CN117233090A - Dam surface defect positioning device - Google Patents
Dam surface defect positioning device Download PDFInfo
- Publication number
- CN117233090A CN117233090A CN202311327930.3A CN202311327930A CN117233090A CN 117233090 A CN117233090 A CN 117233090A CN 202311327930 A CN202311327930 A CN 202311327930A CN 117233090 A CN117233090 A CN 117233090A
- Authority
- CN
- China
- Prior art keywords
- positioning device
- dam surface
- dam
- surface defect
- camera
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 56
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 32
- 230000010287 polarization Effects 0.000 claims abstract description 23
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 230000004807 localization Effects 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 5
- 239000000523 sample Substances 0.000 claims description 4
- 238000000034 method Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Abstract
The invention discloses a dam surface defect positioning device, which comprises a shell, and a high-definition color camera, a binocular polarization camera, a water depth sensor, an ultrasonic ranging sensor and an embedded AI platform which are integrated on the shell, wherein the high-definition color camera is used for monitoring defects at a dam surface structure seam in real time; the binocular polarization camera is provided with at least one polarization image for acquiring underwater multi-angle; the water depth sensor is used for detecting the distance z' between the positioning device and the water surface in real time; the ultrasonic ranging sensor is used for detecting the distance y' of the positioning device from the dam surface in real time; the embedded AI platform is used for implementing a multi-sensor fusion defect positioning algorithm to analyze the position and the posture of the positioning device and the horizontal movement distance x'. The invention can accurately position the surface defect position of the dam in the complex underwater environment.
Description
Technical Field
The invention relates to the technical field of underwater positioning, in particular to a dam surface defect positioning device.
Background
Daily observation is carried out by arranging monitoring facilities, so that the safety state of the dam can be reflected. However, the monitoring facilities can only monitor points, cannot cover the reservoir dam in a full-scale mode, and missing detection and blind areas exist. Therefore, it is becoming increasingly important to inspect the reservoir dam by using the dam inspection robot and to precisely locate and repair the surface defects.
The dam detection robot is difficult to accurately position the defect position in the process of underwater target detection or operation, and often after the robot completes the defect identification task, workers are difficult to find the corresponding position under water to repair and maintain. The dam surface defect accurate positioning technology is a basis for detecting the operation application of a robot, and the accuracy, timeliness and reliability of the dam surface defect accurate positioning technology all determine whether underwater detection and operation tasks can be smoothly implemented. However, due to the fact that the deep water dam environment is complex, various unknown factors exist, the noise influence of underwater sound signals is large, the accuracy of the sensor on the robot is easy to influence, and the method for positioning the sensor on the land by using a single sensor cannot be implemented in the reservoir dam environment.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a dam surface defect positioning device which can accurately position the dam surface defect position under a complex underwater environment.
The invention is realized by the following technical scheme:
a dam surface defect positioning device, the defect positioning device descending along a vertical direction of a dam surface structural joint, the dam surface defect positioning device comprising:
the high-definition color camera is used for monitoring defects at the structural joints of the surface of the dam in real time;
the binocular polarization camera is provided with at least one polarization image used for acquiring underwater multi-angle;
the water depth sensor is used for detecting the distance z' between the positioning device and the water surface in real time;
the ultrasonic ranging sensor is used for detecting the distance y' of the positioning device from the dam surface in real time;
the embedded AI platform is used for implementing a multi-sensor fusion defect positioning algorithm to analyze the position and the posture of the positioning device and the horizontal movement distance x';
the embedded AI platform, the high-definition color camera, the binocular polarization camera, the water depth sensor and the ultrasonic ranging sensor are integrated on the shell.
Furthermore, an inertial measurement unit is arranged on the embedded AI platform, and the multi-sensor fusion defect positioning algorithm analyzes the pose of the positioning device and the horizontal movement distance x' based on the detection data of the binocular polarization camera and the inertial measurement unit.
Further, the multi-sensor fusion defect localization algorithm is an ORB-SLAM3 algorithm.
Further, the high-definition color camera is installed above the vertical center line of the main body of the positioning device.
Furthermore, the binocular polarization camera consists of two groups of IMX250 area array polarization sensors, and can acquire polarized images at four angles simultaneously.
Further, at least one binocular polarized camera is symmetrically installed at both sides of the vertical center line of the positioning device body.
Further, the water depth sensor is arranged at the right lower part inside the positioning device.
