A transmission line tower monitoring method and system

Abstract

The present application discloses a method and system for monitoring a transmission line tower, which involves power grid and image processing technology, including: pre-establishing standard contour data of various types of towers under multiple viewing angles; collecting image data of a target tower and extracting the current contour data of the target tower; determining multiple contour nodes in the contour data based on the extracted contour data; dividing the contour data into multiple sub-contours based on each contour node; splicing based on the corresponding standard contour data according to each segmented sub-contour; determining the corresponding contour boundary deviation in the splicing result based on the contour boundary between contour nodes that can form a line segment in each contour node, and executing an alarm when the deviation is greater than a preset threshold. The method of the present application can improve the monitoring efficiency of transmission line towers and reduce the labor input of workers.

Description

Technical Field

[0001] The present application relates to the field of power grid and image processing technology, and in particular to a method and system for monitoring transmission line towers. Background Art

[0002] With the annual growth of China's power grid users, more and more high-voltage lines are put into operation. Power companies spend a lot of manpower and material resources every year to operate, maintain and repair transmission towers. In view of the problems of high labor intensity, low efficiency and terrain restrictions of manual inspection, transmission tower inspection has become a direction that needs to be developed in the future.

[0003] In the prior art, transmission tower inspections are mainly performed by workers on a regular basis, or by manually collecting track and go-around data in a flight mode, or by point cloud scanning to collect tower data. However, these two methods are not only costly, but also inefficient. Summary of the invention

[0004] The embodiments of the present application provide a transmission line tower monitoring method and system, which are used to improve the monitoring efficiency of transmission line towers and reduce the labor input of workers.

[0005] The present application embodiment provides a transmission line tower monitoring method, comprising the following steps:

[0006] Pre-establish standard profile data of various types of towers at multiple viewing angles;

[0007] Collect image data of the target tower and extract current contour data of the target tower;

[0008] Based on the extracted contour data, determining a plurality of contour nodes in the contour data;

[0009] Based on each contour node, the contour data is divided into a plurality of sub-contours, wherein each sub-contour comprises a branch structure diverging from a corresponding contour node, and all sub-contours are combined to form a complete contour data;

[0010] According to each segmented sub-contour, splicing is performed based on corresponding standard contour data;

[0011] Based on the contour boundary between the contour nodes that can form a line segment in each contour node, the corresponding contour boundary deviation in the splicing result is determined, and an alarm is executed when the deviation is greater than a preset threshold.

[0012] Optionally, collecting image data of the target tower and extracting current contour data of the target tower include:

[0013] identifying a first pixel range of a target pole in the image data according to the histogram, and expanding the first pixel range, and,

[0014] Extracting a representative pixel range from the image data except the first pixel range;

[0015] Eliminate pixels belonging to the representative pixel range in the image data, and retain pixels in the expanded first pixel range;

[0016] For the remaining image data, the Sobel operator is used to calculate the gradient amplitude and direction to determine the gradient of the partial image data, so as to extract the current contour data of the target tower.

[0017] Optionally, based on the extracted contour data, determining a plurality of contour nodes in the contour data comprises:

[0018] Determine, according to the contour data, intersection nodes between contour lines and between extension lines of contour lines;

[0019] Based on any intersection node, the intersection nodes whose number of other intersection nodes within the specified pixel range of the any intersection node is greater than the specified number are determined as contour nodes; and

[0020] The node representative position of the outline node is determined according to the center area of ​​the graph within the outline area covered by each intersection node.

[0021] Optionally, based on each contour node, dividing the contour data into a plurality of sub-contours comprises:

[0022] Based on the determined contour nodes, determining the pixel length of the connecting rod structure between the contour nodes;

[0023] The contours of the connecting rod structure whose pixel length is shorter than the specified pixel length are not selected;

[0024] The segmentation point is determined according to the middle range of the pixel lengths of the remaining link structures of any determined contour node, so as to segment the contour data into a plurality of sub-contours and form a graphic structure diverging from any contour node.

