2015-09-09 | 2015-12-02 | 招商局重庆交通科研设计院有限公司 | Tunnel water disaster intelligent monitoring system and method based on video event detection |
CN106326901A (en) * | 2016-08-30 | 2017-01-11 | 南京鑫和汇通电子科技有限公司 | Water stain image recognition based on edge point self-similarity and TEDS system |
CN106651843A (en) * | 2016-12-15 | 2017-05-10 | 太原科技大学 | Image processing method for tunnel water seepage detection |
CN106802215A (en) * | 2015-11-20 | 2017-06-06 | 沈阳新松机器人自动化股份有限公司 | A kind of device for detecting water leakage of water pipe and detection method |
CN107358270A (en) * | 2017-08-08 | 2017-11-17 | 浙江国自机器人技术有限公司 | A kind of infiltration detection method and device of tunnel wall |
CN110458044A (en) * | 2019-07-22 | 2019-11-15 | 苏州慧润百年物联科技有限公司 | A kind of judgement ground immersion method based on image recognition |
CN112070754A (en) * | 2020-09-11 | 2020-12-11 | 武汉百家云科技有限公司 | Tunnel segment water leakage detection method and device, electronic equipment and medium |
CN115035060A (en) * | 2022-06-07 | 2022-09-09 | 贵州聚原数技术开发有限公司 | Tunnel wall deformation detection method based on computer image recognition |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11259656A (en) * | 1998-03-10 | 1999-09-24 | Teito Rapid Transit Authority | Tunnel wall surface decision device |
JP2011117788A (en) * | 2009-12-02 | 2011-06-16 | Sumitomo Mitsui Construction Co Ltd | Concrete surface inspection device |
CN102211590A (en) * | 2011-04-07 | 2011-10-12 | 同济大学 | Detecting vehicle for tunnel |
CN102261982A (en) * | 2011-04-26 | 2011-11-30 | 同济大学 | Early warning method for water seepage of tunnel |
CN102279081A (en) * | 2011-04-26 | 2011-12-14 | 同济大学 | Method and device for detecting water seepage of tunnel |
-
2012
- 2012-01-16 CN CN2012100122230A patent/CN102589808A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11259656A (en) * | 1998-03-10 | 1999-09-24 | Teito Rapid Transit Authority | Tunnel wall surface decision device |
JP2011117788A (en) * | 2009-12-02 | 2011-06-16 | Sumitomo Mitsui Construction Co Ltd | Concrete surface inspection device |
CN102211590A (en) * | 2011-04-07 | 2011-10-12 | 同济大学 | Detecting vehicle for tunnel |
CN102261982A (en) * | 2011-04-26 | 2011-11-30 | 同济大学 | Early warning method for water seepage of tunnel |
CN102279081A (en) * | 2011-04-26 | 2011-12-14 | 同济大学 | Method and device for detecting water seepage of tunnel |
Non-Patent Citations (1)
Title |
---|
唐磊: "基于图像分析的路面病害自动检测", 《中国博士学位论文全文数据库信息科技辑》, no. 06, 15 December 2007 (2007-12-15), pages 3 - 6 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105120224A (en) * | 2015-09-09 | 2015-12-02 | 招商局重庆交通科研设计院有限公司 | Tunnel water disaster intelligent monitoring system and method based on video event detection |
CN106802215A (en) * | 2015-11-20 | 2017-06-06 | 沈阳新松机器人自动化股份有限公司 | A kind of device for detecting water leakage of water pipe and detection method |
CN106326901A (en) * | 2016-08-30 | 2017-01-11 | 南京鑫和汇通电子科技有限公司 | Water stain image recognition based on edge point self-similarity and TEDS system |
CN106326901B (en) * | 2016-08-30 | 2019-06-14 | 南京鑫和汇通电子科技有限公司 | Water stain image-recognizing method and TEDS system based on marginal point self-similarity |
CN106651843A (en) * | 2016-12-15 | 2017-05-10 | 太原科技大学 | Image processing method for tunnel water seepage detection |
CN106651843B (en) * | 2016-12-15 | 2019-09-03 | 太原科技大学 | The image processing method of water seepage of tunnel detection |
CN107358270A (en) * | 2017-08-08 | 2017-11-17 | 浙江国自机器人技术有限公司 | A kind of infiltration detection method and device of tunnel wall |
CN107358270B (en) * | 2017-08-08 | 2020-12-25 | 浙江国自机器人技术股份有限公司 | Water seepage detection method and device for tunnel wall |
CN110458044A (en) * | 2019-07-22 | 2019-11-15 | 苏州慧润百年物联科技有限公司 | A kind of judgement ground immersion method based on image recognition |
CN112070754A (en) * | 2020-09-11 | 2020-12-11 | 武汉百家云科技有限公司 | Tunnel segment water leakage detection method and device, electronic equipment and medium |
CN115035060A (en) * | 2022-06-07 | 2022-09-09 | 贵州聚原数技术开发有限公司 | Tunnel wall deformation detection method based on computer image recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102589808A (en) | Large-scale tunnel seepage point measuring method | |
CN110529186B (en) | Tunnel structure water leakage accurate identification device and method based on infrared thermal imaging | |
US11421659B2 (en) | Method and device for determining tower clearance for wind turbine | |
Huang et al. | Inspection equipment study for subway tunnel defects by grey-scale image processing | |
CN104914108B (en) | Freeway tunnel detection car system based on machine vision | |
CN105784710B (en) | A kind of glue into concrete beam cracks detection device based on Digital Image Processing | |
CN104730091B (en) | The extraction of gas turbine blades defect and analysis method based on region segmentation detection | |
CN104062354A (en) | Steel pipe magnetic powder inspection fluorescent image detection apparatus and detection method | |
CN102175701A (en) | System and method for online flaw detection of industrial X-ray machine | |
CN104165653B (en) | For gathering device and the acquisition method thereof of bearing roller end face and chamfering image | |
CN107064172A (en) | A kind of Tunnel Lining Cracks rapid detection system | |
JP2009133085A (en) | Crack checking device for tunnel lining | |
CN102842034A (en) | Device for laser scanning and automatically identifying carved character and identification method | |
CN206223683U (en) | A kind of tabular workpiece with hole surface defect detection apparatus | |
CN113418925A (en) | Photovoltaic panel abnormal target detection system and method based on satellite images | |
CN114941807A (en) | Unmanned aerial vehicle-based rapid monitoring and positioning method for leakage of thermal pipeline | |
CN112967221A (en) | Shield constructs section of jurisdiction production and assembles information management system | |
CN113670931A (en) | Steel plate surface defect detection method and system based on neural network | |
CN113902792B (en) | Building height detection method, system and electronic equipment based on improved RETINANET network | |
CN209182255U (en) | A kind of bridge surface crack detection device | |
CN102538759A (en) | Method for fully-automatically catching near earth and medium and high orbit space targets in real time | |
CN113155852A (en) | Transmission band detection method and device and electronic equipment | |
Yang et al. | A real-time tunnel surface inspection system using edge-AI on drone | |
CN113566704A (en) | Bearing assembly ball size detection method based on machine vision | |
CN116667775A (en) | Unmanned aerial vehicle-based photovoltaic electric field automatic cleaning method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120718 |