CN113807348A - High-voltage cable target identification and positioning method and device - Google Patents
High-voltage cable target identification and positioning method and device Download PDFInfo
- Publication number
- CN113807348A CN113807348A CN202110973073.9A CN202110973073A CN113807348A CN 113807348 A CN113807348 A CN 113807348A CN 202110973073 A CN202110973073 A CN 202110973073A CN 113807348 A CN113807348 A CN 113807348A
- Authority
- CN
- China
- Prior art keywords
- target
- voltage cable
- image
- identification
- roi
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003062 neural network model Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 26
- 238000009826 distribution Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000009471 action Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a high-voltage cable target identification and positioning method and a device, wherein a Yolo v4 deep neural network model is optimized and used for extracting an ROI (region of interest) of a target; then, extracting the minimum external rectangle of the cable target in the ROI area by combining the HSV color tracking technology; and finally, the three-dimensional coordinate information of a plurality of equally-divided points on the cable target is obtained by combining the parameter information of the depth camera, so that the three-dimensional coordinate of the high-voltage cable target is extracted, and more accurate target space information is provided for the mechanical arm action of the live working robot. The positioning identification method provided by the invention has the advantages of higher identification speed, higher identification accuracy and higher reliability in the identification of the high-voltage cable, and solves the problem of inaccurate identification and positioning of target identification under different backgrounds in the prior art.
Description
Technical Field
The invention relates to the technical field of power grid equipment detection, in particular to a high-voltage cable target identification and positioning method and device.
Background
In recent years, with the steady promotion of the construction of a national smart grid and the improvement of the requirement on the power supply stability, the traditional power distribution network maintenance means is more and more difficult to meet the actual requirements due to the defects of high working strength, high safety risk, low operation efficiency and the like. In order to follow the principle of 'energy band non-stop' in distribution network maintenance operation, power supply enterprise units in various regions are continuously strengthening the construction of the non-stop capability of a distribution network, and the non-stop operation becomes an important means for equipment maintenance.
The live working robot system is a common power maintenance operation and maintenance means by depending on a mechanical arm control technology, an artificial intelligence algorithm, a visual sensor and the like, and becomes an important operation mode for replacing manual operation. In the prior art, development of semi-autonomous and fully-autonomous hot-line work robots has gradually become an inevitable trend of electric power scene overhaul and maintenance. However, the live working robot has various problems in practical application, especially for the accuracy of target positioning identification, which needs to be further improved.
Disclosure of Invention
Based on the above situation in the prior art, the present invention aims to provide a method and an apparatus for identifying and positioning a high-voltage cable target, which utilize an optimized Yolo v4 target detection technology and a color tracking technology, and combine a depth camera to extract a three-dimensional coordinate of the high-voltage cable target. Therefore, the problem that the target identification in the prior art is inaccurate in identification and positioning under different backgrounds is solved.
In order to achieve the above object, according to one aspect of the present invention, there is provided a high voltage cable target identification and positioning method, including the steps of:
acquiring a high-voltage cable image and preprocessing the high-voltage cable image;
optimizing a YOLO v4 deep neural network model, simplifying the number of residual error units in a backbone network, and reducing the number of channels;
recognizing a high-voltage cable target in the image by adopting the trained deep neural network model and extracting an ROI (region of interest) of the target;
extracting a minimum circumscribed rectangle of the target in the ROI area according to the inherent attribute and the depth information of the high-voltage cable target;
according to the minimum external rectangle, carrying out N equal division on the length of the cable target to obtain three-dimensional coordinates of equal division points;
and positioning by using the three-dimensional coordinates.
Further, the acquiring a target image of the high-voltage cable and preprocessing the target image comprises:
acquiring a high-voltage cable image by using a depth camera;
and labeling the acquired image.
Further, the recognizing a high-voltage cable target in the image and extracting an ROI region of the target by using the trained deep neural network model includes:
carrying out target detection on the image by adopting the trained deep neural network model;
judging whether the image contains a high-voltage cable target or not, and if so, carrying out the next step; if not, returning to the step of acquiring the high-voltage cable image;
and performing mask processing on the ROI area of the cable target on the acquired image according to the position information output by the detection result.
Further, the extracting a minimum bounding rectangle of the high-voltage cable target in the ROI region according to the intrinsic property and the depth information of the target includes:
performing HSV feature transformation on the ROI and counting distribution features of the ROI;
selecting a threshold value to carry out binarization processing according to the counted HSV distribution characteristics and the inherent attribute and depth information of the high-voltage cable target;
filtering the image after the binarization processing by using morphological processing;
and solving the minimum circumscribed rectangle of the cable target by using the moment of the image.
Further, the method also comprises the following steps:
after the minimum external rectangle of the cable target is obtained, judging whether the rectangle contains the target or not, and if so, carrying out the next step; and if not, returning to the step of acquiring the high-voltage cable image.
Further, the equally dividing the cable target by N in length to obtain three-dimensional coordinates of an equally divided point includes:
dividing N equally on the long side of the rectangle according to the position information and the rotation angle of the minimum circumscribed rectangle; the rotation angle is obtained in the process of obtaining the minimum circumscribed rectangle of the cable target;
and obtaining the three-dimensional coordinate value of the bisector according to the camera depth information and the parameter information.
According to a second aspect of the present invention, there is provided a robot arm guiding method for a live working robot, which guides a robot arm of the live working robot to perform work using three-dimensional coordinates obtained by a high voltage cable target recognition positioning method, the high voltage cable target recognition positioning method including the method according to the first aspect of the present invention.
According to a third aspect of the invention, a high-voltage cable target identification and positioning device is provided, which comprises an image acquisition module, a neural network model optimization module, an image identification module, a coordinate acquisition module and a positioning module; wherein,
the image acquisition module is used for acquiring a high-voltage cable image and carrying out preprocessing;
the neural network model optimization module is used for optimizing a YOLO v4 deep neural network model, simplifying the number of residual error units in a backbone network and reducing the number of channels;
the image recognition module recognizes a high-voltage cable target in the image by adopting the trained deep neural network model and extracts an ROI (region of interest) of the target;
the coordinate acquisition module is used for extracting the minimum external rectangle of the target in the ROI area according to the inherent attribute and the depth information of the high-voltage cable target; according to the minimum external rectangle, the length of the cable target is divided into N equal parts, and the three-dimensional coordinates of equal division points are obtained;
and the positioning module is used for positioning by utilizing the three-dimensional coordinates.
Further, the coordinate obtaining module extracts a minimum circumscribed rectangle of the high-voltage cable target in the ROI region according to the inherent property and the depth information of the target, and includes:
performing HSV feature transformation on the ROI and counting distribution features of the ROI;
selecting a threshold value to carry out binarization processing according to the counted HSV distribution characteristics and the inherent attribute and depth information of the high-voltage cable target;
filtering the image after the binarization processing by using morphological processing;
and solving the minimum circumscribed rectangle of the cable target by using the moment of the image.
According to a fourth aspect of the present invention, there is provided a storage medium storing a computer program which, when executed by a processor, performs the method according to the first aspect of the present invention.
In summary, the invention provides a high-voltage cable target identification and positioning method and device, which optimize a Yolo v4 deep neural network model and extract an ROI of a target by using the model; then, extracting the minimum external rectangle of the cable target in the ROI area by combining the HSV color tracking technology; and finally, the three-dimensional coordinate information of a plurality of equally-divided points on the cable target is obtained by combining the parameter information of the depth camera, so that the three-dimensional coordinate of the high-voltage cable target is extracted, and more accurate target space information is provided for the mechanical arm action of the live working robot. The positioning identification method provided by the invention has the advantages of higher identification speed, higher identification accuracy and higher reliability in the identification of the high-voltage cable, and solves the problem of inaccurate identification and positioning of target identification under different backgrounds in the prior art.
