CN111260615A - Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge - Google Patents
Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge Download PDFInfo
- Publication number
- CN111260615A CN111260615A CN202010032544.1A CN202010032544A CN111260615A CN 111260615 A CN111260615 A CN 111260615A CN 202010032544 A CN202010032544 A CN 202010032544A CN 111260615 A CN111260615 A CN 111260615A
- Authority
- CN
- China
- Prior art keywords
- disease
- image
- target detection
- detection surface
- unmanned aerial
- 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.)
- Granted
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 116
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 116
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims description 25
- 238000001514 detection method Methods 0.000 claims abstract description 93
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/20036—Morphological image processing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an unmanned aerial vehicle bridge apparent disease detection method based on laser and machine vision fusion, which comprises the following steps: an unmanned aerial vehicle with a laser ranging device, a positioning device and an image acquisition device acquires an image of a target detection surface, the position of the target detection surface and the distance between the unmanned aerial vehicle and the target detection surface; inputting the target detection surface image into a disease recognition neural network to recognize the disease in the target detection surface image and the position of the disease in the target detection surface image; calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface; and generating apparent bridge disease detection information. The invention can realize automatic detection of diseases, save a large amount of time and cost, improve the detection accuracy, automatically and accurately calculate the parameters of the diseases and improve the detection efficiency.
Description
Technical Field
The invention relates to the field of bridge detection, in particular to an unmanned aerial vehicle bridge apparent disease detection method based on laser and machine vision fusion.
Background
The construction of highway bridges in China has been rapidly developed for more than 30 years, and has become the country with the most number of constructed bridges in the world. According to the statistical bulletin developed by the transportation industry of the department of transportation in 2016, the total mileage of the road is 469.63 kilometers in China by the end of 2016. Wherein, the highway mileage of four and above grades in the country is 422.65 kilometers, and the highway mileage reaches 13.10 kilometers. Highway bridge 80.53 ten thousand seats, 4916.97 ten thousand meters. According to the classification statistics of the bridges, 4257 and 753.54 kilometers of the extra-large bridge, 86178 and 2251.50 kilometers of the bridge are counted.
At present, bridge external detection is mainly carried out in the bridge detection industry in modes of bridge inspection vehicles, telescopes, video monitoring and the like, and due to the distance and the resolution of the telescopes and the video monitoring, the bridge cannot be detected more finely. Therefore, the general bridge inspection vehicle in the industry can be used for carrying out detailed detection on the outside of the bridge.
Most of the bridge inspection vehicle is formed by additionally arranging various special working devices on the basis of a second-class truck chassis. The chassis is divided into two main categories, namely a hanging basket type bridge inspection vehicle and a truss type bridge inspection vehicle, according to different working devices on the chassis.
At present, an aircraft system for bridge detection at home and abroad generally uses an aircraft as a carrying platform, and carries a related bridge detection instrument on the aircraft to detect a bridge, however, the existing method generally adopts human eyes to identify the diseases, the method is low in efficiency and too dependent on the experience of personnel, the accuracy is low, and the sizes of the diseases cannot be directly obtained from images collected by the aircraft.
In conclusion, how to efficiently and accurately detect the apparent bridge diseases and acquire the size parameters of the diseases becomes a problem which needs to be solved by the technical personnel in the field.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to efficiently and accurately detect the apparent bridge diseases and obtain the size parameters of the diseases.
In order to solve the technical problems, the invention adopts the following technical scheme:
the method for detecting the apparent diseases of the unmanned aerial vehicle bridge based on the fusion of laser and machine vision comprises the following steps:
an unmanned aerial vehicle with a laser ranging device, a positioning device and an image acquisition device acquires an image of a target detection surface, the position of the target detection surface and the distance between the unmanned aerial vehicle and the target detection surface;
inputting the target detection surface image into a disease recognition neural network to recognize the disease in the target detection surface image and the position of the disease in the target detection surface image;
calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface;
and generating apparent bridge disease detection information.
Preferably, the training method of the disease recognition neural network comprises the following steps:
acquiring an apparent bridge disease image and a corresponding recognition result;
taking the bridge apparent disease images and corresponding recognition results in a preset proportion as a training set, and taking the rest bridge apparent disease images and corresponding recognition results as a test set;
inputting the training set into a disease recognition neural network to be trained for training until the recognition accuracy is greater than or equal to the preset accuracy after the test set is used for testing;
and storing the trained disease recognition neural network.
Preferably, the calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface includes:
calibrating the target detection surface image by a checkerboard method, acquiring the focal length and distortion parameters of the image acquisition device, and correcting the target detection surface image by using the distortion parameters;
preprocessing the corrected image;
acquiring a disease image by using the position of the disease in the target detection surface image and carrying out binarization processing;
acquiring edge information of the disease image after binarization processing by using an edge detection algorithm, and performing morphological corrosion expansion and connection on the edge to acquire a complete disease edge;
calculating the image size of the disease by using the disease edge;
and calculating the actual size of the disease by using the image size of the disease and the distance between the unmanned aerial vehicle and the target detection surface, and taking the actual size of the disease as the size parameter of the disease.
Preferably, the preprocessing in the preprocessing of the corrected image includes image enhancement, motion blur removal and uneven illumination elimination;
preferably, the disease identification neural network is a target detection network using feature map fusion, image features are constructed by fusing feature maps of different convolution layers, the size of a deeper feature map is consistent with that of a feature map of a previous layer by a deconvolution method, then addition operation is performed to perform feature fusion to obtain a new feature map, and the new feature map is fused with the feature map of the previous layer until all feature maps are classified.
In summary, the invention discloses an unmanned aerial vehicle bridge apparent disease detection method based on laser and machine vision fusion, which comprises the following steps: an unmanned aerial vehicle with a laser ranging device, a positioning device and an image acquisition device acquires an image of a target detection surface, the position of the target detection surface and the distance between the unmanned aerial vehicle and the target detection surface; inputting the target detection surface image into a disease recognition neural network to recognize the disease in the target detection surface image and the position of the disease in the target detection surface image; calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface; and generating apparent bridge disease detection information. The invention can realize automatic detection of diseases, save a large amount of time and cost, improve the detection accuracy, automatically and accurately calculate the parameters of the diseases and improve the detection efficiency.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for detecting apparent diseases of bridges of an unmanned aerial vehicle based on fusion of laser and machine vision;
FIG. 2 is a structural diagram of an unmanned aerial vehicle bridge apparent disease detection method based on laser and machine vision fusion;
FIGS. 3(a) and (b) are a crack image and an image after crack binarization processing;
FIGS. 4(a) and (b) are schematic diagrams of crack length calculations;
fig. 5 is a schematic diagram of crack width calculation.
FIG. 6 is a schematic diagram of a feature graph fused target detection network.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
As shown in FIG. 1, the invention discloses an unmanned aerial vehicle bridge apparent disease detection method based on laser and machine vision fusion, which comprises the following steps:
an unmanned aerial vehicle with a laser ranging device (a laser ranging sensor), a positioning device and an image acquisition device acquires an image of a target detection surface, the position of the target detection surface and the distance between the unmanned aerial vehicle and the target detection surface;
inputting the target detection surface image into a disease recognition neural network to recognize the disease in the target detection surface image and the position of the disease in the target detection surface image;
calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface;
and generating apparent bridge disease detection information (detection result).
The invention can realize automatic detection of diseases, save a large amount of time and cost, improve the detection accuracy, automatically and accurately calculate the parameters of the diseases and improve the detection efficiency. The bridge apparent disease detection information may include the location, size, and category of the disease.
As shown in fig. 2, in the present invention, the image capturing device may employ a high-definition camera, and the positioning device may employ a GPS. After the unmanned aerial vehicle collects various information, the information is transmitted to a processor (an onboard computer), and the processor processes the information according to prestored programs and data to generate bridge apparent disease detection information. The unmanned aerial vehicle can guarantee normal flight and path flight by means of an internal sensor and an attitude stabilization algorithm. Rely on the basic information of the inside data of unmanned aerial vehicle and bridge, the airborne computer calculates the shooting angle of airborne high definition digtal camera, makes the shooting direction perpendicular with the bridge floor all the time. The method comprises the steps of obtaining basic information of the bridge, wherein the basic information of the bridge comprises position information of the bridge in reality, and the position information of each apparent surface of the bridge is contained; the internal data of the unmanned aerial vehicle comprises position information of the unmanned aerial vehicle in the real world, including GPS coordinate position and compass information; the shooting angle of the camera can be calculated by utilizing the position information and the compass information of each surface of the bridge, so that the shooting direction is always vertical to the bridge floor.
In specific implementation, the training method of the disease recognition neural network comprises the following steps:
acquiring an apparent bridge disease image and a corresponding recognition result;
taking the bridge apparent disease images and corresponding recognition results in a preset proportion as a training set, and taking the rest bridge apparent disease images and corresponding recognition results as a test set;
inputting the training set into a disease recognition neural network (convolutional neural network) to be trained for training until the recognition accuracy is greater than or equal to the preset accuracy after the test set is used for testing;
and storing the trained disease recognition neural network.
In the invention, the training of the disease recognition neural network is completed by taking the calibrated and classified bridge apparent disease images and the recognition results thereof as a training set and a test set. The method and the device finish the identification of the diseases in the image through the neural network, have high efficiency, and can continuously update the neural network in the identification process, thereby improving the identification accuracy.
As shown in fig. 3(a) and 3(b), in specific implementation, the calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface includes:
calibrating the target detection surface image by a checkerboard method, acquiring the focal length and distortion parameters of the image acquisition device, and correcting the target detection surface image by using the distortion parameters;
preprocessing the corrected image;
acquiring a disease image by using the position of the disease in the target detection surface image and carrying out binarization processing;
acquiring edge information of the disease image after binarization processing by using an edge detection algorithm, and performing morphological corrosion expansion and connection on the edge to acquire a complete disease edge;
the target detection is to find out where the disease is, and the binarization processing and the edge detection are to divide the found disease from the image.
Calculating the image size of the disease by using the disease edge;
and calculating the actual size of the disease by using the image size of the disease and the distance between the unmanned aerial vehicle and the target detection surface, and taking the actual size of the disease as the size parameter of the disease.
Because the distortion degree of each lens in the production and assembly processes is different, the distortion of the lens can be corrected through camera calibration to generate a corrected image.
As shown in fig. 4(a) and (b) and fig. 5, in the present invention, taking a defect as an example of a crack, the calculated size parameters include the length and width of the crack, wherein:
the crack length is calculated by connecting a first point of a crack end point with a last point of the crack by using a curve fitting method to obtain a line segment AB, solving the vertical distance of the line segment from each point on the crack, and selecting the line segment representing the maximum vertical distance as PX, wherein the difference of the slopes of the connecting lines of the two end points of the line segment is the maximum, so that the APX and the PXB are considered to belong to different straight lines. And regarding APX and PXB as new cracks, and circularly executing the steps until the maximum vertical distance is smaller than a set distance threshold value T. Finally, a series of line segments AP are obtainedX1,PX1PX2,……,PXnB. The distances of these line segments are added up to obtain the length of the crack.
The width of the crack is calculated as follows:
and scanning the disease image, and scanning the disease image from the first column to the nth column from top to bottom until a point with a pixel value of 1 is scanned and recorded as an upper edge coordinate point (x1, y 1).
Continuing to scan the nth column from yn until scanning to a point with a pixel value of 1 again as a lower edge coordinate point (x2, y2), recording a vertical coordinate difference value y1-y 2-1I of the point as an initial value of the crack width b, wherein the coordinate point is an edge center coordinate and the actual crack width is a distance between the bottom of the upper edge and the upper part of the lower edge;
and scanning the left and right five columns of the nth column, respectively recording the lower edge points of the n column as (x2-i, y2-i) and (x2+ i, y2+ i), wherein i ranges from 1 to 5, respectively calculating the distance from the five lower edge points adjacent to the left and right to the edge point on the nth column through a distance formula between the two points, comparing the distance with a vertical coordinate difference value, and taking the minimum value as an actual crack width value at the point.
In specific implementation, the preprocessing of the corrected image includes image enhancement, motion blur removal, and uneven illumination elimination.
This is to remove the interference in the image.
Because the size in the image does not represent the size in reality, consequently still need convert, when the distance of unmanned aerial vehicle and target detection face is L, has according to the lens imaging principle:
in the formula: l' is the image distance; f is the focal length of the lens of the image acquisition device, namely the actual physical width of the crack; assuming that A is the target actual size, there are:
substituting to obtain:
the imaging dimension a' is:
wherein the dimension A' is the number of pixels imaged; d is the image sensor long edge physics (the image sensor is CCD, CCD is a photosensitive chip, D is the length of the chip, D is the number of pixels of the image sensor long edge, and the pixel resolution is:
j denotes an actual physical size represented by a unit pixel, which is a conversion coefficient of the actual physical size and the number of pixels. And processing the digital image to obtain the number of pixels (image size) occupied by the detected target in the whole image, and calculating the actual physical size of the disease (crack).
As shown in fig. 6, in specific implementation, the disease identification neural network is a target detection network using feature map fusion, image features are constructed by fusing feature maps of different convolutional layers, the size of a deeper feature map is consistent with that of a feature map of a previous layer by a deconvolution method, then addition operation is performed to perform feature fusion to obtain a new feature map, and the new feature map is fused with the feature map of the previous layer again until all feature maps are classified.
Finally, it is noted that the above-mentioned embodiments illustrate rather than limit the invention, and that, while the invention has been described with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. The method for detecting the apparent diseases of the unmanned aerial vehicle bridge based on the fusion of laser and machine vision is characterized by comprising the following steps of:
an unmanned aerial vehicle with a laser ranging device, a positioning device and an image acquisition device acquires an image of a target detection surface, the position of the target detection surface and the distance between the unmanned aerial vehicle and the target detection surface;
inputting the target detection surface image into a disease recognition neural network to recognize the disease in the target detection surface image and the position of the disease in the target detection surface image;
calculating the size parameter of the disease based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface;
and generating apparent bridge disease detection information.
2. The unmanned aerial vehicle bridge apparent disease detection method based on the fusion of laser and machine vision as claimed in claim 1, wherein the training method of the disease recognition neural network comprises:
acquiring an apparent bridge disease image and a corresponding recognition result;
taking the bridge apparent disease images and corresponding recognition results in a preset proportion as a training set, and taking the rest bridge apparent disease images and corresponding recognition results as a test set;
inputting the training set into a disease recognition neural network to be trained for training until the recognition accuracy is greater than or equal to the preset accuracy after the test set is used for testing;
and storing the trained disease recognition neural network.
3. The method for detecting the apparent diseases of the unmanned aerial vehicle bridge based on the fusion of the laser and the machine vision as claimed in claim 1, wherein the step of calculating the size parameters of the diseases based on the target detection surface image and the distance between the unmanned aerial vehicle and the target detection surface comprises the following steps:
calibrating the target detection surface image by a checkerboard method, acquiring distortion parameters of an image acquisition device, and correcting the target detection surface image by using the distortion parameters;
preprocessing the corrected image;
acquiring a disease image by using the position of the disease in the target detection surface image and carrying out binarization processing;
acquiring edge information of the disease image after binarization processing by using an edge detection algorithm, and performing morphological corrosion expansion and connection on the edge to acquire a complete disease edge;
calculating the image size of the disease by using the disease edge;
and calculating the actual size of the disease by using the image size of the disease and the distance between the unmanned aerial vehicle and the target detection surface, and taking the actual size of the disease as the size parameter of the disease.
4. The method for detecting the apparent diseases of the unmanned aerial vehicle bridge based on the fusion of the laser and the machine vision as claimed in claim 3, wherein the preprocessing in the preprocessing of the corrected image comprises image enhancement, motion blur removal and uneven illumination elimination.
5. The method for detecting the apparent diseases of the unmanned aerial vehicle bridge based on the fusion of the laser and the machine vision as claimed in claim 1, wherein the disease recognition neural network is a target detection network using feature map fusion, image features are constructed by fusing feature maps of different convolution layers, the size of a feature map of a deeper layer is kept consistent with that of a feature map of a previous layer by a deconvolution method, then, addition operation is carried out to carry out feature fusion to obtain a new feature map, and the new feature map is fused with the feature map of the previous layer again until all feature maps are classified.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010032544.1A CN111260615B (en) | 2020-01-13 | 2020-01-13 | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010032544.1A CN111260615B (en) | 2020-01-13 | 2020-01-13 | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111260615A true CN111260615A (en) | 2020-06-09 |
CN111260615B CN111260615B (en) | 2022-11-15 |
Family
ID=70945231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010032544.1A Active CN111260615B (en) | 2020-01-13 | 2020-01-13 | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111260615B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111707196A (en) * | 2020-05-13 | 2020-09-25 | 苏州天炯信息科技有限公司 | Bridge defect size measuring device and method based on unmanned aerial vehicle |
CN112215805A (en) * | 2020-09-22 | 2021-01-12 | 广州誉宸信息科技有限公司 | Unmanned aerial vehicle inspection method and system for highway bridge slope maintenance |
CN112903710A (en) * | 2021-01-22 | 2021-06-04 | 山东高速工程检测有限公司 | Method, system and device for monitoring apparent bridge diseases |
CN113190032A (en) * | 2021-05-10 | 2021-07-30 | 重庆交通大学 | Unmanned aerial vehicle perception planning system and method applied to multiple scenes and unmanned aerial vehicle |
CN114202660A (en) * | 2022-02-21 | 2022-03-18 | 广东建科交通工程质量检测中心有限公司 | Remote distributed control method and system based on edge cloud bridge detection |
CN114486908A (en) * | 2021-12-31 | 2022-05-13 | 长江航道工程局有限责任公司 | Pier disease identification and detection unmanned aerial vehicle and detection method |
CN115032206A (en) * | 2022-06-15 | 2022-09-09 | 招商局重庆交通科研设计院有限公司 | Intelligent detection method for bridge robot |
CN115546170A (en) * | 2022-10-17 | 2022-12-30 | 风脉能源(武汉)股份有限公司 | Fan blade defect positioning method and system based on laser ranging |
CN116295020A (en) * | 2023-05-22 | 2023-06-23 | 山东高速工程检测有限公司 | Bridge disease positioning method and device |
CN117011688A (en) * | 2023-07-11 | 2023-11-07 | 广州大学 | Method, system and storage medium for identifying diseases of underwater structure |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105096317A (en) * | 2015-07-03 | 2015-11-25 | 吴晓军 | Fully automatic calibration method for high performance camera under complicated background |
CN204854730U (en) * | 2015-06-23 | 2015-12-09 | 赵国梁 | Unmanned aerial survey system of multi -angle |
CN106352856A (en) * | 2016-07-29 | 2017-01-25 | 北京观著信息技术有限公司 | Single-camera rotational oblique photography method and oblique photography device |
CN107917695A (en) * | 2017-11-16 | 2018-04-17 | 南京工业大学 | A kind of inclined building monitoring method based on image recognition technology |
CN108460403A (en) * | 2018-01-23 | 2018-08-28 | 上海交通大学 | The object detection method and system of multi-scale feature fusion in a kind of image |
CN108871296A (en) * | 2018-06-28 | 2018-11-23 | 河南省中纬测绘规划信息工程有限公司 | A kind of multi-angle aerial survey of unmanned aerial vehicle camera support |
CN110070008A (en) * | 2019-04-04 | 2019-07-30 | 中设设计集团股份有限公司 | Bridge disease identification method adopting unmanned aerial vehicle image |
CN110222701A (en) * | 2019-06-11 | 2019-09-10 | 北京新桥技术发展有限公司 | A kind of bridge defect automatic identifying method |
-
2020
- 2020-01-13 CN CN202010032544.1A patent/CN111260615B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204854730U (en) * | 2015-06-23 | 2015-12-09 | 赵国梁 | Unmanned aerial survey system of multi -angle |
CN105096317A (en) * | 2015-07-03 | 2015-11-25 | 吴晓军 | Fully automatic calibration method for high performance camera under complicated background |
CN106352856A (en) * | 2016-07-29 | 2017-01-25 | 北京观著信息技术有限公司 | Single-camera rotational oblique photography method and oblique photography device |
CN107917695A (en) * | 2017-11-16 | 2018-04-17 | 南京工业大学 | A kind of inclined building monitoring method based on image recognition technology |
CN108460403A (en) * | 2018-01-23 | 2018-08-28 | 上海交通大学 | The object detection method and system of multi-scale feature fusion in a kind of image |
CN108871296A (en) * | 2018-06-28 | 2018-11-23 | 河南省中纬测绘规划信息工程有限公司 | A kind of multi-angle aerial survey of unmanned aerial vehicle camera support |
CN110070008A (en) * | 2019-04-04 | 2019-07-30 | 中设设计集团股份有限公司 | Bridge disease identification method adopting unmanned aerial vehicle image |
CN110222701A (en) * | 2019-06-11 | 2019-09-10 | 北京新桥技术发展有限公司 | A kind of bridge defect automatic identifying method |
Non-Patent Citations (3)
Title |
---|
WEIDONG WU 等: "Coupling Deep Learning and UAV for Infrastructure Condition Assessment Automation", 《2018 IEEE INTERNATIONAL SMART CITIES CONFERENCE (ISC2)》 * |
范帅 等: "基于机器视觉的轴承内外圈尺寸检测及分类", 《自动化仪表》 * |
雷闻等: "无人机倾斜摄影在地质灾害调查中的应用", 《区域治理》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111707196A (en) * | 2020-05-13 | 2020-09-25 | 苏州天炯信息科技有限公司 | Bridge defect size measuring device and method based on unmanned aerial vehicle |
CN112215805A (en) * | 2020-09-22 | 2021-01-12 | 广州誉宸信息科技有限公司 | Unmanned aerial vehicle inspection method and system for highway bridge slope maintenance |
CN112903710A (en) * | 2021-01-22 | 2021-06-04 | 山东高速工程检测有限公司 | Method, system and device for monitoring apparent bridge diseases |
CN113190032A (en) * | 2021-05-10 | 2021-07-30 | 重庆交通大学 | Unmanned aerial vehicle perception planning system and method applied to multiple scenes and unmanned aerial vehicle |
CN114486908A (en) * | 2021-12-31 | 2022-05-13 | 长江航道工程局有限责任公司 | Pier disease identification and detection unmanned aerial vehicle and detection method |
CN114202660B (en) * | 2022-02-21 | 2022-12-30 | 广东建科交通工程质量检测中心有限公司 | Remote distributed control method and system based on edge cloud bridge detection |
CN114202660A (en) * | 2022-02-21 | 2022-03-18 | 广东建科交通工程质量检测中心有限公司 | Remote distributed control method and system based on edge cloud bridge detection |
CN115032206A (en) * | 2022-06-15 | 2022-09-09 | 招商局重庆交通科研设计院有限公司 | Intelligent detection method for bridge robot |
CN115546170A (en) * | 2022-10-17 | 2022-12-30 | 风脉能源(武汉)股份有限公司 | Fan blade defect positioning method and system based on laser ranging |
CN115546170B (en) * | 2022-10-17 | 2023-04-21 | 风脉能源(武汉)股份有限公司 | Fan blade defect positioning method and system based on laser ranging |
CN116295020A (en) * | 2023-05-22 | 2023-06-23 | 山东高速工程检测有限公司 | Bridge disease positioning method and device |
CN116295020B (en) * | 2023-05-22 | 2023-08-08 | 山东高速工程检测有限公司 | Bridge disease positioning method and device |
CN117011688A (en) * | 2023-07-11 | 2023-11-07 | 广州大学 | Method, system and storage medium for identifying diseases of underwater structure |
CN117011688B (en) * | 2023-07-11 | 2024-03-08 | 广州大学 | Method, system and storage medium for identifying diseases of underwater structure |
Also Published As
Publication number | Publication date |
---|---|
CN111260615B (en) | 2022-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111260615B (en) | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge | |
CN110148169B (en) | Vehicle target three-dimensional information acquisition method based on PTZ (pan/tilt/zoom) pan-tilt camera | |
US10931871B2 (en) | Pipeline detection method and apparatus, and storage medium | |
WO2018153304A1 (en) | Map road mark and road quality collection apparatus and method based on adas system | |
CN108692719B (en) | Object detection device | |
CN109373921B (en) | Tunnel monitoring method and device | |
US20160133008A1 (en) | Crack data collection method and crack data collection program | |
CN111508027B (en) | Method and device for calibrating external parameters of camera | |
CN111369495B (en) | Panoramic image change detection method based on video | |
CN104574393A (en) | Three-dimensional pavement crack image generation system and method | |
CN110533649B (en) | Unmanned aerial vehicle general structure crack identification and detection device and method | |
CN111354047B (en) | Computer vision-based camera module positioning method and system | |
CN116597013B (en) | Satellite image geometric calibration method based on different longitude and latitude areas | |
CN113554667B (en) | Three-dimensional displacement detection method and device based on image recognition | |
KR101255461B1 (en) | Position Measuring Method for street facility | |
CN111243003A (en) | Vehicle-mounted binocular camera and method and device for detecting road height limiting rod | |
CN114719873B (en) | Low-cost fine map automatic generation method and device and readable medium | |
CN114037953A (en) | Slope safety monitoring method and device, computer equipment and storage medium | |
CN107941241B (en) | Resolution board for aerial photogrammetry quality evaluation and use method thereof | |
CN113808103A (en) | Automatic road surface depression detection method and device based on image processing and storage medium | |
CN112184903A (en) | Method, device, equipment and medium for detecting high-voltage line tree obstacle risk points | |
CN109084721B (en) | Method and apparatus for determining a topographical parameter of a target structure in a semiconductor device | |
CN115984360A (en) | Method and system for calculating length of dry beach based on image processing | |
Ziqiang et al. | Research of the algorithm calculating the length of bridge crack based on stereo vision | |
CN112991372B (en) | 2D-3D camera external parameter calibration method based on polygon matching |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |