CN114022763A - Foreign matter detection method and device for high-voltage overhead line and readable storage medium - Google Patents
Foreign matter detection method and device for high-voltage overhead line and readable storage medium Download PDFInfo
- Publication number
- CN114022763A CN114022763A CN202111266402.2A CN202111266402A CN114022763A CN 114022763 A CN114022763 A CN 114022763A CN 202111266402 A CN202111266402 A CN 202111266402A CN 114022763 A CN114022763 A CN 114022763A
- Authority
- CN
- China
- Prior art keywords
- target image
- image
- preset standard
- detected
- standard image
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a foreign matter detection method, a device and a readable storage medium for a high-voltage overhead line, wherein the method comprises the following steps: acquiring an image of a high-voltage overhead line to be detected as a target image; matching the target image with a preset standard image to determine the number of similar features in the two images, wherein the preset standard image is an image of the high-voltage overhead line to be detected at one or more preset angles without foreign matters; and determining whether foreign matters exist in the target image according to the similar characteristic quantity. The foreign matter detection method, the device and the readable storage medium for the high-voltage overhead line disclosed by the embodiment of the invention are used for realizing the foreign matter detection of the high-voltage overhead line from the normal state of the high-voltage overhead line without establishing a known foreign matter sample knowledge base or collecting massive training samples in advance.
Description
Technical Field
The present invention relates to the field of electric power safety detection, and more particularly, to a method and apparatus for detecting foreign objects in a high voltage overhead line, and a readable storage medium.
Background
In a booster station and a high-voltage overhead network, due to the high voltage ratio, short circuits and even fires are easily caused by hanging some high-altitude floating objects on high-voltage line equipment. In some intelligent power stations, inspection robots are often equipped to detect the power equipment and the high-voltage network, wherein the detection of foreign matters at high altitude is a very important detection link.
At present, most of the methods for detecting objects are based on known knowledge base detection, namely, the positions of the objects are calibrated under the condition that some foreign body samples exist, and then the detection is carried out after a model is trained through a large number of such samples. Such a detection method is effective based on the detection of a known object, but the unknown degree of the floating foreign matter is relatively large, and the training sample cannot cover all the foreign matters.
Disclosure of Invention
In a first aspect, an embodiment of the present application provides a method for detecting foreign matter in a high-voltage overhead line, including:
acquiring an image of a high-voltage overhead line to be detected as a target image;
matching the target image with a preset standard image to determine the number of similar features in the two images, wherein the preset standard image is an image of the high-voltage overhead line to be detected at one or more preset angles without foreign matters;
and determining whether foreign matters exist in the target image according to the similar feature quantity.
In a second aspect, an embodiment of the present application provides a foreign object detection apparatus for a high voltage overhead line, including a memory and a processor, where the memory is used for storing a computer program; the computer program, when executed by the processor, implements a method of foreign object detection for a high voltage overhead line as set forth in any of the embodiments of the first aspect.
In a third aspect, the present application provides a computer-readable storage medium, on which computer instructions are stored, and when executed by a processor, the instructions implement the steps of the method according to any one of the embodiments of the first aspect.
Compared with the prior art, the foreign matter detection method, the foreign matter detection device and the readable storage medium for the high-voltage overhead line provided by at least one embodiment of the application have the following beneficial effects: starting from the normal state of the high-voltage overhead line, the obtained current shot target measured image is compared with the preset standard image which is set in advance, so that the foreign matter detection of the high-voltage overhead line is realized, a known foreign matter sample knowledge base does not need to be established, and a large amount of training samples do not need to be collected in advance.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. Other advantages of the present application may be realized and attained by the instrumentalities and combinations particularly pointed out in the specification and the drawings.
Drawings
The accompanying drawings are included to provide an understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the examples serve to explain the principles of the disclosure and not to limit the disclosure.