Drawings
FIG. 1 is a flow chart of a high voltage cable target identification and positioning method of the present invention;
FIG. 2 is a diagram of cable target HSV feature distribution of statistics under different light rays and angles;
fig. 3 is a block diagram of the high-voltage cable target identification and positioning device of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The technical solution of the present invention will be described in detail below with reference to the accompanying drawings. According to an embodiment of the present invention, there is provided a high voltage cable target identification and positioning method, a flowchart of which is shown in fig. 1, and the method includes the following steps:
and S1, acquiring a high-voltage cable image and preprocessing the high-voltage cable image. A depth camera may be employed to capture images of the high voltage cable target including information about various positions, heights, and angles of the cable. Compared with a traditional camera, the depth camera has the function of depth measurement, so that the surrounding environment and change can be sensed more conveniently and accurately. The image is preprocessed to eliminate the effect of noise, and for example, the image may be labeled by using processing software such as Yolo _ mark or labelImg and saved in txt format.
S2, optimizing a YOLO v4 deep neural network model. In the present embodiment, the YOLO v4 deep neural network model is used for image recognition. The YOLO v4 deep neural network model is an algorithm which combines a large number of previous research technologies, combines the technologies and creates a proper innovation, and the balance between speed and precision is realized. For specific application objects, the YOLO v4 deep neural network model is optimized appropriately by the embodiment, so that the recognition speed of the model on the high-voltage cable is higher, the recognition accuracy is improved, and the reliability is higher. The optimization process comprises the following steps: the feature extraction backbone network is simplified and optimized, the CSPDarknet53 backbone network of YOLO v4 has 5 downsampling layers and 5 CSPNet structures, and the CSPNet structures respectively have 1, 2, 8 and 4 residual error units Res-unit. In this embodiment, the number of residual error units in the CSPNet structure is simplified to 1, 2, 4, 2 residual error units, and the model size is further reduced by halving the number of channels; an SPP structure network is improved, and a structure similar to a CSP unit, namely a CSP-SPP module, is formed by adding a short layer; cutting on the channel dimension by using a network cutting method; and generating the anchors size of the high-voltage cable by using a k-Means clustering method and combining the actual target of the high-voltage cable, and replacing the anchors in the configuration file.
And S3, recognizing the high-voltage cable target in the image by adopting the trained deep neural network model and extracting the ROI (region of interest) of the target. The following steps may be employed:
carrying out target detection on the image by adopting the trained deep neural network model;
judging whether the image contains a high-voltage cable target or not, and if so, carrying out the next step; if not, returning to the step of acquiring the high-voltage cable image;
and performing mask processing on the ROI area of the cable target on the acquired image according to the position information output by the detection result.
And S4, extracting the minimum circumscribed rectangle of the cable target according to the inherent attribute and the depth information of the high-voltage cable target. The details will be described below.
And performing HSV feature transformation on the ROI and counting distribution features of the ROI. In this embodiment, according to the cable imaging characteristics of different illumination and different angles, three component values H, S, V of the remaining cable pixels 1300 are counted, and the distribution characteristics thereof are counted, and the cable target HSV characteristic distribution counted under different light rays and angles is shown in fig. 2, wherein the abscissa represents the magnitude of H, S, V, and the ordinate represents the intensity thereof. According to the statistical HSV distribution characteristics and the inherent attributes of the high-voltage cable target, a threshold is selected to carry out binarization processing, namely, under an HSV color space, a proper threshold is selected to carry out binarization processing according to the inherent attributes and depth information of high-voltage cable color information under different environments, specifically, a depth map corresponding to an ROI (region of interest) region can be subjected to binarization processing according to a preset range of the cable target from a depth camera, and then two binarization maps are subjected to AND operation to obtain a more accurate binarization map. Filtering the image after the binarization processing by using morphological processing; and solving the minimum circumscribed rectangle of the cable target by using the moment of the image. Because the cable image obtained after the binarization processing is a black-and-white image, a white part in the image represents a cable under normal conditions, and a black part represents a background; however, some false targets with colors relatively close to the colors of the cables are extracted in abnormal conditions, and the target images with higher reliability can be obtained by performing the processing on the images. In this step, for example, a basic function in the commonly used image processing software OpenCV may be used to obtain the minimum bounding rectangle, and in this process, parameters such as the aspect ratio, the area size, and the rotation angle of the minimum bounding rectangle may be obtained.