[0025] Optionally, according to each segmented sub-contour, splicing based on corresponding standard contour data includes:

[0026] Selecting the standard contour closest to the image data perspective of the target tower from the established standard contour data under multiple perspectives;

[0027] Determine a reference connecting rod structure according to the selected standard profile, and determine a deviation relationship between the reference connecting rod structure and a corresponding structure in the profile data;

[0028] Perspective or scale the standard profile according to the deviation relationship so that the deviation between the reference connecting rod structure and the corresponding structure is within a preset deviation range;

[0029] The segmented sub-contours are spliced ​​according to the adjusted standard contour.

[0030] Optionally, according to the adjusted standard contour, splicing the segmented sub-contours comprises:

[0031] According to the node representative positions of two directly connected contour nodes, the sub-contour with the longest connecting rod structure or the sub-contour with the largest pixel area is determined as the starting position for splicing;

[0032] The sub-contours are spliced ​​based on the splicing starting position and the extension direction of the connecting rod structure.

[0033] Optionally, taking the contour boundary between contour nodes that can form a line segment in each contour node as a reference, determining the corresponding contour boundary deviation in the splicing result includes:

[0034] According to the node representative positions of two directly connected contour nodes, the corresponding connecting rod structure reference line is determined;

[0035] Based on the reference line and the segmentation position, the deviations from the contour boundaries of each splicing are calculated respectively.

[0036] Optionally, based on the reference line and the segmentation position, respectively calculating the deviations from each spliced ​​contour boundary includes:

[0037] Prioritize calculating the deviation between each trunk connecting rod structure and the reference line;

[0038] When the deviation between the main connecting rod structure and the reference line exceeds the preset threshold, an alarm is issued directly;

[0039] When the deviation between the main connecting rod structure and the reference line does not exceed the preset threshold, the angle difference between the branch connecting rod structure and the reference line is further calculated, and the calculated angle difference is compared with the corresponding angle reference, and an alarm is issued to the corresponding branch connecting rod structure according to the comparison result.

[0040] The embodiment of the present application further proposes a transmission line tower monitoring system, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the transmission line tower monitoring method as described above are implemented.

[0041] The solution of the present application establishes standard contour data and collects tower image data to perform matching based on the established standard contour data, thereby achieving stability monitoring of towers, improving the monitoring efficiency of transmission line towers, and reducing the labor input of workers.

[0042] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0044] Figure 1 The following is a schematic diagram of the basic process of the transmission line tower monitoring method of this embodiment. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] The present application embodiment provides a transmission line tower monitoring method, such as Figure 1 As shown, the following steps are included:

[0047] In step S101, standard outline data of various types of towers under multiple viewing angles are pre-established. In some embodiments, for a tower with a relatively large structure, multiple standard outline data may be established in partitions, with partial overlap between the partitions.

[0048] In step S102, the image data of the target tower is collected, and the current contour data of the target tower is extracted. In a specific example, a fixed image acquisition device can be set, or a drone can be used for patrolling. For the fixed image acquisition device, the acquisition can be performed directly. For the drone patrolling method, the acquisition angle of each standard contour data can be saved in advance, and the image can be collected in the corresponding angle range. After the required image is collected, the current contour data of the target tower is extracted.

[0049] In step S103, multiple contour nodes in the contour data are determined based on the extracted contour data. For example, for some slightly complex towers, which contain many components, multiple contour nodes in the contour data are further determined in this example, so as to be used as a benchmark in subsequent examples to monitor the contour.

[0050] In step S104, the contour data is divided into a plurality of sub-contours based on each contour node, wherein any sub-contour includes a branch structure diverging from a corresponding contour node, and all sub-contours are combined to form the complete contour data.

[0051] In step S105, each segmented sub-contour is spliced ​​based on the corresponding standard contour data.

[0052] In step S106, the contour boundary between the contour nodes that can form a line segment in each contour node is used as a reference to determine the corresponding contour boundary deviation in the splicing result, and when the deviation is greater than a preset threshold, an alarm is executed. For example, in some examples, there is a situation where the contour boundary deviation in the splicing result is greater than the set value, which may indicate that the tower is tilted or has local defects. In the specific example, the specific alarm position can be determined based on the splicing result, thereby facilitating review by the staff.

[0053] The embodiment of the present application utilizes image processing to timely detect and warn of relatively invisible tower defects, without the need for manual inspection. By establishing standard contour data and collecting tower image data to match based on the established standard contour data, the stability of the tower can be monitored, the monitoring efficiency of the transmission line tower can be improved, and the labor of workers can be reduced.

[0054] In some embodiments, collecting image data of a target tower and extracting current contour data of the target tower includes:

[0055] A first pixel range of a target pole in the image data is identified according to the histogram, and the first pixel range is expanded. Specifically, the pixel range of the pole identified by the histogram can be expanded to cover the pixels of the edge of the pole to the first pixel range, and when the boundary is unclear or partially contains similar pixels, the expansion can ensure complete coverage of the pole pixels.

[0056] Extracting a representative pixel range from the image data except the first pixel range. Specifically, the present application further extracts representative pixels from pixels outside the tower, such as sky, land, forest, and similar representative pixel ranges.

[0057] Pixels belonging to the representative pixel range in the image data are eliminated, and pixels in the expanded first pixel range are retained. Multiple rounds of elimination can further approximate the real tower pixels to achieve filtering effects, thereby reducing the amount of calculation for subsequent operations.

[0058] For the remaining image data, the Sobel operator is used to calculate the gradient amplitude and direction to determine the gradient of the partial image data, so as to extract the current contour data of the target tower. In the embodiment of the present application, for the remaining image, the Sobel operator is directly used to calculate the gradient amplitude and direction according to the characteristic that the color of the tower is generally uniform, which can improve the efficiency of the tower edge detection.

[0059] In some embodiments, based on the extracted contour data, determining a plurality of contour nodes in the contour data comprises:

[0060] According to the contour data, the intersection nodes between the contour lines and the extension lines of the contour lines are determined. In another specific example, for example, a pole tower includes many connecting rod structures, and nodes are formed between the connecting rod structures. In this application, the contour nodes are determined by determining the intersection nodes between the contour lines and the extension lines of the contour lines.

[0061] Based on any cross node, the cross nodes whose number of other cross nodes within the specified pixel range of any cross node is greater than the specified number are determined as contour nodes. This application is not based on a single cross node, and the positions of several cross nodes included in a certain image range are identified as contour nodes, so that multiple main contour nodes in the tower can be selected, and minor nodes such as those with only two connecting rods are discarded.

[0062] The node representative position of the outline node is determined according to the center area of ​​the graph within the outline area covered by each intersection node. In a specific example, for the selected main outline node, the node representative position is determined according to the center position of the area formed by each line and the outline according to the aforementioned outline lines and the extension lines of the outline lines.

[0063] In some embodiments, based on each contour node, segmenting the contour data into a plurality of sub-contours comprises:

[0064] Based on the determined contour nodes, the pixel length of the link structure between the contour nodes is determined.

[0065] The contours of the connecting rod structures whose pixel lengths are shorter than the specified pixel lengths are not selected, that is, for the secondary connecting rod structures, segmentation is not performed first. The secondary connecting rod structures can be reflected in the corresponding two sub-contours, so that the secondary connecting rod structures are spliced ​​twice in the subsequent splicing to realize the monitoring of the secondary connecting rods.

[0066] The segmentation point is determined according to the middle range of the pixel length of each connecting rod structure remaining in any determined contour node, so as to segment the contour data into multiple sub-contours and form a graphical structure diverging from any contour node. In the embodiment of the present application, the main connecting rod structure and nodes are focused on, and the contour data is segmented into multiple sub-contours. On the one hand, the amount of segmentation calculation can be reduced, and at the same time, the deviation of the main connecting rod structure can be calculated preferentially in subsequent examples to improve monitoring efficiency.

[0067] In some embodiments, according to each segmented sub-contour, splicing based on corresponding standard contour data includes:

[0068] The standard contour closest to the image data perspective of the target tower is selected from the standard contour data under the established multiple perspectives. In some embodiments, for a fixed image acquisition device, the corresponding standard contour is directly selected. For a complex tower containing multiple local images, the standard contour closest to the image data perspective of the target tower is selected.

[0069] The reference connecting rod structure is determined according to the selected standard profile, and the deviation relationship between the reference connecting rod structure and the corresponding structure in the profile data is determined. For example, the deviation between the reference connecting rod structure and the tower structure extending into the ground in the profile data can be determined based on the tower structure extending into the ground as the reference connecting rod structure, such as the angle deviation, the length and width deviation of the connecting rod, etc.

[0070] The standard profile is perspectively or scaled according to the deviation relationship so that the deviation between the reference connecting rod structure and the corresponding structure is within a preset deviation range. By adjusting the deviation from the reference connecting rod within the preset deviation range, the standard profile is adjusted together to eliminate the possible impact of the viewing angle deviation.

[0071] The segmented sub-contours are spliced ​​according to the adjusted standard contour.

[0072] In some embodiments, according to the adjusted standard contour, splicing the segmented sub-contours comprises:

[0073] According to the node representative positions of two directly connected contour nodes, the longest connecting rod structure or the sub-contour with the largest sub-contour pixel area is determined as the splicing starting position.

[0074] The sub-contours are spliced ​​based on the splicing starting position and the extension direction of the connecting rod structure.

[0075] In some embodiments, based on the contour boundary between contour nodes that can form a line segment in each contour node, determining the corresponding contour boundary deviation in the splicing result includes:

[0076] According to the node representative positions of two directly connected contour nodes, the corresponding connecting rod structure reference line is determined, for example, by taking the connection line between the two node representative positions as the reference line.

[0077] Based on the reference line and the segmentation position, the deviations from the contour boundaries of each splicing are calculated respectively.

[0078] In some embodiments, based on the reference line and the segmentation position, respectively calculating the deviations from each spliced ​​contour boundary includes:

[0079] Prioritize calculating the deviation between each trunk connecting rod structure and the reference line;

[0080] When the deviation between the trunk connecting rod structure and the reference line exceeds a preset threshold, an alarm is directly issued. In some embodiments, the preset threshold can be determined according to the deviation between the boundary of the standard profile and the reference line.

[0081] When the deviation between the main connecting rod structure and the reference line does not exceed the preset threshold, the angle difference between the branch connecting rod structure and the reference line is further calculated, and the calculated angle difference is compared with the corresponding angle reference, and the corresponding branch connecting rod structure is alarmed according to the comparison result. Through step-by-step detection, the monitoring efficiency of the tower is improved.

[0082] The solution of the present application establishes standard contour data and collects tower image data to perform matching based on the established standard contour data, thereby achieving stability monitoring of towers, improving the monitoring efficiency of transmission line towers, and reducing the labor input of workers.

[0083] The embodiment of the present application further proposes a transmission line tower monitoring system, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the transmission line tower monitoring method as described above are implemented.

[0084] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present disclosure with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. It is not limited to the examples described in this specification or during the implementation of this application, and its examples will be interpreted as non-exclusive.

[0085] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art may use other embodiments when reading the above description.

[0086] The above embodiments are merely exemplary embodiments of the present disclosure. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the essence and protection scope of the present disclosure, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present invention.

Claims

1. A method for monitoring a transmission line tower, characterized in that: The steps include: Pre-establish standard profile data of various types of towers at multiple viewing angles; Collect image data of the target tower and extract current contour data of the target tower; Based on the extracted contour data, determining a plurality of contour nodes in the contour data; Based on each contour node, the contour data is divided into a plurality of sub-contours, wherein each sub-contour comprises a branch structure diverging from a corresponding contour node, and all sub-contours are combined to form a complete contour data; According to each segmented sub-contour, splicing is performed based on corresponding standard contour data; Based on the contour boundary between the contour nodes that can form a line segment in each contour node, the corresponding contour boundary deviation in the splicing result is determined, and an alarm is executed when the deviation is greater than a preset threshold; Based on the contour boundary between the contour nodes that can form a line segment in each contour node, the corresponding contour boundary deviation in the splicing result is determined to include: According to the node representative positions of two directly connected contour nodes, the corresponding connecting rod structure reference line is determined; Based on the reference line and the segmentation position, the deviations from the contour boundaries of each splicing are calculated respectively.

2. The transmission line tower monitoring method according to claim 1, characterized in that: Collect the image data of the target tower and extract the current contour data of the target tower including: identifying a first pixel range of a target pole in the image data according to the histogram, and expanding the first pixel range, and, Extracting a representative pixel range from the image data except the first pixel range; Eliminate pixels belonging to the representative pixel range in the image data, and retain pixels in the expanded first pixel range; For the remaining image data, the Sobel operator is used to calculate the gradient amplitude and direction to determine the gradient of the partial image data, so as to extract the current contour data of the target tower.

3. The transmission line tower monitoring method according to claim 2, characterized in that: Based on the extracted contour data, determining a plurality of contour nodes in the contour data comprises: Determine, according to the contour data, intersection nodes between contour lines and between extension lines of contour lines; Based on any intersection node, the intersection nodes whose number of other intersection nodes within the specified pixel range of the any intersection node is greater than the specified number are determined as contour nodes; and The node representative position of the outline node is determined according to the center area of ​​the graph within the outline area covered by each intersection node.

4. The transmission line tower monitoring method according to claim 3, characterized in that: Based on each contour node, dividing the contour data into a plurality of sub-contours comprises: Based on the determined contour nodes, determining the pixel length of the connecting rod structure between the contour nodes; The contours of the connecting rod structure whose pixel length is shorter than the specified pixel length are not selected; The segmentation point is determined according to the middle range of the pixel lengths of the remaining link structures of any determined contour node, so as to segment the contour data into a plurality of sub-contours and form a graphic structure diverging from any contour node.

5. The transmission line tower monitoring method according to claim 3, characterized in that: According to the segmented sub-contours, splicing based on the corresponding standard contour data includes: Selecting the standard contour closest to the image data perspective of the target tower from the established standard contour data under multiple perspectives; Determine a reference connecting rod structure according to the selected standard profile, and determine a deviation relationship between the reference connecting rod structure and a corresponding structure in the profile data; Perspective or scale the standard profile according to the deviation relationship so that the deviation between the reference connecting rod structure and the corresponding structure is within a preset deviation range; The segmented sub-contours are spliced ​​according to the adjusted standard contour.

6. The transmission line tower monitoring method according to claim 5, characterized in that: According to the adjusted standard contour, splicing the segmented sub-contours comprises: According to the node representative positions of two directly connected contour nodes, the sub-contour with the longest connecting rod structure or the sub-contour with the largest pixel area is determined as the starting position for splicing; The sub-contours are spliced ​​based on the splicing starting position and the extension direction of the connecting rod structure.

7. The transmission line tower monitoring method according to claim 1, characterized in that: Based on the reference line and the segmentation position, respectively calculating the deviation from each spliced ​​contour boundary includes: Prioritize calculating the deviation between each trunk connecting rod structure and the reference line; When the deviation between the main connecting rod structure and the reference line exceeds the preset threshold, an alarm is issued directly; When the deviation between the main connecting rod structure and the reference line does not exceed the preset threshold, the angle difference between the branch connecting rod structure and the reference line is further calculated, and the calculated angle difference is compared with the corresponding angle reference, and an alarm is issued to the corresponding branch connecting rod structure according to the comparison result.

8. A transmission line tower monitoring system, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the transmission line tower monitoring method according to any one of claims 1 to 7 are implemented.

Images