CN117197526A - Auxiliary reconnaissance system for power grid planning based on video AI - Google Patents
Auxiliary reconnaissance system for power grid planning based on video AI Download PDFInfo
- Publication number
- CN117197526A CN117197526A CN202310917320.2A CN202310917320A CN117197526A CN 117197526 A CN117197526 A CN 117197526A CN 202310917320 A CN202310917320 A CN 202310917320A CN 117197526 A CN117197526 A CN 117197526A
- Authority
- CN
- China
- Prior art keywords
- video
- base
- video acquisition
- suite
- power grid
- 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
- 238000011835 investigation Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000013016 damping Methods 0.000 claims abstract description 5
- 238000003709 image segmentation Methods 0.000 claims abstract description 4
- 230000007613 environmental effect Effects 0.000 claims abstract description 3
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000035939 shock Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000004807 localization Effects 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
- 108091008695 photoreceptors Proteins 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a video AI-based power grid planning auxiliary investigation system, which comprises a video acquisition suite, a transportation base and a data algorithm background system; the video acquisition suite is used for collecting environmental image information and comprises two cameras for simulating binocular stereoscopic vision and acquiring the length, width and depth information of a three-dimensional object; the transportation base is a base for carrying the video acquisition suite and moving and comprises a damping cradle head assembly for preventing the video acquisition suite from shaking violently; the data algorithm background system acquires environment image information collected by the video acquisition suite, firstly performs image classification through a built-in computer vision algorithm, and then realizes target detection, object positioning and image segmentation on the basis of the image classification. The invention can realize intelligent final investigation operation.
Description
Technical Field
The invention relates to a video AI-based power grid planning auxiliary investigation system for the field of power transmission and transformation line selection.
Background
The transmission and transformation project line selection is an important link in the power grid planning and design work, and plays a role in the power grid planning and design. The power transmission and transformation project line selection relates to the current situation of a power grid, a geographical environment, socioeconomic performance and other factors, and in the traditional line selection technology, the planning of each line depends on the experience of a designer to a great extent, and the defects of long design period, high labor intensity, strong subjectivity, low intelligent degree and the like exist. Meanwhile, the traditional line selection technology is difficult to select the optimal line selection scheme from alternative schemes based on social economy and geographic environment conditions, namely the optimal line selection scheme cannot be realized, and the requirements of high-efficiency and high-quality construction of the modern electric network cannot be met. Therefore, how to design an intelligent power grid planning line selection method has become one of the technical problems to be solved.
The prior art scheme is generally divided into two steps, namely initial survey line selection and final survey line selection.
The method comprises the steps of initially surveying, marking the positions of a line starting point and a middle necessary point on a power grid GIS map or a topographic map (the proportion is generally 1/5 ten thousand or 1/10 ten thousand), marking 2-3 schemes on the map according to the topographic features appearing on the map and considering factors such as traffic conditions, calculating communication interference and the like according to short-circuit current planned by a system perspective, the condition of large conductivity in the region and the like, and correcting and providing specific measures for the selected path scheme according to calculation results.
The final investigation is that the method is implemented on site on the basis of the preliminarily designed route scheme, the final trend of the route is determined according to actual conditions, and conditions are created for positioning construction of the route; the path selection comprises mountain path, river crossing path selection, corner point position determination, path selection of the line approaching or passing through a special section and the like. In the process of determining the path in the final investigation, a great deal of manpower and material resources are consumed for repeated investigation. By means of photographing record, the overall view of the scene cannot be displayed in a three-dimensional way, the distance between the elements cannot be automatically marked, and the distance cannot be fused with future planning of cities and future planning of roads.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a video AI-based power grid planning auxiliary investigation system which can realize intelligent final investigation operation.
The technical scheme for achieving the purpose is as follows: a video AI-based power grid planning auxiliary investigation system comprises a video acquisition suite, a transportation base and a data algorithm background system;
the video acquisition suite is used for collecting environmental image information and comprises two cameras for simulating binocular stereoscopic vision and acquiring the length, width and depth information of a three-dimensional object;
the transportation base is a base for carrying the video acquisition suite and moving and comprises a damping cradle head assembly for preventing the video acquisition suite from shaking violently;
the data algorithm background system acquires environment image information collected by the video acquisition suite, firstly performs image classification through a built-in computer vision algorithm, and then realizes target detection, object positioning and image segmentation on the basis of the image classification.
Further, two cameras of video acquisition external member set up in a horizontal supporting platform's both ends, and horizontal supporting platform's middle part is equipped with the support column, supports on the transportation base.
Still further, the distance between the two camera shots is 20cm-80cm.
Further, the specific method for the information of the length, width and depth of the three-dimensional object of the video acquisition kit is that one object is observed from two, images under different visual angles are obtained, and according to the matching relation of pixels between the images, the offset between the pixels is calculated through a triangulation principle to obtain the three-dimensional information of the object.
Further, the transportation base is a vehicle-mounted base mobile robot base or an unmanned aerial vehicle base.
Further, the damping tripod head component comprises a tripod head base, a direct current brushless motor and a high-precision acceleration sensor, and is controlled by a time-attitude tracking and adjusting algorithm; when the camera tripod head is affected by the environment and shakes or tilts, the tripod head base accurately obtains the deviation of the visual axis through the high-precision acceleration sensor, calculates and outputs a control signal to the DC brushless motor through the attitude tracking adjustment algorithm, and adjusts the tripod head base to shock.
The video AI-based power grid planning auxiliary investigation system can greatly reduce the time of on-site repeated investigation, is convenient for automatic induction and arrangement of investigation results, is convenient for sharing the investigation results with other designs or reviewers, can more conveniently realize the team force of the key element of the investigation design, and can more accurately and efficiently improve the planning design efficiency, improve the reliability of the planning design stage and save a large amount of manpower and material resource costs.
Drawings
Fig. 1 is a schematic diagram of triangulation of a video AI-based grid planning assisted survey system of the present invention.
Detailed Description
In order to better understand the technical solution of the present invention, the following detailed description is given by way of specific examples:
the invention relates to a video AI-based power grid planning auxiliary investigation system, which comprises a video acquisition suite, a transportation base and a data algorithm background system.
Example 1
The video acquisition suite adopts binocular stereoscopic vision technology and consists of two cameras. The two cameras are arranged at two ends of a horizontal supporting platform, and the middle part of the horizontal supporting platform is provided with a supporting column which is supported on the transportation base. The distance between the two shooting shots is 20cm-80cm, preferably 50cm. The acquisition suite is used for collecting environment image information, simulating binocular stereoscopic vision and acquiring information of the length, width and depth of a three-dimensional object.
The specific method for acquiring the information of the length, the width and the depth of the three-dimensional object of the suite is that one object is observed from two, images under different visual angles are acquired, and the three-dimensional information of the object is acquired by calculating the offset among pixels according to the matching relation of the pixels among the images and the triangulation principle. Referring to fig. 1, Q is a certain point on an object to be measured, OR and OT are optical centers of two cameras respectively, imaging points of the point Q on photoreceptors of the two cameras are P and P' (an imaging plane of the camera is placed in front of a lens after rotation), f is a focal length of the camera, B is a center distance of the two cameras, and Z is depth information that we want to obtain.
The transportation base is a base for carrying the video acquisition suite and moving, and the vehicle-mounted base is adopted, and the vibration reduction cradle head assembly is used for avoiding violent shaking of the video acquisition suite. The damping tripod head component comprises a tripod head base, a direct current brushless motor and a high-precision acceleration sensor, and is controlled by a time-attitude tracking and adjusting algorithm; when the camera tripod head is affected by the environment and shakes or tilts, the tripod head base accurately obtains the deviation of the visual axis through the high-precision acceleration sensor, calculates and outputs a control signal to the DC brushless motor through the attitude tracking adjustment algorithm, and adjusts the tripod head base to shock.
The data algorithm background system acquires environment image information collected by the video acquisition suite, firstly performs image classification through a built-in computer vision algorithm, and then realizes target detection, object positioning and image segmentation on the basis of the image classification. Among other things, object detection is a challenging computer vision task that can be seen as a combination of image classification and localization, i.e., given a picture, the object of the picture is identified and its location is given. The auxiliary reconnaissance system for the power grid planning based on the video AI can rapidly detect line selection elements (such as elements for identifying electric poles, well covers and the like) through target detection and identification, and can implement calculation distance by combining depth information.
Example 2
The transportation base adopts a mobile robot. The robot adopts a crawler robot which stably moves.
Example 3
The transportation base adopts unmanned aerial vehicle base.
It will be appreciated by persons skilled in the art that the above embodiments are provided for illustration only and not for limitation of the invention, and that variations and modifications of the above described embodiments are intended to fall within the scope of the claims of the invention as long as they fall within the true spirit of the invention.
Claims (6)
1. The power grid planning auxiliary investigation system based on the video AI is characterized by comprising a video acquisition suite, a transportation base and a data algorithm background system;
the video acquisition suite is used for collecting environmental image information and comprises two cameras for simulating binocular stereoscopic vision and acquiring the length, width and depth information of a three-dimensional object;
the transportation base is a base for carrying the video acquisition suite and moving and comprises a damping cradle head assembly for preventing the video acquisition suite from shaking violently;
the data algorithm background system acquires environment image information collected by the video acquisition suite, firstly performs image classification through a built-in computer vision algorithm, and then realizes target detection, object positioning and image segmentation on the basis of the image classification.
2. The auxiliary reconnaissance system for power grid planning based on video AI of claim 1, wherein the two cameras of the video acquisition suite are arranged at two ends of a horizontal supporting platform, and a supporting column is arranged in the middle of the horizontal supporting platform and is supported on a transportation base.
3. A video AI-based grid planning assistance investigation system according to claim 2, characterized in that the distance between two camera shots is 20cm-80cm.
4. The auxiliary survey system for planning a power grid based on video AI of claim 1, wherein the specific method for acquiring the information of the length, width and depth of the three-dimensional object of the suite is to observe one object from two, acquire images under different view angles, calculate the offset between pixels according to the matching relation of the pixels between the images, and acquire the three-dimensional information of the object by the triangulation principle.
5. The video AI-based grid planning assistance prospecting system of claim 1, wherein the transport base is a vehicle-mounted base mobile robot base or an unmanned aerial vehicle base.
6. The video AI-based grid planning auxiliary survey system of claim 1, wherein the shock absorbing pan-tilt assembly comprises a pan-tilt base, a brushless dc motor and a high precision acceleration sensor, which are controlled by a time-attitude tracking adjustment algorithm; when the camera tripod head is affected by the environment and shakes or tilts, the tripod head base accurately obtains the deviation of the visual axis through the high-precision acceleration sensor, calculates and outputs a control signal to the DC brushless motor through the attitude tracking adjustment algorithm, and adjusts the tripod head base to shock.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310917320.2A CN117197526A (en) | 2023-07-25 | 2023-07-25 | Auxiliary reconnaissance system for power grid planning based on video AI |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310917320.2A CN117197526A (en) | 2023-07-25 | 2023-07-25 | Auxiliary reconnaissance system for power grid planning based on video AI |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117197526A true CN117197526A (en) | 2023-12-08 |
Family
ID=89004173
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310917320.2A Pending CN117197526A (en) | 2023-07-25 | 2023-07-25 | Auxiliary reconnaissance system for power grid planning based on video AI |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117197526A (en) |
-
2023
- 2023-07-25 CN CN202310917320.2A patent/CN117197526A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110174093B (en) | Positioning method, device, equipment and computer readable storage medium | |
WO2018103408A1 (en) | Aerial image capturing method and system for unmanned aerial vehicle to survey traffic accident scene | |
US11017228B2 (en) | Method and arrangement for condition monitoring of an installation with operating means | |
KR102362714B1 (en) | Methods and systems for generating route data | |
US7982665B2 (en) | GPS-installed all-azimuth camera and spatial data collecting device | |
JP4767578B2 (en) | High-precision CV calculation device, CV-type three-dimensional map generation device and CV-type navigation device equipped with this high-precision CV calculation device | |
US9465129B1 (en) | Image-based mapping locating system | |
CN110246175A (en) | Intelligent Mobile Robot image detecting system and method for the panorama camera in conjunction with holder camera | |
KR20180079428A (en) | Apparatus and method for automatic localization | |
CN103747207A (en) | Positioning and tracking method based on video monitor network | |
CN102436738A (en) | Traffic monitoring device based on unmanned aerial vehicle (UAV) | |
CN112113542A (en) | Method for checking and accepting land special data for aerial photography construction of unmanned aerial vehicle | |
CN103885455B (en) | Tracking measurement robot | |
CN109883433B (en) | Vehicle positioning method in structured environment based on 360-degree panoramic view | |
CN110398760A (en) | Pedestrian's coordinate acquisition equipment and its application method based on image analysis | |
JP5769149B2 (en) | Mobile mapping system, roadside object measurement method using the same, and position specifying program | |
Zeng et al. | The algorithm to generate color point-cloud with the registration between panoramic image and laser point-cloud | |
CN105959529B (en) | It is a kind of single as method for self-locating and system based on panorama camera | |
CN112240762A (en) | Ground photogrammetry data acquisition system | |
CN105321186A (en) | Closed space map collection method and device based on orthographic projection | |
CN111586303A (en) | Control method and device for dynamically tracking road surface target by camera based on wireless positioning technology | |
CN117197526A (en) | Auxiliary reconnaissance system for power grid planning based on video AI | |
CN113190564A (en) | Map updating system, method and device | |
CN115950435A (en) | Real-time positioning method for unmanned aerial vehicle inspection image | |
CN206179016U (en) | Three -dimensional on -vehicle removal image acquisition device who builds pattern |
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 |