After the minimum circumscribed rectangle of the cable target is obtained, judging whether the rectangle contains the target or not, if so, performing step S5; if not, the process returns to step S1 to acquire the high-voltage cable image. The length-width ratio, the area size, the rotation angle and other parameters of the minimum circumscribed rectangle obtained in the previous step can be used for judging whether the obtained minimum circumscribed rectangle contains the high-voltage cable target or not, namely, the result of target identification is verified again.
S5, equally dividing the cable object in length by N according to the minimum circumscribed rectangle, and obtaining the three-dimensional coordinates of the equally divided points. Dividing N equal parts on the long side of the rectangle according to the position information of the minimum circumscribed rectangle and the parameter rotation angle obtained in the last step; and obtaining the three-dimensional coordinate value of the bisector according to the camera depth information and the parameter information. The parameter information includes internal parameter information of the camera and information such as a focal length of the lens. The three-dimensional coordinate values can be obtained by using a commonly used projection formula.
And S6, positioning by using the three-dimensional coordinates.
According to a second embodiment of the invention, a robot arm guiding method of a live working robot is provided, which guides a robot arm of the live working robot to perform work by using three-dimensional coordinates obtained by a high-voltage cable target identification and positioning method. The high-voltage cable target identification and positioning method may adopt the positioning method as described in the first embodiment of the present invention. In practical application, after the lower computer acquires the three-dimensional coordinate information of the equant points by using the positioning method, the three-dimensional coordinate information is uploaded to a control center by using a communication protocol such as socket, and the control center issues a control instruction to a mechanical arm of the electrified operating robot according to the three-dimensional coordinate information to control the mechanical arm to reach a specified position.
According to a third embodiment of the present invention, a block diagram of a high voltage cable target identification and positioning device is provided, and the device is shown in fig. 3 and includes an image acquisition module, a neural network model optimization module, an image identification module, a coordinate acquisition module, and a positioning module.
The image acquisition module is used for acquiring a high-voltage cable image and carrying out preprocessing;
the neural network model optimization module is used for optimizing a YOLO v4 deep neural network model;
the image recognition module recognizes and extracts an ROI (region of interest) of the high-voltage cable target image by adopting the trained deep neural network model;
the coordinate acquisition module is used for extracting the minimum external rectangle of the cable target according to the inherent attribute and the depth information of the high-voltage cable target; according to the minimum external rectangle, the length of the cable target is divided into N equal parts, and the three-dimensional coordinates of equal division points are obtained;
and the positioning module performs positioning by using the three-dimensional coordinates.
The specific process of each module in the device to realize its function is the same as each step of the fault location method in the first embodiment provided by the present invention, and is not described herein again.
According to a fourth embodiment of the invention, a storage medium is provided, which stores a computer program which, when executed by a processor, implements the method as described in the first or second embodiment of the invention.