Fig. 1 is a flowchart of a foreign object detection method for a high voltage overhead line according to an exemplary embodiment of the present invention;
fig. 2 is a flowchart illustrating feature matching between a target image and a preset standard image according to an embodiment of the present invention;
fig. 3 is a flowchart of target image area calibration according to an embodiment of the present invention;
fig. 4 is a flowchart of a foreign object detection method for a high voltage overhead line according to an exemplary embodiment of the present invention;
fig. 5 is a block diagram of a foreign matter detection device for a high-voltage overhead line according to an embodiment of the present invention.
Detailed Description
The present application describes embodiments, but the description is illustrative rather than limiting and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or instead of any other feature or element in any other embodiment, unless expressly limited otherwise.
The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive concept as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive aspects to form yet another unique inventive aspect, as defined by the claims. Thus, it should be understood that any of the features shown and/or discussed in this application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not limited except as by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.
Further, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other orders of steps are possible as will be understood by those of ordinary skill in the art. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Further, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.
Fig. 1 is a flowchart of a foreign object detection method for a high voltage overhead line according to an exemplary embodiment of the present invention, and as shown in fig. 1, the foreign object detection method for a high voltage overhead line may include:
s101: and acquiring an image of the high-voltage overhead line to be detected as a target image.
In this embodiment, mainly to the detection that high-voltage and extra-high voltage overhead line foreign matter of booster station and extra-high voltage transformer substation hung or unusual object covers, through obtaining the image of waiting to detect high-voltage overhead line and have or not the foreign matter.
Wherein, the accessible is patrolled and examined the robot and is shot the image that acquires the high-tension overhead line who treats the detection, perhaps the accessible unmanned aerial vehicle aerial photography detects the image of high-tension overhead line.
S102: and matching the target image with a preset standard image to determine the number of similar features in the two images, wherein the preset standard image is an image of the high-voltage overhead line to be detected at one or more preset angles without foreign matters.
In this embodiment, one or more preset standard images based on the same high-voltage overhead line as the target image may be determined in advance, and images of the high-voltage overhead line to be detected taken at several different angles without foreign matter may be used as the preset standard images.
In practical application, foreign matter detection of a high-voltage overhead line is mostly based on known knowledge base detection, namely, the position of an object is calibrated under the condition that some foreign matter samples exist, and then the foreign matter is detected after a large number of samples are used for training a model. However, when detecting foreign objects using a deep learning method based on sample training, a large number of training samples need to be collected in advance, but due to the particularity of the power station, many samples cannot be artificially manufactured for hanging foreign objects in the power station. And although the detection mode based on the known object is effective, the unknown degree of the floating foreign matters is relatively large, and the training sample cannot cover all the foreign matters.
In this embodiment, starting from a normal state of the high-voltage overhead line, the obtained current captured target measurement image is compared with a preset standard image (also referred to as a template image) to perform feature detection on the high-voltage overhead line.
In an example, if there are a plurality of preset standard images having the same area as the target image, the target image may be compared with the plurality of preset standard images having the same area one by one.
S103: and determining whether foreign matters exist in the target image according to the similar characteristic quantity.
In this embodiment, the target measurement image and the preset standard image may be matched, the number of similar features of the two images may be determined to determine the difference in the target image, and the presence or absence of foreign matter in the high-voltage overhead line may be determined according to the difference.
In one example, determining whether there is a foreign object in the target image according to the number of similar features may include:
comparing the number of similar feature points with a preset threshold; when the number of the similar feature points is larger than or equal to a preset threshold value, judging that foreign matters exist in the target image; and when the number of the similar characteristic points is smaller than a preset threshold value, judging that no foreign matter exists in the target image.
In this embodiment, the number of similar feature points of the target test image and the preset standard image is compared with a preset threshold, and whether the number of matched similar feature points is greater than an empirical threshold is determined, where the empirical threshold may be 3000 points. And if the number of the similar feature points is greater than or equal to a preset threshold value, judging that no foreign object exists in the detection target and patrolling the next image. And if the number of the similar characteristic points is smaller than a preset threshold value, judging that foreign matters exist in the detection target.
According to the foreign matter detection method for the high-voltage overhead line, provided by the embodiment of the invention, the obtained current shot target measurement image is compared with the preset standard image in advance according to the normal state of the high-voltage overhead line, so that the foreign matter detection of the high-voltage overhead line is realized, a known foreign matter sample knowledge base is not required to be established, and a large amount of training samples are not required to be collected in advance.
In an exemplary embodiment of the present invention, fig. 2 is a flowchart of performing feature matching between a target image and a preset standard image according to an embodiment of the present invention, and as shown in fig. 2, matching the target image and the preset standard image to determine the number of similar features in the two images may include:
s201: target image area calibration: and comparing the target image with a preset standard image, calibrating and cutting out an area in the target image, which is matched with the position to be detected in the preset standard image.
In this embodiment, the preset standard image and the target image have the same spatial region, for example, the preset standard image may include images of the high-voltage overhead line without the foreign object at three different angles, and the proportions of the same spatial region of the preset standard image and the target image at the three angles may be 40%, 60%, and 80%, respectively. That is, the preset standard image and the target image do not have the same spatial region.
In this embodiment, the target image is compared with the preset standard image, areas with the same parts in the two images are found out and used as areas to be detected, and the areas to be detected in the target image, that is, the areas matched with the positions to be detected in the preset standard image, are calibrated and cut out.
In an example, the region of the preset standard image where the positions to be detected match can also be calibrated or cut out.
S202: and respectively carrying out feature detection on the position to be detected in the preset standard image and the region cut out from the target image by adopting an ORB feature algorithm so as to respectively obtain feature points of the position to be detected in the preset standard image and the region cut out from the target image.
In this embodiment, an ORB feature algorithm may be used to perform feature detection on the to-be-detected position in the preset standard image and the cut-out region in the target image, that is, perform feature detection on the to-be-detected region in the preset standard image and the to-be-detected region in the target image, so as to obtain all feature points of the to-be-detected region in the preset standard image and the target image. The implementation principle of performing feature detection by using the ORB feature algorithm is the same as that of the existing scheme, and this embodiment is not limited and described herein.
In an example, before performing feature detection on the position to be detected in the preset standard image and the region cut out from the target image respectively by using the ORB feature algorithm, the method may further include: preprocessing the designated area: and performing Gaussian blur preprocessing on the region acquired in the step S201 or the cut region to remove some noise interference.
S203: and matching the feature points in the two images by adopting a minimum distance algorithm to determine the number of similar features in the two images.
The formula of the minimum distance algorithm is as follows:
wherein, F1 is the feature point detected by the position to be detected in the preset standard image, and F2 is the feature point detected by the cut-out region in the target image.
In this embodiment, after all the feature points of the region to be detected in the target image and the preset standard image are respectively obtained in S202, feature matching is performed on the feature points in the two obtained images by using the formula of the minimum distance algorithm, and the number of similar feature points is found by using the feature matching.
In an exemplary embodiment of the present invention, fig. 3 is a flowchart of target image area calibration provided in an embodiment of the present invention, and as shown in fig. 3, comparing the target image with a preset standard image, calibrating and cutting out an area in the target image, which is matched with a to-be-detected position in the preset standard image, may include:
s301: detecting image characteristic points: and respectively detecting the feature points in the preset standard image and the target image by adopting an ORB feature algorithm.
In this embodiment, all the feature points in the target image and the preset standard image may be obtained by using an ORB feature algorithm.
S302: image descriptor matching: and matching the characteristic points in the preset standard image and the target image by adopting a minimum distance algorithm.
In this embodiment, descriptor matching may be performed on the features of the target image and the preset standard image according to the formula of the minimum distance algorithm.
S303: finding a single mapping matrix: and determining a single mapping matrix between the preset standard image and the target image according to the matched characteristic points, and adjusting the target image shot from different visual angles to the angle of the same visual angle as the preset standard image by using the single mapping matrix.
In this embodiment, a single mapping matrix between the target image and the preset standard image is found according to the matched feature points, and the target image captured from different viewing angles is adjusted to have the same viewing angle as the preset standard image by using the single mapping matrix.
S304: acquiring coordinates of four corner points of a target image: and determining four corner coordinates in the target image according to the single mapping matrix and the four corner coordinates of the position to be detected in the preset standard image.
In this embodiment, a region (i.e., a region to be detected) in which the target image and the preset standard image have the same portion may be found, four corner coordinates of the position to be detected in the preset standard image may be found and determined, and based on the four corner coordinates of the position to be detected in the preset standard image and the single mapping matrix determined in S303, the four corner coordinates of the region in the target image matching the position to be detected in the preset standard image may be determined, i.e., the four corner coordinates of the region to be detected in the target image may be determined.
In an example, determining four corner coordinates in the target image according to the single mapping matrix and four corner coordinates of the position to be detected in the preset standard image may include:
according to the single mapping matrix and the coordinates of four corner points of the position to be detected in the preset standard image
Respectively determining four corner point coordinates in a target image;
wherein the content of the first and second substances,
representing the coordinates of the upper left corner or the lower right corner of the position to be detected in the preset standard image,
representing the upper left or lower right coordinates in the target image,
representing a single mapping matrix.
S305: cutting a target image: and calibrating and cutting out an area matched with the position to be detected in the preset standard image in the target image by using coordinates of four corner points in the target image.
In this embodiment, the target image is cut by using the four corner coordinates calculated in S304 to obtain a region in the regional target image, where the region is matched with the to-be-detected position in the preset standard image, that is, the region to be detected in the target image is cut.
In an example, as shown in fig. 3, after the target image is cropped, the method may further include:
s306: and (5) carrying out perspective transformation on the target image.
In this embodiment, the viewing angle of the image cropped in S305 may have an angle difference with the viewing angle of the preset standard image, and the viewing angles of the two images are corrected to the same angle as much as possible through image perspective.
In an exemplary embodiment of the present invention, after determining that there is a foreign object in the target image, the method may further include:
and marking the position of the foreign matter in the target image.
In this embodiment, when it is determined that the target image is a foreign object based on the number of similar features, the position of the foreign object in the target image is marked.
In one example, marking the position of the foreign object in the target image may include:
respectively detecting feature points in a preset standard image and a target image by adopting an ORB feature algorithm; removing the characteristic points matched with the preset standard image in the target image, and clustering the residual characteristic points in the target image; finding out the coordinates of four corner points at the edge in the cluster, and drawing the obtained coordinates of the four corner points on the target image in a bounding box mode to mark the position of the foreign matter in the target image.
In the present embodiment, the foreign object in the target image is detected using the idea of the row difference from the viewpoint of the normal state of the high-voltage overhead line. The region to be detected can be found out by using the characteristics, different characteristics in the preset standard image can be found out by using the characteristics, and the different characteristics are clustered to obtain the coordinates of the region to be detected, so that the effect of detecting the foreign matters is achieved.
In one example, removing the feature points in the target image that match the preset standard image may include: and respectively subtracting the same characteristic points from all the characteristic points of the target image and the preset standard image to obtain different characteristic points of the target image and the preset standard image.
In an example, clustering the remaining feature points in the target image may include: and obtaining different clustering areas by the residual characteristic points in the target image through a K-means clustering algorithm.
In one example, finding four corner coordinates of an edge in a cluster may include:
and (4) sorting the coordinates of the clustered regions in a descending order to obtain the coordinates of the upper left corner and the coordinates of the lower right corner of the clustered regions.
In this embodiment, coordinate sorting may be performed on the clustered regions in the target image in a descending order, and the upper left corner coordinate and the lower right corner coordinate of the clustered regions are obtained. In addition, regions with areas smaller than a threshold may be filtered out through area calculation. The threshold value may be determined based on an empirical value, for example, the threshold value may be set to 1/8 area of the target image.
In an example, drawing the acquired four corner coordinates on the target image by using a bounding box to mark the position of the foreign object in the target image may include:
in this embodiment, a bounding box may be used to mark the foreign object location. For example, the coordinates of four corner points obtained by clustering can be drawn on the target image in the form of a rectangular box by using a box drawing software tool.
Fig. 4 is a flowchart of a foreign object detection method for a high voltage overhead line according to an exemplary embodiment of the present invention, and as shown in fig. 4, the foreign object detection method for a high voltage overhead line may include:
s401: and making a preset standard image.
S402: and calibrating a target image area.
S403: the designated area is preprocessed.
S404: and detecting the characteristics of the cut image and a preset standard image.
S405: the number of similar feature points is found using feature matching.
S406: and judging whether the matching number is larger than a threshold value. If yes, executing S407; otherwise, S409 is executed.
Wherein, the matching number is the number of similar feature points.
S407: it is judged that there is a foreign matter in the detection target.
S408: marking the position of the foreign body.
S409: and judging whether the detected target has foreign objects or not, and inspecting the next image.
Fig. 5 is a block diagram of a structure of a foreign object detection apparatus for a high-voltage overhead line according to an embodiment of the present invention, and as shown in fig. 5, the foreign object detection apparatus for a high-voltage overhead line according to an embodiment of the present invention may include: a memory 51 and a processor 52.
The processor may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits that implement embodiments of the present invention. The memory is for storing a computer program, which when executed by the processor, is for performing the following operations:
acquiring an image of a high-voltage overhead line to be detected as a target image;
matching the target image with a preset standard image to determine the number of similar features in the two images, wherein the preset standard image is an image of the high-voltage overhead line to be detected at one or more preset angles without foreign matters;
and determining whether foreign matters exist in the target image according to the similar feature quantity.
In one example, the processor determines whether there is a foreign object in the target image according to the similar feature quantity, and may include:
comparing the number of similar feature points with a preset threshold;
when the number of the similar feature points is larger than or equal to a preset threshold value, judging that foreign matters exist in the target image;
and when the number of the similar characteristic points is smaller than a preset threshold value, judging that no foreign matter exists in the target image.
In an example, the matching of the target image with a preset standard image by the processor to determine the number of similar features in the two images may include:
target image area calibration: comparing the target image with a preset standard image, calibrating and cutting out an area in the target image, which is matched with a position to be detected in the preset standard image;
respectively carrying out feature detection on the position to be detected in the preset standard image and the region cut out from the target image by adopting an ORB feature algorithm so as to respectively obtain feature points of the position to be detected in the preset standard image and the region cut out from the target image;
matching the feature points in the two images by adopting a minimum distance algorithm to determine the number of similar features in the two images;
the formula of the minimum distance algorithm is as follows:
f1 is a feature point detected at a position to be detected in the preset standard image, and F2 is a feature point detected in a cut-out region in the target image.
In an example, the comparing, by the processor, the target image with a preset standard image, and calibrating and cutting out an area in the target image, which matches the position to be detected in the preset standard image, may include:
respectively detecting feature points in the preset standard image and the target image by adopting an ORB feature algorithm;
matching the feature points in the preset standard image and the target image by adopting a minimum distance algorithm;
determining a single mapping matrix between the preset standard image and the target image according to the matched feature points, and adjusting the target image shot from different visual angles to the angle of the same visual angle as the preset standard image by using the single mapping matrix;
determining four corner coordinates in the target image according to the single mapping matrix and the four corner coordinates of the position to be detected in the preset standard image;
and calibrating and cutting out the area matched with the position to be detected in the preset standard image in the target image by using the coordinates of the four corner points in the target image.
In an example, the determining, by the processor, the coordinates of four corner points in the target image according to the single mapping matrix and the coordinates of four corner points of the position to be detected in the preset standard image may include:
according to the single mapping matrix and the coordinates of the four corner points of the position to be detected in the preset standard image, passing through
Respectively determining coordinates of four corner points in the target image;
wherein the content of the first and second substances,
representing the upper left corner coordinate or the lower right corner coordinate of the position to be detected in the preset standard image,
representing the upper left corner coordinate or the lower right corner coordinate in the target image,
representing the single mapping matrix.
In one example, after the processor determines that there is a foreign object in the target image, the processor is further configured to:
and marking the position of the foreign matter in the target image.
In one example, the processor marking the position of the foreign object in the target image may include:
respectively detecting feature points in the preset standard image and the target image by adopting an ORB feature algorithm;
removing the characteristic points matched with the preset standard image in the target image, and clustering the residual characteristic points in the target image;
finding out coordinates of four corner points of the edge in the cluster, and drawing the obtained coordinates of the four corner points on the target image in a bounding box mode to mark the position of the foreign matter in the target image.
In one example, the processor finding four corner coordinates of the edge in the cluster may include:
and (4) sorting the coordinates of the clustered regions in a descending order to obtain the coordinates of the upper left corner and the coordinates of the lower right corner of the clustered regions.
Embodiments of the present invention may also provide a computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method shown in any of the above embodiments.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Claims (10)
1. A foreign matter detection method for a high-voltage overhead line is characterized by comprising the following steps:
acquiring an image of a high-voltage overhead line to be detected as a target image;
matching the target image with a preset standard image to determine the number of similar features in the two images, wherein the preset standard image is an image of the high-voltage overhead line to be detected at one or more preset angles without foreign matters;
and determining whether foreign matters exist in the target image according to the similar feature quantity.
2. The method of claim 1, wherein said determining whether a foreign object is present in the target image based on the number of similar features comprises:
comparing the number of similar feature points with a preset threshold;
when the number of the similar feature points is larger than or equal to a preset threshold value, judging that foreign matters exist in the target image;
and when the number of the similar characteristic points is smaller than a preset threshold value, judging that no foreign matter exists in the target image.
3. The method of claim 1, wherein matching the target image with a preset standard image and determining the number of similar features in the two images comprises:
target image area calibration: comparing the target image with a preset standard image, calibrating and cutting out an area in the target image, which is matched with a position to be detected in the preset standard image;
respectively carrying out feature detection on the position to be detected in the preset standard image and the region cut out from the target image by adopting an ORB feature algorithm so as to respectively obtain feature points of the position to be detected in the preset standard image and the region cut out from the target image;
matching the feature points in the two images by adopting a minimum distance algorithm to determine the number of similar features in the two images;
the formula of the minimum distance algorithm is as follows:
f1 is a feature point detected at a position to be detected in the preset standard image, and F2 is a feature point detected in a cut-out region in the target image.
4. The method according to claim 3, wherein the comparing the target image with a preset standard image, calibrating and cutting out an area in the target image, which is matched with a position to be detected in the preset standard image, comprises:
respectively detecting feature points in the preset standard image and the target image by adopting an ORB feature algorithm;
matching the feature points in the preset standard image and the target image by adopting a minimum distance algorithm;
determining a single mapping matrix between the preset standard image and the target image according to the matched feature points, and adjusting the target image shot from different visual angles to the angle of the same visual angle as the preset standard image by using the single mapping matrix;
determining four corner coordinates in the target image according to the single mapping matrix and the four corner coordinates of the position to be detected in the preset standard image;
and calibrating and cutting out the area matched with the position to be detected in the preset standard image in the target image by using the coordinates of the four corner points in the target image.
5. The method according to claim 4, wherein the determining four corner coordinates in the target image according to the single mapping matrix and the four corner coordinates of the position to be detected in the preset standard image comprises:
according to the single mapping matrix and the coordinates of the four corner points of the position to be detected in the preset standard image, passing through
Respectively determining coordinates of four corner points in the target image;
wherein the content of the first and second substances,
representing the upper left corner coordinate or the lower right corner coordinate of the position to be detected in the preset standard image,
representing the upper left corner coordinate or the lower right corner coordinate in the target image,
representing the single mapping matrix.
6. The method of claim 2, wherein after determining that there is a foreign object in the target image, the method further comprises:
and marking the position of the foreign matter in the target image.
7. The method of claim 6, wherein the marking the location of the foreign object in the target image comprises:
respectively detecting feature points in the preset standard image and the target image by adopting an ORB feature algorithm;
removing the characteristic points matched with the preset standard image in the target image, and clustering the residual characteristic points in the target image;
finding out coordinates of four corner points of the edge in the cluster, and drawing the obtained coordinates of the four corner points on the target image in a bounding box mode to mark the position of the foreign matter in the target image.
8. The method of claim 7, wherein finding four corner coordinates of an edge in a cluster comprises:
and (4) sorting the coordinates of the clustered regions in a descending order to obtain the coordinates of the upper left corner and the coordinates of the lower right corner of the clustered regions.
9. A foreign object detection device of a high-voltage overhead line is characterized by comprising a memory and a processor, wherein the memory is used for storing a computer program; the computer program, when executed by the processor, implements a foreign object detection method for a high voltage overhead line according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111266402.2A CN114022763A (en) | 2021-10-28 | 2021-10-28 | Foreign matter detection method and device for high-voltage overhead line and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111266402.2A CN114022763A (en) | 2021-10-28 | 2021-10-28 | Foreign matter detection method and device for high-voltage overhead line and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114022763A true CN114022763A (en) | 2022-02-08 |
Family
ID=80058634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111266402.2A Pending CN114022763A (en) | 2021-10-28 | 2021-10-28 | Foreign matter detection method and device for high-voltage overhead line and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114022763A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117315515A (en) * | 2023-11-29 | 2023-12-29 | 深圳市大易电气实业有限公司 | Visual auxiliary inspection method and system for distribution line |
-
2021
- 2021-10-28 CN CN202111266402.2A patent/CN114022763A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117315515A (en) * | 2023-11-29 | 2023-12-29 | 深圳市大易电气实业有限公司 | Visual auxiliary inspection method and system for distribution line |
| CN117315515B (en) * | 2023-11-29 | 2024-03-15 | 深圳市大易电气实业有限公司 | Visual auxiliary inspection method and system for distribution line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705405B (en) | Target labeling method and device | |
| US8121400B2 (en) | Method of comparing similarity of 3D visual objects | |
| CN112102409B (en) | Target detection method, device, equipment and storage medium | |
| CN111582054B (en) | Point cloud data processing method and device and obstacle detection method and device | |
| CN108489996B (en) | Insulator defect detection method and system and terminal equipment | |
| CN108710913A (en) | A kind of switchgear presentation switch state automatic identification method based on deep learning | |
| CN105956632B (en) | A kind of method and apparatus detecting target | |
| CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
| CN109376580B (en) | Electric power tower component identification method based on deep learning | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| CN113970734B (en) | Method, device and equipment for removing snowfall noise points of road side multi-line laser radar | |
| CN110415296B (en) | Method for positioning rectangular electric device under shadow illumination | |
| CN113592839B (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
| CN111337789A (en) | Method and system for detecting fault electrical element in high-voltage transmission line | |
| Somawirata et al. | Road detection based on the color space and cluster connecting | |
| CN114022763A (en) | Foreign matter detection method and device for high-voltage overhead line and readable storage medium | |
| JP2011165170A (en) | Object detection device and program | |
| CN114581419A (en) | Transformer insulating sleeve defect detection method, related equipment and readable storage medium | |
| CN111009003A (en) | Method, system and storage medium for correcting deviation of traffic signal lamp | |
| CN108520255B (en) | Infrared weak and small target detection method and device | |
| CN111104861B (en) | Method and apparatus for determining wire position and storage medium | |
| CN107843261B (en) | Method and system for positioning robot position based on laser scanning data | |
| CN110147695B (en) | Station signboard for bus station identification and bus station identification system | |
| CN111008951A (en) | Method for calculating opening and closing angle of split type disconnecting link based on positioning identification | |
| CN115439319A (en) | Exposed detection method for electric slide wire protection device |
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 |