Further, the ultrasonic ranging sensor is installed below the vertical center line of the positioning device main body, and the probe of the ultrasonic ranging sensor is arranged outside the shell.
Further, the dam surface defect positioning device further comprises a deepwater controllable light source, wherein the deepwater controllable light source is integrated on the shell and used for providing linearly controllable illumination underwater.
Further, the deepwater controllable light source comprises two light sources with controllable illuminance, and the two light sources are fixed on the outer side of the shell.
Compared with the prior art, the invention has the advantages that:
1. the defect positioning device can detect multiple directions and multiple angles by aiming at complex underwater environments of the dam; the VISLAM algorithm can be realized by combining visual and inertial navigation information, and the pose of the positioning device is estimated; the method can be used for fusing the depth data acquired by the water depth sensor, the distance data acquired by the ultrasonic ranging sensor from the dam surface, and the carrier posture and the transverse movement distance calculated by the VISLAM algorithm, so that the accurate positioning of the dam surface defect position is realized.
Drawings
FIG. 1 is a front view of a dam surface defect locating apparatus of the present invention;
FIG. 2 is a left side view of a dam surface defect locating apparatus of the present invention;
FIG. 3 is a schematic diagram of the operation of the dam surface defect positioning apparatus of the present invention.
1. An embedded AI platform; 2. a high definition color camera; 3. a binocular polarized camera; 4. a water depth sensor; 5. an ultrasonic ranging sensor; 6. a light source; 7. a housing.
Detailed Description
The technical scheme of the invention is further described in non-limiting detail below with reference to the preferred embodiments and the accompanying drawings. In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. refer to the azimuth or positional relationship based on the azimuth or positional relationship shown in the drawings. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
As shown in fig. 1 and 2, in an embodiment of the present invention, a dam surface defect positioning device is configured to descend along a vertical direction of a dam surface structural seam, where the dam surface defect positioning device includes an embedded AI platform 1, a high definition color camera 2, a binocular polarization camera 3, a water depth sensor 4, an ultrasonic ranging sensor 5, a deep water controllable light source, and a housing 7, and the embedded AI platform 1, the high definition color camera 2, the binocular polarization camera 3, the water depth sensor 4, the ultrasonic ranging sensor 5, and the deep water controllable light source are all integrated on the housing 7. The high-definition color camera 2 is used for monitoring defects at the dam surface structural joint in real time, the binocular polarization camera 3 is provided with at least one polarization image for acquiring underwater multi-angle, the water depth sensor 4 is used for detecting the distance z ' of the positioning device from the water surface in real time, the ultrasonic ranging sensor 5 is used for detecting the distance y ' of the positioning device from the dam surface in real time, the embedded AI platform 1 is used for implementing a multi-sensor fusion defect positioning algorithm to analyze the pose and the horizontal movement distance x ' of the positioning device, and the deep water controllable light source is used for providing linear controllable illumination underwater.
The embedded AI platform 1 is provided with an inertial measurement unit, and the multi-sensor fusion defect positioning algorithm analyzes the pose and the horizontal movement distance x' of the positioning device based on the detection data of the binocular polarization camera 3 and the inertial measurement unit. Wherein the multi-sensor fusion defect positioning algorithm is ORB-SLAM3 algorithm.
The embedded AI platform 1 is developed based on the british MLU220-SOM intelligent module, expands the AI intelligent module according to the dam surface defect positioning requirement, and comprises the following specific contents: two giga net gapes, DC 12V/3A power adapter, TF draw-in groove, mSATA draw-in groove, type-C interface, USB3.0 interface, wifi antenna, HDMI interface. The inertial measurement unit is selected from MPU9250, and the inertial measurement unit and the camera are in hardware time synchronization. The embedded AI platform 1 is laterally fixed inside the housing 7 and a heat dissipation module (not shown in the figure) is mounted above the embedded AI platform 1.
The high definition color camera 2 is mounted above the positioning device main body vertical center line X. The sub-blog intelligent high-definition drive-free camera is selected as the high-definition color camera 2, the camera pixel is 200W, the image and video transmission can reach 1920 x 1080p/30fps, and the angle of view is 80-120 degrees (depending on the resolution of the video). The high-definition color camera 2 is used for detecting the underwater environment in real time, and can track the structural seam of the surface of the dam when the positioning device is submerged.
In this embodiment, the binocular polarization camera 3 is composed of two sets of IMX250 area array polarization sensors, and can acquire polarized images at four angles at the same time. At least one binocular polarized camera 3 is symmetrically installed at both sides of the vertical center line X of the positioning apparatus body.
Preferably, the binocular polarization camera 3 selects two groups of IMX250 area array polarization sensor groups with 2448 multiplied by 2048 resolution and 500 ten thousand pixels to form a binocular stereoscopic vision system, has ultra-long exposure time, can acquire polarized images at four angles at the same time, and has 800 ten thousand resolution, can adaptively eliminate chromatic aberration, and has excellent relative illumination, good low-temperature stability and low image distortion rate. Preferably, the camera lens adopts MVL-MF0828M-8MP, the focal length is 8mm, and the F number is F2.8-F16. The polarization camera is installed on the left and right sides of the horizontal center line of the main body of the positioning device, and the camera lens is waterproof and protected by a transparent glass cover in front of the positioning device.
The water depth sensor 4 is installed at the right lower part inside the positioning device. In the embodiment, the water depth sensor 4 is ELEC-DS2-3026 with resolution of 2mm and is arranged at the lower right side inside the positioning device. The depth of the positioning device under water can be calculated in real time by detecting the water pressure of the positioning device.
The ultrasonic ranging sensor 5 is installed below the vertical center line X of the positioning device body, and the probe of the ultrasonic ranging sensor 5 is disposed outside the housing 7. In this embodiment, the ultrasonic ranging sensor 5 selects an ultrasonic range finder YZ-4, the resolution is 1mm, the ultrasonic range finder YZ-4 is installed at the lower left of the positioning device, the sensor probe is required to be installed outside the positioning device, and the distance y' of the positioning device from the dam surface can be detected in real time through the time difference between ultrasonic transmission and return.
The deepwater controllable light source comprises two light sources 6 with controllable illuminance, and the two light sources 6 are fixed on the outer side of a shell 7. In this embodiment, two deepwater light sources ZF-LL-052 are selected as the deepwater controllable light source 6, the illuminance of the deepwater light sources is linearly controllable, the deepwater controllable light source is arranged on two sides outside the positioning device, the brightness can reach 5000 lumens, the brightness can be adjusted by PWM, and the illumination supplement can be realized.
As shown in fig. 3, the specific implementation flow of the dam surface defect positioning is as follows: the method comprises the steps of taking a water inlet point of a throwing positioning device as a base point position (x, y, z), enabling the positioning device to descend along the vertical direction of a dam surface structural joint according to videos transmitted by a high-definition color camera 2 in real time, detecting defects in camera images, measuring the distance from the positioning device to the water surface, namely the distance z ' in the vertical direction, by using a water depth sensor 4, measuring the distance y ' from an optical positioning device to the dam surface where the defects are located by using an ultrasonic ranging sensor 5, analyzing the pose and the horizontal movement distance x ' of a robot by using an ORB-SLAM3 algorithm, and carrying out multi-sensor information fusion to accurately position the defects on the dam surface.
Aiming at complex underwater environments of the dam, the defect positioning device can detect in multiple directions and angles; the VISLAM algorithm can be realized by combining visual and inertial navigation information, and the pose of the positioning device is estimated; the depth data acquired by the water depth sensor 4, the distance data acquired by the ultrasonic ranging sensor 5 from the dam surface, the carrier posture and the transverse moving distance calculated by the VISLAM algorithm can be fused, so that the accurate positioning of the surface defect position of the dam is realized.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A dam surface defect positioning device which descends along a vertical direction of a structural joint of a dam surface, the dam surface defect positioning device comprising:
the high-definition color camera (2) is used for monitoring defects at structural joints of the surface of the dam in real time;
a binocular polarized camera (3), wherein the binocular polarized camera (3) is provided with at least one polarized image for acquiring underwater multi-angle;
the water depth sensor (4) is used for detecting the distance z' of the positioning device from the water surface in real time;
the ultrasonic ranging sensor (5) is used for detecting the distance y' of the positioning device from the dam surface in real time;
the embedded AI platform (1) is used for implementing a multi-sensor fusion defect positioning algorithm to analyze the position and the posture of the positioning device and the horizontal movement distance x';
the embedded AI platform comprises a shell (7), wherein the embedded AI platform (1), the high-definition color camera (2), the binocular polarization camera (3), the water depth sensor (4) and the ultrasonic ranging sensor (5) are integrated on the shell (7).
2. The dam surface defect positioning device according to claim 1, wherein an inertial measurement unit is arranged on the embedded AI platform (1), and the multi-sensor fusion defect positioning algorithm resolves a positioning device pose and a horizontal movement distance x' based on detection data of the binocular polarization camera (3) and the inertial measurement unit.
3. The dam surface defect localization apparatus of claim 1, wherein the multisensor fusion defect localization algorithm is an ORB-SLAM3 algorithm.
4. Dam surface defect localization device according to claim 1, characterized in that the high definition color camera (2) is mounted above the vertical center line (X) of the localization device body.
5. Dam surface defect localization device according to claim 1, characterized in that the binocular polarization camera (3) consists of two sets of IMX250 area array polarization sensors, which can acquire polarized images of four angles simultaneously.
6. Dam surface defect localization device according to claim 1, characterized in that at least one binocular polarized camera (3) is symmetrically mounted on both sides of the vertical centre line (X) of the localization device body.
7. Dam surface defect localization device according to claim 1, characterized in that the water depth sensor (4) is mounted in the lower right of the inside of the localization device.
8. Dam surface defect localization device according to claim 1, characterized in that the ultrasonic ranging sensor (5) is mounted below the vertical centre line (X) of the localization device body and the probe of the ultrasonic ranging sensor (5) is arranged outside the housing (7).
9. Dam surface defect localization apparatus according to claim 1, further comprising a deepwater controllable light source integrated on the housing (7) for providing linearly controllable illumination under water.
10. Dam surface defect localization device according to claim 9, characterized in that the deep water controllable light source comprises two light sources (6) with controllable illuminance, the two light sources (6) being fixed outside the housing (7).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311327930.3A CN117233090A (en) | 2023-10-13 | 2023-10-13 | Dam surface defect positioning device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311327930.3A CN117233090A (en) | 2023-10-13 | 2023-10-13 | Dam surface defect positioning device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117233090A true CN117233090A (en) | 2023-12-15 |
Family
ID=89087953
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311327930.3A Pending CN117233090A (en) | 2023-10-13 | 2023-10-13 | Dam surface defect positioning device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117233090A (en) |
-
2023
- 2023-10-13 CN CN202311327930.3A patent/CN117233090A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11726292B2 (en) | Optical system | |
CN107110953B (en) | Underwater positioning system | |
AU2013333801B2 (en) | Improvements in relation to underwater imaging for underwater surveys | |
CN104217439B (en) | Indoor visual positioning system and method | |
CN103675588B (en) | The machine vision detection method of printed component part polarity and equipment | |
CN110244314B (en) | Low-slow small target detection and identification system and method | |
CN105953771A (en) | Active theodolite system and measuring method | |
CN109141255A (en) | A kind of bow net monitoring method | |
CN104034261A (en) | Surface normal measurement device and method | |
Cvišić et al. | Recalibrating the KITTI dataset camera setup for improved odometry accuracy | |
CN112595236A (en) | Measuring device for underwater laser three-dimensional scanning and real-time distance measurement | |
CN105806319B (en) | A kind of across shaft type image measuring method for glass pipeline three-dimensional motion analysis | |
CN111208146B (en) | Tunnel cable detection system and detection method | |
CN113819881A (en) | Fire source distance and map azimuth detection method for reconnaissance and inspection robot | |
CN105303580A (en) | Identification system and method of panoramic looking-around multi-camera calibration rod | |
CN117233090A (en) | Dam surface defect positioning device | |
US10685448B2 (en) | Optical module and a method for objects' tracking under poor light conditions | |
Lu et al. | Image-based system for measuring objects on an oblique plane and its applications in 2-D localization | |
KR100913165B1 (en) | Apparatus and method for detecting a localization of mobility | |
CN109990901A (en) | The latent oil sniffing robot and latent oil detection system of for transformer detection | |
KR20080054094A (en) | Method for object recognizing and distance measuring | |
Tezerjani | High resolution visual pipe characterization system using an omnidirectional camera | |
Bosch Alay | Underwater navigation and mapping with an omnidirecional optical sensor | |
CN106303183A (en) | A kind of video camera based on flying time technology | |
WO2023108307A1 (en) | System for inspecting farming netting in aquaculture cages |
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 |