In summary, the invention relates to a high-voltage cable target identification and positioning method and device, which optimize a Yolo v4 deep neural network model and extract an ROI of a target by using the model; then, extracting the minimum external rectangle of the cable target in the ROI area by combining the HSV color tracking technology; and finally, the three-dimensional coordinate information of a plurality of equally-divided points on the cable target is obtained by combining the parameter information of the depth camera, so that the three-dimensional coordinate of the high-voltage cable target is extracted, and more accurate target space information is provided for the mechanical arm action of the live working robot. The positioning identification method provided by the invention has the advantages of higher identification speed, higher identification accuracy and higher reliability in the identification of the high-voltage cable, and solves the problem of inaccurate identification and positioning of target identification under different backgrounds in the prior art.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (10)
1. A high-voltage cable target identification and positioning method is characterized by comprising the following steps:
acquiring a high-voltage cable image and preprocessing the high-voltage cable image;
optimizing a YOLO v4 deep neural network model, simplifying the number of residual error units in a backbone network, and reducing the number of channels;
recognizing a high-voltage cable target in the image by adopting the trained deep neural network model and extracting an ROI (region of interest) of the target;
extracting a minimum circumscribed rectangle of the target in the ROI area according to the inherent attribute and the depth information of the high-voltage cable target;
according to the minimum external rectangle, carrying out N equal division on the length of the cable target to obtain three-dimensional coordinates of equal division points;
and positioning by using the three-dimensional coordinates.
2. The method of claim 1, wherein the acquiring and preprocessing high voltage cable target images comprises:
acquiring a high-voltage cable image by using a depth camera;
and labeling the acquired image.
3. The method of claim 2, wherein the identifying the high voltage cable target in the image and extracting the ROI area of the target by using the trained deep neural network model comprises:
carrying out target detection on the image by adopting the trained deep neural network model;
judging whether the image contains a high-voltage cable target or not, and if so, carrying out the next step; if not, returning to the step of acquiring the high-voltage cable image;
and performing mask processing on the ROI area of the cable target on the acquired image according to the position information output by the detection result.
4. The method of claim 3, wherein the extracting the minimum bounding rectangle of the high voltage cable target in the ROI area according to the intrinsic properties and the depth information of the target comprises:
performing HSV feature transformation on the ROI and counting distribution features of the ROI;
selecting a threshold value to carry out binarization processing according to the counted HSV distribution characteristics and the inherent attribute and depth information of the high-voltage cable target;
filtering the image after the binarization processing by using morphological processing;
and solving the minimum circumscribed rectangle of the cable target by using the moment of the image.
5. The method of claim 4, further comprising the step of:
after the minimum external rectangle of the cable target is obtained, judging whether the rectangle contains the target or not, and if so, carrying out the next step; and if not, returning to the step of acquiring the high-voltage cable image.
6. The method of claim 5, wherein the equally dividing the cable target by N in length to obtain three-dimensional coordinates of an equally divided point comprises:
dividing N equally on the long side of the rectangle according to the position information and the rotation angle of the minimum circumscribed rectangle; the rotation angle is obtained in the process of obtaining the minimum circumscribed rectangle of the cable target;
and obtaining the three-dimensional coordinate value of the bisector according to the camera depth information and the parameter information.
7. A method for guiding a robot arm of a live working robot by using three-dimensional coordinates obtained by a high-voltage cable target identification and positioning method, wherein the high-voltage cable target identification and positioning method comprises the method according to any one of claims 1 to 6.
8. A high-voltage cable target identification and positioning device is characterized by comprising an image acquisition module, a neural network model optimization module, an image identification module, a coordinate acquisition module and a positioning module; wherein,
the image acquisition module is used for acquiring a high-voltage cable image and carrying out preprocessing;
the neural network model optimization module is used for optimizing a YOLO v4 deep neural network model, simplifying the number of residual error units in a backbone network and reducing the number of channels;
the image recognition module recognizes a high-voltage cable target in the image by adopting the trained deep neural network model and extracts an ROI (region of interest) of the target;
the coordinate acquisition module is used for extracting the minimum external rectangle of the target in the ROI area according to the inherent attribute and the depth information of the high-voltage cable target; according to the minimum external rectangle, the length of the cable target is divided into N equal parts, and the three-dimensional coordinates of equal division points are obtained;
and the positioning module is used for positioning by utilizing the three-dimensional coordinates.
9. The apparatus of claim 8, wherein the coordinate obtaining module extracts a minimum bounding rectangle of the high voltage cable target in the ROI area according to the intrinsic property and the depth information of the target, comprising:
performing HSV feature transformation on the ROI and counting distribution features of the ROI;
selecting a threshold value to carry out binarization processing according to the counted HSV distribution characteristics and the inherent attribute and depth information of the high-voltage cable target;
filtering the image after the binarization processing by using morphological processing;
and solving the minimum circumscribed rectangle of the cable target by using the moment of the image.
10. A storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973073.9A CN113807348A (en) | 2021-08-24 | 2021-08-24 | High-voltage cable target identification and positioning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973073.9A CN113807348A (en) | 2021-08-24 | 2021-08-24 | High-voltage cable target identification and positioning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113807348A true CN113807348A (en) | 2021-12-17 |
Family
ID=78941484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110973073.9A Pending CN113807348A (en) | 2021-08-24 | 2021-08-24 | High-voltage cable target identification and positioning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807348A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
| CN112069886A (en) * | 2020-07-31 | 2020-12-11 | 许继集团有限公司 | Transformer substation respirator state intelligent identification method and system |
| CN112796036A (en) * | 2020-12-29 | 2021-05-14 | 黑龙江维摩科技有限责任公司 | Bobbin state detection method |
-
2021
- 2021-08-24 CN CN202110973073.9A patent/CN113807348A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109814600A (en) * | 2019-03-12 | 2019-05-28 | 重庆大学 | A kind of unmanned plane cable tunnel inspection flying method |
| CN112069886A (en) * | 2020-07-31 | 2020-12-11 | 许继集团有限公司 | Transformer substation respirator state intelligent identification method and system |
| CN112796036A (en) * | 2020-12-29 | 2021-05-14 | 黑龙江维摩科技有限责任公司 | Bobbin state detection method |
Non-Patent Citations (1)
| Title |
|---|
| 李东宾 等: "基于改进YOLO 与HSV 变换的高压线缆识别定位方法", 《通信电源技术》, vol. 38, no. 12, pages 1 - 6 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977813B (en) | Inspection robot target positioning method based on deep learning framework | |
| CN111340797A (en) | Laser radar and binocular camera data fusion detection method and system | |
| CN109993086B (en) | Face detection method, device and system and terminal equipment | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN108710913A (en) | A kind of switchgear presentation switch state automatic identification method based on deep learning | |
| CN113034624B (en) | Temperature early warning image identification method, system, equipment and storage medium based on thermochromic adhesive | |
| CN106908064B (en) | Indoor night vision navigation method based on Kinect2 sensor | |
| CN111260788A (en) | Power distribution cabinet switch state identification method based on binocular vision | |
| CN107845095A (en) | Mobile object real time detection algorithm based on three-dimensional laser point cloud | |
| CN113324864A (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN112197705A (en) | Fruit positioning method based on vision and laser ranging | |
| CN111639568A (en) | Navigation patrol method for intelligent robot of transformer substation | |
| CN114596555A (en) | Obstacle point cloud data screening method and device, electronic equipment and storage medium | |
| CN113469178A (en) | Electric power meter identification method based on deep learning | |
| CN116703986A (en) | Infrared and visible light-based transformation equipment temperature abnormality early warning method and system | |
| CN113837044A (en) | Organ positioning method based on ambient brightness and related equipment | |
| CN116901089B (en) | Multi-angle vision distance robot control method and system | |
| CN117789090A (en) | High-altitude safety belt detection method, system, equipment and medium | |
| CN114639159A (en) | Moving pedestrian detection method, electronic device and robot | |
| CN113807348A (en) | High-voltage cable target identification and positioning method and device | |
| CN112364693B (en) | Binocular vision-based obstacle recognition method, device, equipment and storage medium | |
| CN111539329B (en) | Self-adaptive substation pointer instrument identification method | |
| CN111079713A (en) | Method for extracting pedestrian color features and terminal equipment | |
| Hou et al. | Detection and localization of citrus picking points based on binocular vision | |
| CN113780040B (en) | Positioning method and device for lip key points, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |