Defect adjustment method, device, equipment, storage medium and product for tower image

Abstract

The present application belongs to the field of image processing technology, and discloses a method, device, equipment, storage medium and product for adjusting defects of a pole tower image. The present application can obtain the matching area of ​​the initial partial image in the initial full image by performing image matching on the initial full image and the initial partial image, and then adjust the initial full image and each initial partial image respectively according to the full defect pixel point range and the local defect pixel point range, and can increase the initial full defects on the initial full image, and deduplicate the initial local defects on the initial partial image, and can effectively adjust the image defects in the pole tower inspection process.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment, storage medium and product for adjusting defects of a tower image. Background Art

[0002] With the continuous expansion of the scale and complexity of power networks, the safe and stable operation of power lines is crucial to ensuring social and economic activities. As an important part of power lines, the status of power towers is directly related to the safety and reliability of the power grid. The traditional tower inspection method mainly relies on manual on-site inspection, which is not only time-consuming and labor-intensive, but also has certain safety risks, especially in complex terrain or harsh climate. In recent years, the development of drone technology has provided a new solution for power tower inspection. Equipped with high-resolution cameras and other sensors, drones can efficiently complete the task of comprehensive inspection of towers. However, the number of photos taken by drones is huge, and there may be a large number of repeated defective images, which brings challenges to subsequent data processing. Therefore, how to effectively adjust the image defects during the tower inspection process has become an urgent problem to be solved. Summary of the invention

[0003] The main purpose of this application is to provide a method, device, equipment, storage medium and product for adjusting defects of a pole tower image, aiming to solve the technical problem of how to effectively adjust image defects during the pole tower inspection process.

[0004] To achieve the above object, the present application provides a method for adjusting defects of a pole tower image, and the method for adjusting defects of a pole tower image comprises the following steps:

[0005] Collecting an initial full-view image and multiple initial local images corresponding to the tower;

[0006] For each initial partial image, performing image matching between the initial full image and the initial partial image to obtain a matching area of ​​the initial partial image in the initial full image;

[0007] Determine a global defect pixel point range of an initial global defect in the matching area, and determine a local defect pixel point range of an initial local defect corresponding to the initial local image;

[0008] The initial overall image and each initial local image are adjusted respectively according to the overall defect pixel point range and the local defect pixel point range to obtain a target overall image and multiple target local images.

[0009] Optionally, for each initial partial image, the step of performing image matching on the initial full image and the initial partial image to obtain a matching area of ​​the initial partial image in the initial full image specifically includes:

[0010] For each initial partial image, determine the initial full picture key features and full picture feature descriptors corresponding to the initial full picture image by a feature detection algorithm, and determine the initial local key features and local feature descriptors corresponding to the initial partial image;

[0011] Based on the global feature descriptor and the local feature descriptor, determining an initial feature mapping relationship between the initial global key feature and the initial local key feature by a fast nearest neighbor search bag algorithm;

[0012] The initial full image is matched with the initial partial image according to the initial feature mapping relationship to obtain a matching area of ​​the initial partial image in the initial full image.

[0013] Optionally, the step of matching the initial full image with the initial partial image according to the initial feature mapping relationship to obtain a matching area of ​​the initial partial image in the initial full image specifically includes:

[0014] Determine whether the initial feature mapping relationship is valid by using a random sample consensus algorithm;

[0015] Filtering a valid target feature mapping relationship from the initial feature mapping relationship according to the judgment result;

[0016] A matching area of ​​the initial local image in the initial full image is determined according to the target feature mapping relationship.

[0017] Optionally, the step of judging whether the initial feature mapping relationship is valid by using a random sample consensus algorithm specifically includes:

[0018] Determine the feature similarity between the initial global key feature and the initial local key feature in the initial feature mapping relationship by a random sample consensus algorithm;

[0019] When the feature similarity is greater than a first preset threshold, determining that the initial feature mapping relationship is valid;

[0020] When the feature similarity is less than or equal to the first preset threshold, it is determined that the initial feature mapping relationship is invalid.

[0021] Optionally, the step of determining a matching area of ​​the initial local image in the initial full image according to the target feature mapping relationship specifically includes:

[0022] Determine the target overall key features corresponding to the target feature mapping relationship;

[0023] The pixel area of ​​the target overall key feature in the initial overall image is determined, and a matching area is determined according to the pixel area.

[0024] Optionally, the step of adjusting the initial full image and each initial local image respectively according to the full defect pixel range and the local defect pixel range to obtain a target full image and a plurality of target local images specifically includes:

[0025] Matching the global defect pixel point range and the local defect pixel point range to obtain a successfully matched target global defect pixel point range and a target local defect pixel point range;

[0026] Compare the target global defect pixel point range and the target local defect pixel point range to obtain a first range difference and a second range difference;

[0027] When the first range difference is greater than a second preset threshold or the second range difference is greater than a third preset threshold, adjusting the initial full image according to the corresponding initial local defect to obtain a target full image;

[0028] When the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, establishing a defect mapping relationship between the initial global defect and the initial local defect;

[0029] The initial local images are adjusted respectively according to the defect mapping relationship to obtain a target local image.

