CN110097504A - A kind of image vision acquisition system for tunnel crusing robot - Google Patents
A kind of image vision acquisition system for tunnel crusing robot Download PDFInfo
- Publication number
- CN110097504A CN110097504A CN201910395186.8A CN201910395186A CN110097504A CN 110097504 A CN110097504 A CN 110097504A CN 201910395186 A CN201910395186 A CN 201910395186A CN 110097504 A CN110097504 A CN 110097504A
- Authority
- CN
- China
- Prior art keywords
- image
- subsystem
- tunnel
- detection device
- intensity value
- 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
- 230000004438 eyesight Effects 0.000 title claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000010191 image analysis Methods 0.000 claims abstract description 11
- 238000013500 data storage Methods 0.000 claims abstract description 8
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 238000012546 transfer Methods 0.000 claims abstract description 6
- 230000005855 radiation Effects 0.000 claims abstract description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000011282 treatment Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000009466 transformation Effects 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of image vision acquisition systems for tunnel crusing robot, belong to tunnel defect detection technique field, including detection device, data acquisition subsystem, image analysis system, image analysis system includes image real time transfer subsystem and data storage transmission subsystem, detection device is used to acquire the image of crack and percolating water, acquired image is transferred to data acquisition subsystem by detection device, data acquisition subsystem splices to multiple images are collected, data acquisition subsystem stores and transmits spliced lining cutting image and heat radiation images to image real time transfer subsystem via data storage transmission subsystem.The present invention utilizes image fusion system, image to be spliced is transformed into the same coordinate system, keep splicing more simple, splicing effect is more preferable, image is spliced so that the tunnel image that multiple cameras obtain is able to carry out transformation and scaling, it is spliced into a width local section image, subsequent detection efficiency can be improved.
Description
Technical field
The invention belongs to tunnel defect detection technique field, it is related to a kind of image vision for tunnel crusing robot and adopts
Collecting system.
Background technique
During current tunnel Image Acquisition, the detection image that multiple cameras obtain often is had, these detections
There is the depth of field of the problem of translation transformation and tunnel buttress in image, need to merge detection image, and current
Blending image is complex during fusion, and the effect merged is bad, influences the work effect of subsequent Crack Detection
Rate.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of image visions for tunnel crusing robot to acquire system
System.
In order to achieve the above objectives, the invention provides the following technical scheme:
The present invention provides a kind of image vision acquisition systems for tunnel crusing robot, including detection device, number
According to acquisition subsystem, image analysis system, described image analysis system includes that image real time transfer subsystem and data storage pass
Defeated subsystem, the detection device are used to acquire the image of crack and percolating water, and the detection device passes acquired image
It is handed to data acquisition subsystem, the data acquisition subsystem splices to multiple images are collected, the data acquisition
System stores and transmits spliced lining cutting image and heat radiation images to image data via data storage transmission subsystem
Processing subsystem, described image data process subsystem are backstage high-performance treatments computer system, are deposited by high speed storing disk
Image data is stored up, and completes disease recognition by image analysis criterion of identification.
As a preferred technical solution of the present invention, lighting device, optical frames of the detection device by offer illumination
Head, CCD line array sensor and infrared heat sensor are constituted.
As a preferred technical solution of the present invention, the data acquisition subsystem includes registration arrangement and image co-registration
System, the tunnel image that the detection device obtains includes multiple repeat regions, and the data acquisition subsystem will contain
The tunnel image mosaic of multiple overlapping regions be a width local section image during, the registration arrangement be used for image into
Row registration, described image emerging system are used to merge the image after registration.
As a preferred technical solution of the present invention, the registration arrangement extracts characteristic point by Hessian matrix, so
Feature description is carried out using characteristic point circle field afterwards, the use of Haar small echo response is that each characteristic point establishes descriptor, simultaneously
Normalized grey scale difference and second order gradient, form new feature descriptor, using the least euclidean distance criteria in calculating field
Feature Points Matching is carried out, and is mismatched a little using the rejecting of RANSAC algorithm, to complete to be registrated.
As a preferred technical solution of the present invention, described image emerging system is by each picture of overlapping region the first row
The starting point of one splicing seams of vegetarian refreshments (x, y) label, and calculate the intensity value of each point.Search extension, the starting point of each splicing seams
Intensity value unanimously searches last line to next line expanded search.The current point of that each splicing seams is respectively and next line
In with this put 3 adjacent pixels (x, y) intensity value be added, find the picture in next line corresponding to minimal intensity value
Vegetarian refreshments, the pixel (x, y) are exactly the propagation direction found in 3 pixels, and the intensity value of splicing seams is revised as minimum strength
Current point is modified as minimal intensity value and corresponds to pixel (x, y) in next line, then searched for gradually downward, until most by value
A line afterwards.Select best splicing seams.Selection intensity value is the smallest from all splicing seams is used as best splicing seams.In optimal spelling
Centered on seam, it is to be weighted and averaged fusion in nine pixels in width, completes splicing, formula are as follows:
Wherein, w1And w2The weight of corresponding pixel, meets w in image overlapping region respectively to be spliced1+w2=1,0 <
w1,w2< 1, f1(x, y), f2(x, y) indicates pixel coordinate point.
The beneficial effects of the present invention are:
The present invention utilizes image fusion system, and image to be spliced is transformed into the same coordinate system, makes splicing more
Simply, splicing effect is more preferable, is spliced to image so that the tunnel image that multiple cameras obtain is able to carry out transformation and scaling,
It is spliced into a width local section image, subsequent detection efficiency can be improved.
Other advantages, target and feature of the invention will be illustrated in the following description to a certain extent, and
And to a certain extent, based on will be apparent to those skilled in the art to investigating hereafter, Huo Zheke
To be instructed from the practice of the present invention.Target of the invention and other advantages can be realized by following specification and
It obtains.
Detailed description of the invention
To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention is made below in conjunction with attached drawing excellent
The detailed description of choosing, in which:
Fig. 1 is overall structure diagram of the invention.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that diagram provided in following embodiment is only to show
Meaning mode illustrates basic conception of the invention, and in the absence of conflict, the feature in following embodiment and embodiment can phase
Mutually combination.
Wherein, the drawings are for illustrative purposes only and are merely schematic diagrams, rather than pictorial diagram, should not be understood as to this
The limitation of invention;Embodiment in order to better illustrate the present invention, the certain components of attached drawing have omission, zoom in or out, not
Represent the size of actual product;It will be understood by those skilled in the art that certain known features and its explanation may be omitted and be in attached drawing
It is understood that.
Referring to Fig. 1, being a kind of image vision acquisition system for tunnel crusing robot, including detection device, number
According to acquisition subsystem, image analysis system, described image analysis system includes that image real time transfer subsystem and data storage pass
Defeated subsystem, the detection device are used to acquire the image of crack and percolating water, and the detection device passes acquired image
It is handed to data acquisition subsystem, the data acquisition subsystem splices to multiple images are collected, the data acquisition
System stores and transmits spliced lining cutting image and heat radiation images to image data via data storage transmission subsystem
Processing subsystem, described image data process subsystem are backstage high-performance treatments computer system, are deposited by high speed storing disk
Image data is stored up, and completes disease recognition by image analysis criterion of identification.
Detection device is by the lighting device of offer illumination, optical lens, CCD line array sensor and infrared heat sensor structure
At the measurement of realization fracture and percolating water, forms lining cutting image and heat radiation images respectively.
Image mosaic: the tunnel image that multiple cameras in tunnel image, especially this paper image capturing system are obtained,
Translation transformation is only existed between image, there is no rotation transformation or only exists that faint rotation transformation, there is no image scalings to ask
Topic, it is only necessary to which the tunnel image mosaic containing overlapping region is a width schematic partial sectional view by the depth of field problem for considering tunnel buttress
Picture is prepared for subsequent long Crack Detection work, and entire splicing mainly includes two portions of image registration and image co-registration
Point.
Using the improvement SURF algorithm based on round field, characteristic point is extracted by Hessian matrix first, is then used
Characteristic point circle field carries out feature description, is that each characteristic point establishes descriptor, while calculating neck using the response of Haar small echo
Normalized grey scale difference and second order gradient, form new feature descriptor in domain, are carried out using the least euclidean distance criteria special
Sign point matching, and the matching precision for a little further increasing algorithm is mismatched using the rejecting of RANSAC algorithm.
After image registration, the corresponding points relationship of the overlapping region of input picture can be determined, advise using based on dynamic
The optimal seam optimization algorithm of improvement for drawing thought is quickly spliced for image, is then merged using Weighted Average Algorithm.
By the starting point of each one splicing seams of pixel label of overlapping region the first row, and calculate the intensity of each point
Value.Search extension, the starting point intensity value of each splicing seams unanimously search last line to next line expanded search.That is each
The current point of splicing seams is added in next line with this intensity value for putting 3 adjacent pixels respectively, is found minimum strong
Pixel in next line corresponding to angle value, which is exactly the propagation direction found in 3 pixels, the strong of splicing seams
Angle value is revised as minimal intensity value, and current point is modified as minimal intensity value and corresponds to pixel in next line, then gradually to
Lower search, to the last a line.Select best splicing seams.Selection intensity value is the smallest from all splicing seams spells as best
Seam.Centered on optimal splicing seams, it is to be weighted and averaged fusion in nine pixels in width, completes splicing.Weighting is melted
Hop algorithm is described as follows:
Using homography matrix, image to be spliced is transformed into the same coordinate system, utilizes the weighting of formula as follows
Smoothing algorithm is merged, and this method is relatively easy, and syncretizing effect is good.
Wherein w1And w2The weight of corresponding pixel, meets w in image overlapping region respectively to be spliced1+w2=1,0 <
w1,w2< 1.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of the technical program, should all be covered in the present invention
Scope of the claims in.
Claims (5)
1. a kind of image vision acquisition system for tunnel crusing robot, it is characterised in that: adopted including detection device, data
Subsystem, image analysis system, described image analysis system include image real time transfer subsystem and data storage transmission
System, the detection device are used to acquire the image of crack and percolating water, and acquired image is transferred to by the detection device
Data acquisition subsystem, the data acquisition subsystem splice to multiple images are collected, the data acquisition subsystem
Spliced lining cutting image and heat radiation images are stored and transmitted via data storage transmission subsystem to image real time transfer
Subsystem, described image data process subsystem is backstage high-performance treatments computer system, by high speed storing disk map
Disease recognition is completed as data, and by image analysis criterion of identification.
2. a kind of image vision acquisition system for tunnel crusing robot according to claim 1, it is characterised in that:
The detection device is made of the lighting device of offer illumination, optical lens, CCD line array sensor and infrared heat sensor.
3. a kind of image vision acquisition system for tunnel crusing robot according to claim 1, it is characterised in that:
The data acquisition subsystem includes registration arrangement and image fusion system, and the tunnel image that the detection device obtains includes
Multiple repeat regions, the data acquisition subsystem are that a width is locally disconnected in the tunnel image mosaic that will contain multiple overlapping regions
During the image of face, the registration arrangement is for being registrated image, and described image emerging system will be for after being registrated
Image is merged.
4. a kind of image vision acquisition system for tunnel crusing robot according to claim 3, it is characterised in that:
The registration arrangement extracts characteristic point by Hessian matrix, then carries out feature description using characteristic point circle field, uses
The response of Haar small echo establishes descriptor for each characteristic point, while normalized grey scale difference and second order gradient in calculating field,
New feature descriptor is formed, Feature Points Matching is carried out using the least euclidean distance criteria, and reject and miss using RANSAC algorithm
With point, to complete to be registrated.
5. a kind of image vision acquisition system for tunnel crusing robot according to claim 3, it is characterised in that:
Described image emerging system calculates the starting point of one splicing seams of each pixel (x, y) label of overlapping region the first row
The intensity value of each point.Search extension, the starting point intensity value of each splicing seams is to next line expanded search, and consistent search is to the end
A line.The current point of that each splicing seams respectively with the intensity value of putting 3 adjacent pixels (x, y) in next line with this
It is added, finds the pixel in next line corresponding to minimal intensity value, which is exactly to find in 3 pixels
The intensity value of splicing seams is revised as minimal intensity value, current point is modified as minimal intensity value and corresponds to next line by propagation direction
In pixel (x, y), then search for gradually downward, to the last a line.Select best splicing seams.From all splicing seams
Selection intensity value is the smallest to be used as best splicing seams.It is to be added in nine pixels in width centered on optimal splicing seams
Weight average fusion, completes splicing, formula are as follows:
Wherein, w1And w2The weight of corresponding pixel, meets w in image overlapping region respectively to be spliced1+w2=1,0 < w1,w2
< 1, f1(x, y), f2(x, y) indicates pixel coordinate point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910395186.8A CN110097504A (en) | 2019-05-13 | 2019-05-13 | A kind of image vision acquisition system for tunnel crusing robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910395186.8A CN110097504A (en) | 2019-05-13 | 2019-05-13 | A kind of image vision acquisition system for tunnel crusing robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110097504A true CN110097504A (en) | 2019-08-06 |
Family
ID=67447801
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910395186.8A Pending CN110097504A (en) | 2019-05-13 | 2019-05-13 | A kind of image vision acquisition system for tunnel crusing robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110097504A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111415344A (en) * | 2020-03-19 | 2020-07-14 | 北京城建勘测设计研究院有限责任公司 | Disease detection method and device for horseshoe-shaped tunnel |
CN112767353A (en) * | 2021-01-19 | 2021-05-07 | 中国科学院武汉岩土力学研究所 | Tunnel lining crack disease evaluation method and equipment |
CN113960049A (en) * | 2021-10-19 | 2022-01-21 | 中南大学 | Tunnel surface disease detection device and detection method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105550995A (en) * | 2016-01-27 | 2016-05-04 | 武汉武大卓越科技有限责任公司 | Tunnel image splicing method and system |
CN106910159A (en) * | 2016-10-12 | 2017-06-30 | 王玲 | Video-splicing method and device |
CN107146201A (en) * | 2017-05-08 | 2017-09-08 | 重庆邮电大学 | A kind of image split-joint method based on improvement image co-registration |
CN108592876A (en) * | 2018-04-24 | 2018-09-28 | 招商局重庆交通科研设计院有限公司 | Tunnel appearance Defect inspection robot based on laser scanning imaging principle |
CN109029277A (en) * | 2018-06-27 | 2018-12-18 | 常州沃翌智能科技有限公司 | A kind of tunnel deformation monitoring system and method |
-
2019
- 2019-05-13 CN CN201910395186.8A patent/CN110097504A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105550995A (en) * | 2016-01-27 | 2016-05-04 | 武汉武大卓越科技有限责任公司 | Tunnel image splicing method and system |
CN106910159A (en) * | 2016-10-12 | 2017-06-30 | 王玲 | Video-splicing method and device |
CN107146201A (en) * | 2017-05-08 | 2017-09-08 | 重庆邮电大学 | A kind of image split-joint method based on improvement image co-registration |
CN108592876A (en) * | 2018-04-24 | 2018-09-28 | 招商局重庆交通科研设计院有限公司 | Tunnel appearance Defect inspection robot based on laser scanning imaging principle |
CN109029277A (en) * | 2018-06-27 | 2018-12-18 | 常州沃翌智能科技有限公司 | A kind of tunnel deformation monitoring system and method |
Non-Patent Citations (3)
Title |
---|
瞿中 等: "一种消除图像拼接缝和鬼影的快速拼接算法", 《计算机科学》 * |
董强 等: "用于遥感图像拼接的改进SURF算法", 《吉林大学学报(工学版)》 * |
高泰: "隧道裂缝图像采集与检测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111415344A (en) * | 2020-03-19 | 2020-07-14 | 北京城建勘测设计研究院有限责任公司 | Disease detection method and device for horseshoe-shaped tunnel |
CN112767353A (en) * | 2021-01-19 | 2021-05-07 | 中国科学院武汉岩土力学研究所 | Tunnel lining crack disease evaluation method and equipment |
CN113960049A (en) * | 2021-10-19 | 2022-01-21 | 中南大学 | Tunnel surface disease detection device and detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110097504A (en) | A kind of image vision acquisition system for tunnel crusing robot | |
CN109961399B (en) | Optimal suture line searching method based on image distance transformation | |
CN105957007B (en) | Image split-joint method based on characteristic point plane similarity | |
CN105100640B (en) | A kind of local registration parallel video joining method and system | |
CN104685513B (en) | According to the high-resolution estimation of the feature based of the low-resolution image caught using array source | |
CN107907048A (en) | A kind of binocular stereo vision method for three-dimensional measurement based on line-structured light scanning | |
CN105678776B (en) | Weld image feature point extraction method based on laser vision sensor | |
CN103902953B (en) | A kind of screen detecting system and method | |
CN103258321A (en) | Image stitching method | |
Moghadam et al. | Road direction detection based on vanishing-point tracking | |
CN110110793B (en) | Binocular image rapid target detection method based on double-current convolutional neural network | |
CN109685078A (en) | Infrared image recognition based on automatic marking | |
CN106952225A (en) | A kind of panorama mosaic method towards forest fire protection | |
Lin et al. | Efficient vessel feature detection for endoscopic image analysis | |
CN106875419A (en) | Small and weak tracking of maneuvering target based on NCC matching frame differences loses weight detecting method | |
CN105447817B (en) | A kind of hot-rolled intermediate billet flat image joining method based on edge contour | |
US20180300954A1 (en) | Method and device for seeing through an obstruction based on smart glasses, and computer-readable storage medium | |
CN114495068B (en) | Pavement health detection method based on human-computer interaction and deep learning | |
CN112164001A (en) | Digital microscope image rapid splicing and fusing method | |
CN106780309A (en) | A kind of diameter radar image joining method | |
Ruan et al. | Image stitching algorithm based on SURF and wavelet transform | |
CN115063477A (en) | Infrared and visible light double-channel synchronous imaging real-time registration fusion acquisition method and device | |
JPH05215547A (en) | Method for determining corresponding points between stereo images | |
CN109448033A (en) | A kind of method for registering images based on BRISK algorithm | |
CN115100556A (en) | Augmented reality method and device based on image segmentation and fusion and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |