CN109931889B - Deviation detection system and method based on image recognition technology - Google Patents
Deviation detection system and method based on image recognition technology Download PDFInfo
- Publication number
- CN109931889B CN109931889B CN201910236213.7A CN201910236213A CN109931889B CN 109931889 B CN109931889 B CN 109931889B CN 201910236213 A CN201910236213 A CN 201910236213A CN 109931889 B CN109931889 B CN 109931889B
- Authority
- CN
- China
- Prior art keywords
- line
- picture
- dimensional model
- deviation
- aerial vehicle
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 8
- 239000000872 buffer Substances 0.000 description 6
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- WYTGDNHDOZPMIW-RCBQFDQVSA-N alstonine Natural products C1=CC2=C3C=CC=CC3=NC2=C2N1C[C@H]1[C@H](C)OC=C(C(=O)OC)[C@H]1C2 WYTGDNHDOZPMIW-RCBQFDQVSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a deviation detection system and method based on an image recognition technology, and relates to the technical field of maintenance and detection of bridges or railway lines. The system comprises: the unmanned aerial vehicle comprises a camera device for shooting a line picture; the image processing module unit is used for identifying the line picture and constructing a three-dimensional model; and the detection unit is used for comparing the three-dimensional models in different time periods and detecting the deviation of the central line of the line. The method comprises the following steps: shooting a line picture by adopting an unmanned aerial vehicle with a camera device; identifying a line picture and constructing a three-dimensional model; and comparing the three-dimensional models in different time periods, and detecting the deviation of the central line of the line. The invention adopts the unmanned aerial vehicle to shoot the picture for detection, does not need to occupy the line, has high detection efficiency, low cost and high safety, and achieves the purpose of detecting the line deviation by establishing the three-dimensional model through the picture and comparing the three-dimensional models in different periods, and has convenient detection and high detection precision.
Description
Technical Field
The invention relates to the technical field of maintenance and detection of bridges or railway lines, in particular to a deviation detection system and method based on an image recognition technology.
Background
For bridge or railway line inspection, maintenance and repair work needs to be carried out regularly, and deviation detection needs to be carried out on the line in the process. At present, the deviation between a railway line and a bridge span center line is mainly measured manually, and the railway line inspection instrument can only inspect the flatness and width deviation of the line. The deviation inspection of the line center line generally needs to measure the center lines of the beam body and the track, and due to the fact that personnel and equipment needed by measurement are more, the railway line is longer, the measurement period needed each time is also longer, and detection can be carried out only once in a few years.
In practice, under the action of train serpentine wave transverse force and temperature, particularly at a railway bending section, the deviation of an iron beam body and a track line has great influence on the stress of a pier column and a support. In view of this, the railway line deviation is specified in the "railway bridge and tunnel building repair rules" as follows: the steel beam is not larger than 50mm, and neither the steel beam nor the masonry beam is larger than 50 mm. If the deviation limit value is exceeded, the calculation should be carried out.
The line deviation inspection needs to be carried out on the line, so that skylight points need to be applied for detection construction, the operation time of the rail line inspection is limited, the safety risk of operators is increased, the bridge rail line deviation inspection is low in efficiency, high in detection cost, poor in detection precision and safe in risk, and the like.
Disclosure of Invention
The present invention is directed to overcome the above-mentioned drawbacks of the background art, and provides a system and a method for detecting a deviation based on an image recognition technology. The invention adopts the unmanned aerial vehicle to shoot the picture for detection, does not need to occupy the line, has high detection efficiency, low cost and high safety, and achieves the purpose of detecting the line deviation by establishing the three-dimensional model through the picture and comparing the three-dimensional models in different periods, and has convenient detection and high detection precision.
The invention provides a deviation detection system based on an image recognition technology, which is used for detecting the deviation of a bridge or railway line and comprises the following components:
the unmanned aerial vehicle comprises a camera device for shooting a line picture;
the image processing module unit is used for identifying the circuit picture and constructing a three-dimensional model;
and the detection unit is used for comparing the three-dimensional models in different time periods and detecting the deviation of the central line of the line.
On the basis of the technical scheme, the line picture comprises a line and a calibration reference object within a line preset range;
correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range;
the detection unit is also used for simulating the central line of the three-dimensional model, correspondingly superposing the calibration reference objects of the three-dimensional model in different time periods and measuring the deviation of the central line.
On the basis of the technical scheme, the image processing module unit is also used for processing the picture by combining with a flight state signal of the unmanned aerial vehicle;
the flight state signal comprises a flight space coordinate, an inclination angle and a vertical deflection angle.
On the basis of the technical scheme, unmanned aerial vehicle loads have GPS and gyroscope, and GPS is used for fixing a position unmanned aerial vehicle's flight space coordinate, and the gyroscope is used for fixing a position inclination and vertical deflection angle.
On the basis of the technical scheme, the line pictures at least comprise three pictures with different angles;
the image processing module unit is used for determining the coordinates of any point on each picture according to the flight state signal when each picture is shot and determining the space coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures.
The invention also provides a deviation detection method based on the image recognition technology, which is used for detecting the deviation of the line of the bridge or the railway and comprises the following steps:
shooting a line picture by adopting an unmanned aerial vehicle with a camera device;
identifying a line picture and constructing a three-dimensional model;
and comparing the three-dimensional models in different time periods, and detecting the deviation of the central line of the line.
On the basis of the technical scheme, the line is divided into a plurality of sections, and at least three pictures are taken when one section of line is taken; three pictures are respectively shot from the left side, the upper air and the right side of the section of line.
On the basis of the technical scheme, when the line picture is processed, the flight state signal of the unmanned aerial vehicle is combined for processing;
the flight state signal comprises a flight space coordinate, an inclination angle and a vertical deflection angle.
On the basis of the technical scheme, the process of processing by combining the flight state signal of the unmanned aerial vehicle comprises the following steps:
and determining the coordinates of any point on each picture according to the flight state signals when each picture is shot, and determining the space coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures.
On the basis of the technical scheme, the line picture comprises a line and a calibration reference object within a line preset range;
correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range;
when three-dimensional models in different time periods are compared, the central line of the three-dimensional model is simulated, calibration reference objects of the three-dimensional model are correspondingly overlapped, and deviation of the central line is measured.
Compared with the prior art, the invention has the following advantages:
(1) according to the invention, the unmanned aerial vehicle shoots the line picture without occupying the line, so that the problems of excessive dependence on weather and detection of specific time periods such as requiring application of skylight points and the like are solved, the detection efficiency is improved, meanwhile, the unmanned aerial vehicle automatically shoots the picture without manual inspection, the detection cost is greatly reduced, the unmanned aerial vehicle flies above the line without influencing the line, manual maintenance on the line is not required, and the safety is high. Unmanned aerial vehicle can freely adjust shooting angle as required, solves the digital camera because the reason in aspects such as shooting angle leads to unable contrast and aassessment between the picture to can't reach the problem of realizing the three-dimensional reconstruction of figure.
Further, the line picture is processed, a three-dimensional model is constructed, the three-dimensional models in different time periods are compared, and line deviation detection can be completed. The three-dimensional model is adopted, the line deviations of two different time periods can be compared, the line deviation condition can be detected at any time, the deviation is measured through the three-dimensional model comparison, the precision is higher than that of manual measurement, and the detection is convenient.
(2) The invention provides a picture processing mode, which is characterized in that a line is divided into a plurality of sections, when one section of line is shot, at least three pictures are shot, and the three pictures are respectively shot from three angles of the left side, the upper space and the right side of the section of line. And then, processing the three pictures by combining with a flight state signal of the unmanned aerial vehicle, obtaining the coordinate of the same point in the three pictures according to the flight state signal, determining the space coordinate of the point in the three-dimensional model according to the three coordinates of the point, and constructing the three-dimensional model by generating dense point cloud. The picture processing mode provided by the invention can accurately construct a three-dimensional model with high reality sense, and is vivid and vivid enough for the earth surface to realize the actual line.
Further, the line picture shot by the unmanned aerial vehicle comprises the line and the calibration reference object within the line preset range, so that the formed three-dimensional model also comprises the line and the calibration reference object within the line preset range. When the two three-dimensional models are compared, the central line of the three-dimensional models is simulated, then the calibration reference objects are overlapped, and the deviation between the central lines is measured, so that the actual line deviation can be obtained. The image processing method provided by the invention can realize automation of the whole deviation measurement and has high measurement precision.
Drawings
Fig. 1 is a schematic structural diagram of a deviation detection system based on an image recognition technology according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a deviation detection system based on an image recognition technology according to another embodiment of the present invention.
Fig. 3 is a flow chart of the deviation detection method based on the image recognition technology of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments.
Referring to fig. 1, an embodiment of the present invention provides a deviation detecting system based on an image recognition technology, for detecting a deviation of a route of a bridge or a railway, including: the unmanned aerial vehicle 1, image processing module unit 21 and detection unit 22.
Wherein, unmanned aerial vehicle 1 includes camera device 11 for shoot the line picture. During operation, the unmanned aerial vehicle 1 flies above the line.
The image processing module unit 21 is used to recognize the line picture and construct a three-dimensional model.
The detection unit 22 is used for comparing the three-dimensional models in different time periods and detecting the deviation of the central line of the line.
Further, in order to facilitate comparison and detection, the line picture comprises a line and a calibration reference object within a preset range of the line; correspondingly, the three-dimensional model also comprises the line and a calibration reference object within the preset range of the line. The compiling reference object can be a house, a mountain, a fixed sign or other fixed object arranged. The preset range can be within 1-15m beside the line.
The detection unit 22 is further configured to simulate a center line of a line of the three-dimensional model, correspondingly superimpose calibration references of the three-dimensional model at different time periods, and measure a deviation of the center line. The image processing mode adopted by the detection unit 22 enables the whole deviation measurement to be automated, and the three-dimensional model realistically simulates the line and the calibration reference object within the preset range of the line, so that the actual deviation can be obtained by directly measuring the deviation of the central line, and the measurement precision is high.
The image processing module unit 21 is further configured to process the image in combination with the flight status signal of the unmanned aerial vehicle 1, where the processing of the image includes operations of stitching, stretching, and cutting. The flight state signal includes flight space coordinates, an inclination angle, and a vertical deflection angle. Specifically, unmanned aerial vehicle 1 loads has GPS and gyroscope, and GPS is used for fixing a position unmanned aerial vehicle 1's flight space coordinate, and the gyroscope is used for location inclination and vertical deflection angle. Wherein the angle of inclination is to the horizontal and the angle of vertical deflection is to the vertical. The GPS can set an unmanned automatic shooting route, or the unmanned aerial vehicle 1 is manually controlled to carry out supplementary shooting on a special disease part of the route, and three-dimensional automatic reconstruction of the route is started on the basis of the image. The gyroscope can be used for acquiring high-precision camera positioning information, orientation information and posture information of the camera at the moment of photographing.
Further optimizing, the line pictures at least comprise three pictures with different angles; the image processing module unit 21 is configured to determine coordinates of any point on each picture according to the flight status signal when each picture is taken, and determine spatial coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures. Wherein, each picture is recorded with the flight status signal of the corresponding unmanned aerial vehicle 1 when shooting. So that the three-dimensional model has dimensions consistent with the actual wiring.
Referring to fig. 2, in practical application, the image processing module 21 and the detection unit 22 are disposed in the server 2, and the server 2 is located on the ground, connected to the display screen 3, and displayed to the user through the display screen 3. Specifically, the display screen 3 may be a computer monitor, a mobile phone or other display devices. The unmanned aerial vehicle 1 sends the line picture and the flight signal state to the server 2 through the network, or derives data from the unmanned aerial vehicle 1 and imports the data into the server 2. The import server 2 transfers data to be processed from the hard disk to a memory allocated in advance, and processes only the data in the memory. The stored data can be imported into the server 2 through the USB port afterwards, and high-precision difference error correction of the coordinate information and writing of the information into the corresponding position of the picture file are carried out.
Wherein, unmanned aerial vehicle 1 can real-time recording own flight state, and the high definition photo time of shooing is synchronous with unmanned aerial vehicle 1's flight state time, confirms unmanned aerial vehicle 1 current flight signal state according to the shooting time of shooing the picture. Through adjusting unmanned aerial vehicle 1 camera shooting parameter and orientation, adjust the luminance and the angle of illumination light source repeatedly in order to obtain the best image in measurement area.
The camera device 11 may be a camera, a video recorder, a video camera, or the like, and is mounted on the unmanned aerial vehicle 1 through a cradle head. The flash lamp hot boot trigger signal when camera device 11 shoots obtains instantaneous information such as location coordinate, azimuth angle, angle of inclination, roll angle, height above sea level height of shooing, has recorded the flight state of unmanned aerial vehicle 1 when shooing on every picture promptly, can contain characteristic information such as circuit space coordinate and camera coordinate, focus, azimuth angle of shooting image data in the picture, and data transfer is to server 2 and is stored simultaneously, shows on display screen 3.
The display screen 3 can display by adopting an off-screen bitmap technology, the off-screen bitmap technology displays images through double buffers, one buffer is used for preparing contents to be displayed, the other buffer is used for displaying currently, the data preparation process is hidden, and the phenomenon of screen flicker caused by visibility of the data updating process is avoided. And creating a display buffer according to the current window, preparing all contents to be displayed in the buffer, and then transferring the prepared data to a screen buffer by using a bit block transmission method of Windows to display on a screen.
In addition, the detection system may further include a ground control and signal receiving device 4 for acquiring a flight state signal of the unmanned aerial vehicle 1 in real time and controlling a flight state of the unmanned aerial vehicle 1. And the ground control and signal receiving device 4 and the unmanned aerial vehicle 1 adopt wireless communication to carry out data transmission and flight control.
Referring to fig. 3, an embodiment of the present invention provides a deviation detection method for performing an image recognition technology by using the detection system, which is used for detecting a deviation of a bridge or a railway line, and includes the following steps:
s1, shooting a line picture by adopting the unmanned aerial vehicle 1 with the camera device 11;
s2, identifying the line picture and constructing a three-dimensional model;
and S3, comparing the three-dimensional models in different time periods, and detecting the deviation of the central line of the line.
In step S1, the line is divided into multiple sections in advance, and when a section of line is photographed, at least three pictures are photographed; three pictures are respectively shot from the left side, the upper air and the right side of the section of line. When the deviation of the railway track is detected, the line is divided into each railway, and each railway is controlled within the range of 32 m. The invention takes three pictures by an aerial triangulation method, recovers the position and the posture of a camera when the image is taken, and completes the conversion from a free coordinate system to an actual measurement coordinate system by utilizing the data information derived by the unmanned aerial vehicle 1 in the recovery process.
In step S2, when identifying the route picture, processing is performed in combination with the flight status signal of the unmanned aerial vehicle 1; the flight state signal includes flight space coordinates, an inclination angle, and a vertical deflection angle. Specifically, the process of processing in combination with the flight status signal of the unmanned aerial vehicle 1 includes: and determining the coordinates of any point on each picture according to the flight state signals when each picture is shot, and determining the space coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures. By analogy, a large amount of point clouds approximating the surface of the object are generated through the position and the posture of the recovered camera and a dense matching method. Point clouds are generated from the images, with a large number of points sufficient to realistically represent geometric details everywhere on the earth's surface. For the generated dense point cloud, a three-dimensional model with high reality is finally generated by a method of network construction and mapping.
The circuit picture comprises a circuit and a calibration reference object in a circuit preset range; correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range; in step S3, when comparing the three-dimensional models in different time periods, a center line of a line of the three-dimensional model is simulated, calibration references of the three-dimensional model are correspondingly overlapped, and a deviation of the center line is measured.
In addition, the constructed three-dimensional model has size information, and analysis of bridge inspection data, such as the width, length, area and the like of a detection pit, can be completed by constructing the three-dimensional model based on the method.
Various modifications and variations of the embodiments of the present invention may be made by those skilled in the art, and they are also within the scope of the present invention, provided they are within the scope of the claims of the present invention and their equivalents.
What is not described in detail in the specification is prior art that is well known to those skilled in the art.
Claims (7)
1. A deviation detection system based on image recognition technology is used for detecting the deviation of a bridge or a railway line, and is characterized by comprising:
the unmanned aerial vehicle comprises a camera device for shooting a line picture;
the image processing module unit is used for identifying the circuit picture and constructing a three-dimensional model;
the detection unit is used for comparing the three-dimensional models in different time periods and detecting the deviation of the central line of the line;
the line picture is a picture which divides a line into a plurality of sections and shoots one section of line, and the line picture at least comprises three pictures with different angles; three pictures are respectively shot from the left side, the upper space and the right side of the section of the line;
the image processing module unit is also used for processing the picture by combining with a flight state signal of the unmanned aerial vehicle;
the image processing module unit is used for determining the coordinates of any point on each picture according to the flight state signals when each picture is shot, determining the space coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures, and constructing the three-dimensional model by generating dense point clouds.
2. The system of claim 1, wherein: the circuit picture comprises a circuit and a calibration reference object in a circuit preset range;
correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range;
the detection unit is also used for simulating the central line of the three-dimensional model, correspondingly superposing the calibration reference objects of the three-dimensional model in different time periods and measuring the deviation of the central line.
3. The system of claim 1, wherein:
the flight state signal comprises a flight space coordinate, an inclination angle and a vertical deflection angle.
4. The system of claim 3, wherein: unmanned aerial vehicle loads have GPS and gyroscope, and GPS is used for fixing a position unmanned aerial vehicle's flight space coordinate, and the gyroscope is used for fixing a position inclination and vertical deflection angle.
5. A deviation detection method based on an image recognition technology is used for detecting the deviation of a bridge or railway line, and is characterized by comprising the following steps:
shooting a line picture by adopting an unmanned aerial vehicle with a camera device;
identifying a line picture and constructing a three-dimensional model;
comparing the three-dimensional models in different time periods, and detecting the deviation of the central line of the line;
the circuit picture comprises a circuit and a calibration reference object in a circuit preset range;
correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range;
when three-dimensional models in different time periods are compared, simulating a central line of a line of the three-dimensional models, correspondingly overlapping calibration reference objects of the three-dimensional models, and measuring deviation of the central line;
dividing a line into a plurality of sections, and shooting at least three pictures when shooting one section of the line; three pictures are respectively shot from the left side, the upper air and the right side of the section of line;
when the line picture is processed, the flight state signal of the unmanned aerial vehicle is combined for processing;
the process of processing in combination with the flight status signal of the drone includes:
and determining the coordinates of any point on each picture according to the flight state signals when each picture is shot, determining the space coordinates of the point in the three-dimensional model according to the coordinates of the point in the three pictures, and constructing the three-dimensional model by generating dense point cloud.
6. The method of claim 5, wherein: the flight state signal comprises a flight space coordinate, an inclination angle and a vertical deflection angle.
7. The method of claim 5, wherein: the circuit picture comprises a circuit and a calibration reference object in a circuit preset range;
correspondingly, the three-dimensional model also comprises a line and a calibration reference object in a line preset range;
when three-dimensional models in different time periods are compared, the central line of the three-dimensional model is simulated, calibration reference objects of the three-dimensional model are correspondingly overlapped, and deviation of the central line is measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236213.7A CN109931889B (en) | 2019-03-27 | 2019-03-27 | Deviation detection system and method based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236213.7A CN109931889B (en) | 2019-03-27 | 2019-03-27 | Deviation detection system and method based on image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109931889A CN109931889A (en) | 2019-06-25 |
| CN109931889B true CN109931889B (en) | 2021-04-06 |
Family
ID=66988475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910236213.7A Active CN109931889B (en) | 2019-03-27 | 2019-03-27 | Deviation detection system and method based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109931889B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112097693A (en) * | 2020-08-19 | 2020-12-18 | 北京机科国创轻量化科学研究院有限公司 | Straightness measuring system and method based on unmanned aerial vehicle |
| CN115908572B (en) * | 2023-02-15 | 2023-05-12 | 南京慧然科技有限公司 | Visual detection method and system for eccentric measurement |
| CN116612012A (en) * | 2023-07-17 | 2023-08-18 | 南方电网数字电网研究院有限公司 | Power transmission line image splicing method, system, computer equipment and storage medium |
| CN118695224B (en) * | 2024-08-26 | 2024-11-12 | 成都纵横通达信息工程有限公司 | A bridge health monitoring system based on wireless sensing and visual fusion |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103528532B (en) * | 2013-11-01 | 2017-01-04 | 深圳市明致物联技术有限公司 | A kind of rail offset method for automatic measurement and device |
| CA2952484A1 (en) * | 2015-12-23 | 2017-06-23 | Wal-Mart Stores, Inc. | Apparatus and method for monitoring premises |
| CN108240794A (en) * | 2016-12-25 | 2018-07-03 | 天津鼎助同立科技有限公司 | The method and device of railway track displacement |
| CN107462213B (en) * | 2017-07-27 | 2020-06-09 | 国网山东省电力公司经济技术研究院 | Iron tower inclination angle automatic measurement method based on machine vision system |
| CN108318499A (en) * | 2018-01-05 | 2018-07-24 | 株洲时代电子技术有限公司 | A kind of bridge method for inspecting |
| CN109444171A (en) * | 2018-09-18 | 2019-03-08 | 山东理工大学 | Integrated Bridges Detection based on unmanned plane |
-
2019
- 2019-03-27 CN CN201910236213.7A patent/CN109931889B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109931889A (en) | 2019-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109931889B (en) | Deviation detection system and method based on image recognition technology | |
| CN112629431B (en) | Civil structure deformation monitoring method and related equipment | |
| CN115065816B (en) | Real geospatial scene real-time construction method and real-time construction device | |
| CN113137955B (en) | Unmanned aerial vehicle aerial survey virtual simulation method based on scene modeling and virtual photography | |
| CN109736894A (en) | A monitoring system, monitoring method and early warning method for surrounding rock disaster of coal mine roadway | |
| CN103226838A (en) | Real-time spatial positioning method for mobile monitoring target in geographical scene | |
| JP2019060641A (en) | Aerial marking, analysis device, and drone airborne survey system | |
| CN104081763A (en) | Image processing apparatus, image processing server, image processing method, image processing program and recording medium | |
| JP7588977B2 (en) | On-site video management system and on-site video management method | |
| CN113012292A (en) | AR remote construction monitoring method and system based on unmanned aerial vehicle aerial photography | |
| WO2016184255A1 (en) | Visual positioning device and three-dimensional mapping system and method based on same | |
| CN209181784U (en) | A video measuring device applied to automatic parking system | |
| CN115128965B (en) | Realistic trajectory simulation and view capture content recommendation method for digital twin scenes | |
| CN106767895B (en) | The system and method for solving camera elements of exterior orientation are oriented using index point | |
| CN104933223A (en) | Power transmission line channel digital surveying method | |
| CN117456108B (en) | Three-dimensional data acquisition method for line laser sensor and high-definition camera | |
| CN118980319A (en) | A wireless intelligent laser displacement sensor system and monitoring method | |
| CN116754076A (en) | Inversion method for high-heterogeneity surface temperature of urban complex three-dimensional scene | |
| JP4565348B2 (en) | Shape measuring apparatus and method | |
| CN115965743A (en) | Three-dimensional modeling system and method based on VR and oblique photography collected data | |
| CN114564049B (en) | Unmanned aerial vehicle wide area search device and method based on deep learning | |
| CN118960667B (en) | Urban rail transit engineering monitoring system and method based on digital twinning | |
| JP2005310044A (en) | Apparatus, method and program for data processing | |
| JP2025512775A (en) | Deformation measurement method, device, electronic device, and storage medium | |
| CN109631849A (en) | A kind of high gradient slope crag measurement method based on oblique photograph |
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 |