[0030] Optionally, the step of adjusting each initial local image according to the defect mapping relationship to obtain a plurality of target local images specifically includes:

[0031] Determine a target overall defect corresponding to the target overall image, and determine a first local defect among initial local defects corresponding to the target overall defect according to the defect mapping relationship;

[0032] Synchronously numbering the target global defect and the first local defect to obtain the same global defect number and local defect number;

[0033] Determine a repeated local defect according to a repeated number in the local defect number;

[0034] The initial local defects corresponding to each initial local image are deduplicated according to the repeated local defects to obtain a plurality of target local images.

[0035] Optionally, after the step of adjusting the initial full image and each initial local image according to the full defect pixel range and the local defect pixel range to obtain a target full image and a plurality of target local images, the step further includes:

[0036] Performing edge detection on the target full-view image to obtain an edge detection result;

[0037] For each target overall defect, determining a relative height of the target overall defect relative to the tower according to the edge detection result;

[0038] Determine the difference in relative heights corresponding to any two target overall defects based on the relative heights;

[0039] When the relative height difference is less than a fourth preset threshold, a similarity detection is performed on the corresponding target overall defect, and a repeated overall defect is determined according to the similarity detection result;

[0040] The target overall defects in the target overall image are deduplicated according to the repeated overall defects to obtain a deduplicated overall image.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a defect adjustment device for a pole tower image, and the defect adjustment device for a pole tower image comprises:

[0042] An image acquisition module, used for acquiring an initial full-view image and multiple initial local images corresponding to the tower;

[0043] An image matching module is used to perform image matching between the initial full image and the initial partial image for each initial partial image, so as to obtain a matching area of ​​the initial partial image in the initial full image;

[0044] A range determination module, used to determine the global defect pixel point range of the initial global defect in the matching area, and determine the local defect pixel point range of the initial local defect corresponding to the initial local image;

[0045] The defect adjustment module is used to adjust the initial full image and each initial local image according to the full defect pixel point range and the local defect pixel point range to obtain a target full image and multiple target local images.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a defect adjustment device for a pole tower image, and the defect adjustment device for a pole tower image includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the defect adjustment method for a pole tower image as described above.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the defect adjustment method of the tower image as described above are implemented.

[0048] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the defect adjustment method of the tower image as described above are implemented.

[0049] The present application collects an initial full image and multiple initial local images corresponding to the pole tower, and for each initial local image, performs image matching on the initial full image and the initial local image to obtain a matching area of ​​the initial local image in the initial full image, and then determines the full defect pixel point range of the initial full defect in the matching area in the matching area, and determines the local defect pixel point range of the initial local defect corresponding to the initial local image, and then adjusts the initial full image and each initial local image according to the full defect pixel point range and the local defect pixel point range to obtain a target full image and multiple target local images. The present application performs image matching on the initial full image and the initial local image to obtain a matching area of ​​the initial local image in the initial full image, and then adjusts the initial full image and each initial local image according to the full defect pixel point range and the local defect pixel point range, and can increase the initial full defects on the initial full image, deduplicate the initial local defects on the initial local image, and can effectively adjust the image defects during the pole tower inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 A schematic diagram of the flow chart of the first embodiment of the defect adjustment method of the tower image of the present application;

[0053] Figure 2 A schematic diagram of the flow chart of the second embodiment of the method for adjusting defects of a tower image of the present application;

[0054] Figure 3A schematic diagram of an initial local image corresponding to a pole tower according to an embodiment of a method for adjusting defects of a pole tower image of the present application;

[0055] Figure 4 A schematic diagram of an initial full-view image corresponding to a pole tower according to an embodiment of a method for adjusting defects of a pole tower image of the present application;

[0056] Figure 5 A schematic diagram of the flow chart of the third embodiment of the method for adjusting defects of a tower image of the present application;

[0057] Figure 6 A schematic flow chart of a fourth embodiment of a method for adjusting defects of a tower image of the present application;

[0058] Figure 7 This is a structural block diagram of the first embodiment of the defect adjustment device for tower images of the present application;

[0059] Figure 8 It is a structural schematic diagram of a defect adjustment device for a tower image in a hardware operating environment involved in an embodiment of the present application.

[0060] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0062] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0063] It should be noted that the execution subject of the present application may be a computing service device with data processing, network communication and program running functions, such as a computer, or an electronic device capable of realizing the above functions, a defect adjustment device for a pole tower image, etc. The following takes the defect adjustment device for a pole tower image as an example to illustrate this embodiment and the following embodiments.

[0064] Based on this, the present application embodiment provides a method for adjusting defects of a tower image, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the defect adjustment method for a tower image of the present application.

[0065] In this embodiment, the defect adjustment method of the tower image includes the following steps:

[0066] Step S10: collecting an initial full-view image and a plurality of initial partial images corresponding to the tower.

[0067] It is understandable that the route is composed of waypoints. A pole tower is a waypoint. At a pole tower, the pole tower may be circled or flown up and down according to a certain trajectory. These are all completed within a waypoint. In this embodiment, the drone can shoot the initial full-view image and multiple initial partial images corresponding to the pole tower at each waypoint. The initial full-view image refers to an image that captures all parts of the pole tower or most of the upper part of the pole tower. The initial partial image refers to an image captured by capturing a local part of the pole tower, such as the tower head, insulator, main pole, cross arm, or main pole. The initial partial image only captures part of the structure of the pole tower. For example, the drone arrives at waypoint 1 and starts to capture the initial full-view image corresponding to the pole tower according to the default zoom factor. The next three images begin to adjust the zoom factor to capture the initial partial images corresponding to the pole tower. The zoom factor corresponding to each initial partial image may be different. The pole tower image and the waypoint name can be bound according to whether the zoom is changed, such as waypoint 1-initial full-view image and waypoint 2-initial partial image. For each tower, an initial full-view image and multiple initial partial images may be collected by a drone, and this embodiment does not impose a specific limit on the number of partial images.

[0068] Step S20: for each initial partial image, image matching is performed between the initial full image and the initial partial image to obtain a matching area of ​​the initial partial image in the initial full image.

[0069] It should be understood that for each initial partial image, image matching can be performed between the initial full image and the initial partial image to obtain a matching area of ​​the initial partial image in the full image, that is, the position of the initial partial image in the initial full image.

[0070] Step S30: determining a global defect pixel point range of the initial global defect in the matching area, and determining a local defect pixel point range of the initial local defect corresponding to the initial local image.

[0071] It is understandable that the initial global defects and the initial local defects corresponding to the initial local image in the matching area can be determined. Specifically, the initial global defects and the initial local defects can be determined through deep learning technology, such as the target detection algorithm, namely the YOLO algorithm.

[0072] It should be understood that the position of the initial global defect in the matching area can be determined and converted into a global defect pixel point range. Specifically, for the matching area, a pixel point coordinate system is established with the upper left corner of the area as the origin to obtain the global pixel point range corresponding to the initial global defect. The local defect pixel point range of the initial local defect in the local image can also be determined.

[0073] Step S40: adjusting the initial overall image and each initial local image according to the overall defect pixel range and the local defect pixel range to obtain a target overall image and multiple target local images.

[0074] It should be understood that if there are multiple initial global defects in the matching area, after obtaining the global defect pixel point range corresponding to the initial global defect and the local defect pixel point range corresponding to the initial local defect, the global defect pixel point range and the local defect pixel point range are matched to determine the successfully matched target global defect pixel point range and target local defect pixel point range, and then the initial global image and the initial local image are adjusted respectively according to the target global defect pixel point range and the target local defect pixel point range.

[0075] It can be understood that this embodiment can adjust the initial full picture image and each initial local image separately according to the full picture defect pixel point range and the local defect pixel point range. Specifically, the initial full picture defect on the initial full picture image and the initial local defect on the initial local image can be adjusted. The full picture defect pixel point range and the local defect pixel point range can be compared to determine whether the two ranges are similar. If so, the corresponding initial full picture defect and initial local defect can be considered to be the same defect. If they are not similar, the initial full picture defect can be added and marked on the full picture image to obtain the target full picture defect. All initial local defects can also be deduplicated to avoid repeated defects in the obtained target local defects.

[0076] This embodiment collects an initial full-view image and multiple initial local images corresponding to the pole tower, and for each initial local image, performs image matching on the initial full-view image and the initial local image to obtain a matching area of ​​the initial local image in the initial full-view image, and then determines the full-view defect pixel point range of the initial full-view defect in the matching area, and determines the local defect pixel point range of the initial local defect corresponding to the initial local image, and then adjusts the initial full-view image and each initial local image according to the full-view defect pixel point range and the local defect pixel point range to obtain a target full-view image and multiple target local images. This embodiment performs image matching on the initial full-view image and the initial local image to obtain a matching area of ​​the initial local image in the initial full-view image, and then adjusts the initial full-view image and each initial local image according to the full-view defect pixel point range and the local defect pixel point range, and can increase the initial full-view defects on the initial full-view image, and deduplicate the initial local defects on the initial local image, and can effectively adjust the image defects during the inspection of the pole tower.

[0077] refer to Figure 2 , Figure 2This is a flow chart of the second embodiment of the defect adjustment method for a tower image of the present application.

[0078] Based on the above first embodiment, in this embodiment, step S20 includes:

[0079] Step S201: for each initial partial image, determine the initial full key features and full feature descriptors corresponding to the initial full image through a feature detection algorithm, and determine the initial local key features and local feature descriptors corresponding to the partial image.

[0080] It is understandable that for a certain tower, an initial full-view image and multiple initial local images can be collected at the same waypoint. For each initial local image, since it is taken at the same waypoint, the initial full-view key features and full-view feature descriptors corresponding to the full-view image can be determined by a feature detection algorithm (Scale-Invariant Feature Transform, SIFT), and the initial local key features and local feature descriptors corresponding to the local image can be determined.

[0081] Furthermore, in order to accurately obtain the global feature descriptor and the local feature descriptor, in this embodiment, the step S201 includes: for each initial local image, graying the initial global image and the initial local image respectively to obtain a grayscale global image and a grayscale local image; determining the initial global key features corresponding to the grayscale global image through a feature detection algorithm, and determining the global feature descriptor corresponding to the initial global key features; determining the initial local key features corresponding to the grayscale local image through a feature detection algorithm, and determining the local feature descriptor corresponding to the initial local key features.

[0082] It should be understood that the initial full image and each initial local image can be grayed out to obtain a gray full image and a gray local image. Then, the initial full key features corresponding to the gray full image are extracted by the SIFT feature detection algorithm, and SIFT descriptors, i.e., full feature descriptors, are generated for each initial full key feature. Similarly, the initial local key features corresponding to the gray local image can also be extracted by the SIFT feature detection algorithm, and SIFT descriptors, i.e., local feature descriptors, are generated for each initial local key feature. The initial full key features include the key features of each part of the tower, and the initial local key features refer to the key features of the local parts of the tower included in the initial local image. The number of features of the initial full key features may be different from the number of features of the initial local key features, and the magnification scales corresponding to the initial full key features and the initial local key features may also be different. For example, the main pole length of the initial full key feature may be different from the main pole length of the initial local key feature.

[0083] Step S202: Based on the global feature descriptor and the local feature descriptor, an initial feature mapping relationship between the initial global key feature and the initial local key feature is determined by a fast nearest neighbor search bag algorithm.

[0084] It is understandable that the Fast Library for Approximate Nearest Neighbors (FLANN) algorithm can perform homography matching through the FLANN algorithm, and the homography of a plane is defined as a projection mapping from one plane to another plane. In this embodiment, based on the global feature descriptor and the local feature descriptor, the initial feature mapping relationship between the initial global key feature and the initial local key feature can be determined through the FLANN algorithm, that is, the global key feature corresponds to which local key feature. If there is no correspondence, the key features on the line between the initial global key features can be made to correspond to the key features on the line between the initial local key features.

[0085] Step S203: matching the initial full image with the initial partial image according to the initial feature mapping relationship to obtain a matching region of the initial partial image in the initial full image.

[0086] It should be understood that the initial full image and the initial partial image can be matched according to the initial feature mapping relationship to obtain the matching area of ​​the initial partial image in the initial full image, that is, the position of the initial partial image in the initial full image. Figure 3 and Figure 4 , Figure 3 This is a schematic diagram of an initial local image corresponding to a tower according to an embodiment of a method for adjusting defects of a tower image of the present application. Figure 4 This is a schematic diagram of an initial full-view image corresponding to a pole tower according to an embodiment of a method for adjusting defects of a pole tower image of the present application, Figure 4 The black box area 1 in the Figure 3 The matching area of ​​the initial partial image in the initial full image is shown, namely, the Matcher Area.

[0087] Furthermore, in order to accurately obtain the matching area of ​​the local image in the full image, in this embodiment, the step S203 includes: judging whether the initial feature mapping relationship is valid through a random sample consistency algorithm; screening a valid target feature mapping relationship from the initial feature mapping relationship according to the judgment result; and determining the matching area of ​​the initial local image in the initial full image according to the target feature mapping relationship.

[0088] It is understandable that the Random Sample Consensus (RANSAC) algorithm can determine whether the initial feature mapping relationship is valid, that is, determine whether the key features of the match in the initial mapping relationship are valid, and screen the valid target feature mapping relationship from the initial feature mapping relationship according to the judgment result, and there are also abnormal feature mapping relationships. Then, the matching area of ​​the initial local image in the initial full image is obtained according to the target feature mapping relationship.

[0089] Furthermore, in the present embodiment, the step of judging whether the initial feature mapping relationship is valid by means of a random sample consensus algorithm specifically includes: determining the feature similarity between the initial global key feature and the initial local key feature in the initial feature mapping relationship by means of a random sample consensus algorithm; when the feature similarity is greater than a first preset threshold, judging that the initial feature mapping relationship is valid; when the feature similarity is less than or equal to the first preset threshold, judging that the initial feature mapping relationship is invalid.

[0090] It should be understood that the feature similarity between the initial overall key features and the initial local key features, such as the feature similarity of line length, line angle, etc., can be calculated by the RANSAC algorithm. When the feature similarity is greater than a first preset threshold, the corresponding initial feature mapping relationship is determined to be valid; when the feature similarity is less than or equal to the first preset threshold, the corresponding initial feature mapping relationship is determined to be invalid. The first preset threshold is a pre-set threshold for making effective judgments on the initial feature mapping relationship. This embodiment does not limit the specific value.

[0091] Furthermore, in the present embodiment, the step of determining the matching area of ​​the initial local image in the initial full image according to the target feature mapping relationship specifically includes: determining the target full image key feature corresponding to the target feature mapping relationship; determining the pixel area of ​​the target full image key feature in the initial full image, and determining the matching area according to the pixel area.

[0092] It can be understood that the target full picture key feature corresponding to the target feature mapping relationship can be determined, and the target full picture key feature is a valid full picture key feature, and the position of the target full picture key feature in the initial full picture image is determined, that is, the pixel area, and then all pixel areas constitute the matching area in the initial full picture image.

[0093] In this embodiment, for each initial partial image, the initial full picture key features and full picture feature descriptors corresponding to the initial full picture image are determined by a feature detection algorithm, and the initial local key features and local feature descriptors corresponding to the initial partial image are determined, and then based on the full picture feature descriptors and the local feature descriptors, the initial feature mapping relationship between the initial full picture key features and the initial local key features is determined by a fast nearest neighbor search bag algorithm, and then the initial full picture image is matched with the initial partial image according to the initial feature mapping relationship to obtain the matching area of ​​the initial partial image in the initial full picture image. In this embodiment, for each initial partial image, the initial full picture image is matched with the initial partial image according to the initial feature mapping relationship to obtain the matching area of ​​the initial partial image in the initial full picture image, and the position of the initial partial image in the initial full picture image can be accurately determined.

[0094] refer to Figure 5 , Figure 5 This is a flow chart of the third embodiment of the method for adjusting defects of a tower image of the present application.

[0095] Based on the above embodiments, in this embodiment, step S40 includes:

[0096] Step S401: matching the global defect pixel point range and the local defect pixel point range to obtain a successfully matched target global defect pixel point range and a target local defect pixel point range.

[0097] It should be understood that there may be multiple initial global defects and initial local defects, and there may also be multiple corresponding global defect pixel ranges and local defect pixel ranges. At this time, the global defect pixel range and the local defect pixel range can be matched, that is, the initial global defect and the initial local defect are matched to obtain a successfully matched target global defect pixel range and a target local defect pixel range, that is, the global defect corresponding to the target global defect pixel range corresponds to the local defect corresponding to the target local defect pixel range.

[0098] Step S402: Compare the target global defect pixel range and the target local defect pixel range to obtain a first range difference and a second range difference.

[0099] It is understandable that the target global defect pixel range and the target local defect pixel range can be compared to obtain a first range difference and a second range difference. For example, if the target global defect pixel range is (3,1) and the target local defect pixel range is (3,1.1), then the first range difference is 0 and the second range difference is 0.1.

[0100] Step S403: When the first range difference is greater than a second preset threshold or the second range difference is greater than a third preset threshold, the initial full image is adjusted according to the corresponding initial local defect to obtain a target full image.

[0101] It should be understood that when the first range difference is greater than the second preset threshold or the second range difference is greater than the third preset threshold, it means that the initial full picture defect on the initial full picture image does not correspond to the initial local defect on the initial local image, and is identified as a new defect, that is, it is considered that the initial local defect on the local image is not marked on the full picture image. At this time, the initial full picture defect on the initial full picture image can be adjusted according to the non-corresponding initial local defect, and specifically, a corresponding mark can be made on the full picture image to obtain the target full picture image. The second preset threshold and the third preset threshold are preset thresholds for range judgment, and this embodiment does not limit the specific values.

[0102] Step S404: when the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, a defect mapping relationship between the initial global defect and the initial local defect is established.

[0103] It can be understood that when the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, it is determined that there is a corresponding relationship between the initial overall defect and the initial local defect. Therefore, a defect mapping relationship between the initial overall defect and the initial local defect that meets the above requirements can be constructed.

[0104] Step S405: adjusting the initial local images respectively according to the defect mapping relationship to obtain a target local image.

[0105] Furthermore, in order to effectively adjust the initial local image, in this embodiment, the step S405 includes: determining the target overall defect corresponding to the target overall image, and determining the first local defect in the initial local defects corresponding to the target overall defect according to the defect mapping relationship; synchronously numbering the target overall defect and the first local defect to obtain the same overall defect number and local defect number; determining repeated local defects according to repeated numbers in the local defect numbers; and deduplicating the initial local defects corresponding to each initial local image according to the repeated local defects to obtain multiple target local images.

[0106] It should be understood that all target overall defects contained in the target overall image can be determined, and then the first local defect in the initial local defects corresponding to the target overall defect can be determined according to the defect mapping relationship, that is, the first local defect corresponding to the target overall defect is determined, and these two defects correspond one to one in the defect mapping relationship.

[0107] It is understandable that in this embodiment, all target overall defects on the target overall image may be numbered in sequence, such as 1, 2, 3, etc. At this time, the corresponding first local defects may also be numbered synchronously, and the two numbers are consistent. For example, the overall defect number 1 corresponds to the first local defect in the first local image and the first local defect in the second local image, and the two first local defects may be numbered 1.

[0108] In the specific implementation, repeated local defects can be determined according to the repeated numbers in the local defect numbers. For example, the pole tower corresponds to three local images. The first local image contains initial local defects 1, 2, and 3, the second local image contains initial local defects 2, 3, and 4, and the third local image contains initial local defects 3, 4, and 5. At this time, the initial local defects 2, 3, and 4 can be identified as repeated defects, and the repeated defects can be deduplicated. Specifically, the initial local defect 3 in the second local image and the third local image can be directly deleted, or other methods can be used to deduplicate and obtain multiple target local images. Finally, only the full image and one local image are retained for each defect number. The local image is convenient for later observation of defects, thereby ensuring that the defects under each waypoint are reflected in the full image and have corresponding local images for easy viewing.

[0109] In this embodiment, the target global defect pixel range and the target local defect pixel range are matched, and then the target global defect pixel range and the target local defect pixel range are compared to obtain a first range difference and a second range difference. When the first range difference is greater than the second preset threshold or the second range difference is greater than the third preset threshold, the initial global image is adjusted according to the corresponding initial local defect to obtain the target global image. When the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, a defect mapping relationship between the initial global defect and the initial local defect is established; and each initial local image is adjusted according to the defect mapping relationship to obtain the target local image. In this embodiment, the target global defect pixel range and the target local defect pixel range are compared, and it is determined whether the initial global defect needs to be added or the initial local defect needs to be deduplicated according to the first range difference and the second range difference, so as to accurately and effectively adjust the image defects and obtain the target global image and multiple target local images.

[0110] refer to Figure 6 , Figure 6 This is a flow chart of a fourth embodiment of the method for adjusting defects of a tower image of the present application.

[0111] Based on the above embodiments, in this embodiment, after step S40, the following steps are further included:

[0112] Step S50: performing edge detection on the target full-view image to obtain an edge detection result.

[0113] It is understandable that, for the target full-view image corresponding to the pole tower collected at each waypoint, Gaussian blur can be used to perform noise reduction processing on the target full-view image to obtain a noise-reduced full-view image.

[0114] It should be understood that the Canny algorithm can be used to perform edge detection on the denoised full image to obtain an edge detection result.

[0115] Step S60: for each target overall defect, determine the relative height of the target overall defect with respect to the tower according to the edge detection result.

[0116] It can be understood that the target full-view image corresponding to a certain tower may contain multiple target full-view defects. For each target full-view defect, the relative height of the target full-view defect relative to the tower can be determined based on the edge detection result. The relative height can be the height between the target full-view defect and the bottom of the tower, or the height between the target full-view defect and the top of the tower. Specifically, the height between the upper left corner of the target full-view defect and the bottom of the tower can be used as the relative height.

[0117] Step S70: determining the difference in relative heights corresponding to any two target overall defects according to the relative heights.

[0118] It should be understood that any two target overall defects can be selected from all target overall defects, and the difference in relative heights corresponding to the two target overall defects can be calculated as the relative height difference. When the relative height difference is greater than or equal to the fourth preset threshold, the corresponding two target overall defects can be determined to be different defects, and no processing is required. This can effectively reduce the possibility of some scenarios, such as two bird nests in different locations, being identified as the same defect.

[0119] Step S80: When the relative height difference is less than a fourth preset threshold, a similarity detection is performed on the corresponding target overall defect, and a repeated overall defect is determined according to the similarity detection result.

[0120] It is understandable that when the difference in relative height is less than the fourth preset threshold, the corresponding two target full-view defects can be tested for similarity. Specifically, the similarity test can be performed using a structural similarity algorithm (SSIM) to obtain an SSIM value. The SSIM value ranges from -1 to 1. The closer the value is to 1, the higher the similarity. If the SSIM value exceeds the specified threshold, it is identified as a repeated full-view defect.

[0121] Step S90: Deduplication of target full-view defects in the target full-view image is performed according to the repeated full-view defects to obtain a full-view image after deduplication.

[0122] In a specific implementation, any defect annotation and the corresponding local image on the corresponding target full-image are removed according to the technology and repeated full-image defects to obtain a deduplicated full-image image.

[0123] This embodiment performs edge detection on the target full-view image to obtain edge detection results, and for each target full-view defect, determines the relative height of the target full-view defect relative to the pole tower according to the edge detection result, and then determines the difference in relative heights corresponding to any two target full-view defects according to the relative heights. When the difference in relative heights is less than a fourth preset threshold, similarity detection is performed on the corresponding target full-view defects, and repeated full-view defects are determined according to the similarity detection results, and then the target full-view defects in the target full-view image are deduplicated according to the repeated full-view defects to obtain a deduplicated full-view image. This embodiment performs edge detection on each target full-view defect, determines the relative height of the target full-view defect relative to the pole tower according to the edge detection result, and then deduplicates the target full-view defects in the target full-view image according to the relative height, which can effectively deduplicate repeated defects in the target full-view image, improve the accuracy of defect deduplication, and obtain an accurate deduplicated full-view image.

[0124] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the defect adjustment device for tower images of the present application.

[0125] like Figure 7 As shown, the defect adjustment device for the tower image proposed in the embodiment of the present application includes:

[0126] An image acquisition module 10 is used to acquire an initial full-view image and a plurality of initial partial images corresponding to the tower;

[0127] An image matching module 20 is used to perform image matching between the initial full image and the initial partial image for each initial partial image, so as to obtain a matching area of ​​the initial partial image in the initial full image;

[0128] A range determination module 30 is used to determine the global defect pixel point range of the initial global defect in the matching area, and determine the local defect pixel point range of the initial local defect corresponding to the initial local image;

[0129] The defect adjustment module 40 is used to adjust the initial full image and each initial local image according to the full defect pixel range and the local defect pixel range to obtain a target full image and multiple target local images.

[0130] This embodiment collects an initial full-view image and multiple initial local images corresponding to the pole tower, and for each initial local image, performs image matching on the initial full-view image and the initial local image to obtain a matching area of ​​the initial local image in the initial full-view image, and then determines the full-view defect pixel point range of the initial full-view defect in the matching area, and determines the local defect pixel point range of the initial local defect corresponding to the initial local image, and then adjusts the initial full-view image and each initial local image according to the full-view defect pixel point range and the local defect pixel point range to obtain a target full-view image and multiple target local images. This embodiment performs image matching on the initial full-view image and the initial local image to obtain a matching area of ​​the initial local image in the initial full-view image, and then adjusts the initial full-view image and each initial local image according to the full-view defect pixel point range and the local defect pixel point range, and can increase the initial full-view defects on the initial full-view image, and deduplicate the initial local defects on the initial local image, and can effectively adjust the image defects during the inspection of the pole tower.

[0131] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present application. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0132] In addition, for technical details not fully described in this embodiment, reference can be made to the defect adjustment method for the tower image provided in any embodiment of the present application, which will not be repeated here.

[0133] Based on the first embodiment of the defect adjustment device for the pole tower image of the present application, a second embodiment of the defect adjustment device for the pole tower image of the present application is proposed.

[0134] In this embodiment, the image matching module 20 is further used to determine, for each initial local image, the initial full picture key features and full picture feature descriptors corresponding to the initial full picture image through a feature detection algorithm, and determine the initial local key features and local feature descriptors corresponding to the initial local image; based on the full picture feature descriptors and the local feature descriptors, determine the initial feature mapping relationship between the initial full picture key features and the initial local key features through a fast nearest neighbor search bag algorithm; match the initial full picture image with the initial local image according to the initial feature mapping relationship, and obtain the matching area of ​​the initial local image in the initial full picture image.

[0135] Furthermore, the image matching module 20 is also used to determine whether the initial feature mapping relationship is valid through a random sample consistency algorithm; screen a valid target feature mapping relationship from the initial feature mapping relationship based on the judgment result; and determine the matching area of ​​the initial local image in the initial full image based on the target feature mapping relationship.

[0136] Furthermore, the image matching module 20 is also used to determine the feature similarity between the initial overall key feature and the initial local key feature in the initial feature mapping relationship through a random sample consistency algorithm; when the feature similarity is greater than a first preset threshold, the initial feature mapping relationship is determined to be valid; when the feature similarity is less than or equal to the first preset threshold, the initial feature mapping relationship is determined to be invalid.

[0137] Furthermore, the image matching module 20 is also used to determine the target overall key feature corresponding to the target feature mapping relationship; determine the pixel area of ​​the target overall key feature in the initial overall image, and determine the matching area according to the pixel area.

[0138] Furthermore, the defect adjustment module 40 is also used to match the global defect pixel range and the local defect pixel range to obtain a successfully matched target global defect pixel range and a target local defect pixel range; compare the target global defect pixel range and the target local defect pixel range to obtain a first range difference and a second range difference; when the first range difference is greater than a second preset threshold or the second range difference is greater than a third preset threshold, adjust the initial global image according to the corresponding initial local defect to obtain a target global image; when the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, establish a defect mapping relationship between the initial global defect and the initial local defect; and adjust each initial local image according to the defect mapping relationship to obtain a target local image.

[0139] Furthermore, the defect adjustment module 40 is also used to determine the target overall defect corresponding to the target overall image, determine the first local defect in the initial local defects corresponding to the target overall defect according to the defect mapping relationship; synchronously number the target overall defect and the first local defect to obtain the same overall defect number and local defect number; determine repeated local defects according to repeated numbers in the local defect numbers; and deduplicate the initial local defects corresponding to each initial local image according to the repeated local defects to obtain multiple target local images.

[0140] Furthermore, the defect adjustment module 40 is also used to perform edge detection on the target full-view image to obtain edge detection results; for each target full-view defect, determine the relative height of the target full-view defect relative to the pole tower according to the edge detection result; determine the difference in relative heights corresponding to any two target full-view defects according to the relative heights; when the difference in relative heights is less than a fourth preset threshold, perform similarity detection on the corresponding target full-view defects, and determine repeated full-view defects according to the similarity detection results; deduplicate the target full-view defects in the target full-view image according to the repeated full-view defects to obtain a deduplicated full-view image.

[0141] Other embodiments or specific implementations of the defect adjustment device for tower images of the present application can refer to the above-mentioned method embodiments and will not be described in detail here.

[0142] The present application provides a defect adjustment device for a pole tower image, the defect adjustment device for a pole tower image comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the defect adjustment method for the pole tower image in the above-mentioned embodiment 1.

[0143] Reference below Figure 8 , which shows a schematic diagram of the structure of a defect adjustment device for a pole tower image suitable for implementing the embodiment of the present application. The defect adjustment device for a pole tower image in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The defect adjustment device for the tower image shown is only an example and should not bring any limitation to the function and scope of use of the embodiment of the present application.

[0144] like Figure 8As shown, the defect adjustment device for the pole tower image may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the defect adjustment device for the pole tower image are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the defect adjustment device for the pole tower image to communicate wirelessly or by wire with other devices to exchange data. Although the defect adjustment device for the pole tower image with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0145] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0146] The defect adjustment device for pole tower images provided in the present application adopts the defect adjustment method for pole tower images in the above-mentioned embodiment, which can solve the technical problem of how to effectively adjust image defects during pole tower inspection. Compared with the prior art, the beneficial effects of the defect adjustment device for pole tower images provided in the present application are the same as the beneficial effects of the defect adjustment method for pole tower images provided in the above-mentioned embodiment, and other technical features in the defect adjustment device for pole tower images are the same as the features disclosed in the method of the previous embodiment, which will not be described in detail here.

[0147] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0148] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0149] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the defect adjustment method of the tower image in the above-mentioned embodiment.

[0150] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0151] The computer-readable storage medium may be included in the defect adjustment device for the pole tower image; or may exist independently without being assembled into the defect adjustment device for the pole tower image.

[0152] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the defect adjustment device for the pole tower image, the defect adjustment device for the pole tower image: collects an initial full-view image and multiple initial local images corresponding to the pole tower; for each initial local image, performs image matching on the initial full-view image and the initial local image to obtain a matching area of ​​the initial local image in the initial full-view image; determines a full-view defect pixel point range of an initial full-view defect in the matching area in the matching area, and determines a local defect pixel point range of an initial local defect corresponding to the initial local image; and adjusts the initial full-view image and each initial local image respectively according to the full-view defect pixel point range and the local defect pixel point range to obtain a target full-view image and multiple target local images.

[0153] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0155] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0156] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for adjusting the defects of the tower image, and can solve the technical problem of how to effectively adjust the image defects during the tower inspection process. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the method for adjusting the defects of the tower image provided in the above-mentioned embodiment, and will not be repeated here.

[0157] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for adjusting defects of a tower image when executed by a processor.

[0158] The computer program product provided in this application can solve the technical problem of how to effectively adjust the defects of the image during the inspection of the tower. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the defect adjustment method of the tower image provided in the above embodiment, which will not be repeated here.

[0159] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for adjusting defects of a tower image, characterized in that: The defect adjustment method of the tower image comprises the following steps: Collecting an initial full-view image and multiple initial local images corresponding to the tower; For each initial partial image, performing image matching between the initial full image and the initial partial image to obtain a matching area of ​​the initial partial image in the initial full image; Determine a global defect pixel point range of an initial global defect in the matching area, and determine a local defect pixel point range of an initial local defect corresponding to the initial local image; The initial overall image and each initial local image are adjusted respectively according to the overall defect pixel point range and the local defect pixel point range to obtain a target overall image and multiple target local images.

2. The method for adjusting the defects of a tower image according to claim 1, characterized in that: The step of performing image matching between the initial full image and the initial partial image for each initial partial image to obtain a matching area of ​​the initial partial image in the initial full image specifically includes: For each initial partial image, determine the initial full picture key features and full picture feature descriptors corresponding to the initial full picture image by a feature detection algorithm, and determine the initial local key features and local feature descriptors corresponding to the initial partial image; Based on the global feature descriptor and the local feature descriptor, determining an initial feature mapping relationship between the initial global key feature and the initial local key feature by a fast nearest neighbor search bag algorithm; The initial full image is matched with the initial partial image according to the initial feature mapping relationship to obtain a matching area of ​​the initial partial image in the initial full image.

3. The method for adjusting the defects of a tower image according to claim 2, characterized in that: The step of matching the initial full image with the initial partial image according to the initial feature mapping relationship to obtain a matching area of ​​the initial partial image in the initial full image specifically includes: Determine whether the initial feature mapping relationship is valid by using a random sample consensus algorithm; Filtering a valid target feature mapping relationship from the initial feature mapping relationship according to the judgment result; A matching area of ​​the initial local image in the initial full image is determined according to the target feature mapping relationship.

4. The method for adjusting the defects of a tower image according to claim 3, characterized in that: The step of judging whether the initial feature mapping relationship is valid by using a random sample consensus algorithm specifically includes: Determine the feature similarity between the initial global key feature and the initial local key feature in the initial feature mapping relationship by a random sample consensus algorithm; When the feature similarity is greater than a first preset threshold, determining that the initial feature mapping relationship is valid; When the feature similarity is less than or equal to the first preset threshold, it is determined that the initial feature mapping relationship is invalid.

5. The method for adjusting the defects of a tower image according to claim 3, characterized in that: The step of determining the matching area of ​​the initial local image in the initial full image according to the target feature mapping relationship specifically includes: Determine the target overall key features corresponding to the target feature mapping relationship; The pixel area of ​​the target overall key feature in the initial overall image is determined, and a matching area is determined according to the pixel area.

6. The method for adjusting the defects of a tower image according to claim 1, characterized in that: The step of adjusting the initial full image and each initial local image according to the full defect pixel range and the local defect pixel range to obtain a target full image and a plurality of target local images specifically includes: Matching the global defect pixel point range and the local defect pixel point range to obtain a successfully matched target global defect pixel point range and a target local defect pixel point range; Compare the target global defect pixel point range and the target local defect pixel point range to obtain a first range difference and a second range difference; When the first range difference is greater than a second preset threshold or the second range difference is greater than a third preset threshold, adjusting the initial full image according to the corresponding initial local defect to obtain a target full image; When the first range difference is less than or equal to the second preset threshold and the second range difference is less than or equal to the third preset threshold, establishing a defect mapping relationship between the initial global defect and the initial local defect; The initial local images are adjusted respectively according to the defect mapping relationship to obtain a target local image.

7. The method for adjusting the defects of a tower image according to claim 6, characterized in that: The step of adjusting each initial local image according to the defect mapping relationship to obtain a plurality of target local images specifically includes: Determine a target overall defect corresponding to the target overall image, and determine a first local defect among initial local defects corresponding to the target overall defect according to the defect mapping relationship; Synchronously numbering the target global defect and the first local defect to obtain the same global defect number and local defect number; Determine a repeated local defect according to a repeated number in the local defect number; The initial local defects corresponding to each initial local image are deduplicated according to the repeated local defects to obtain a plurality of target local images.

8. The method for adjusting the defects of a tower image according to any one of claims 1 to 7, characterized in that: After the step of adjusting the initial full image and each initial local image according to the full defect pixel range and the local defect pixel range to obtain a target full image and a plurality of target local images, the method further includes: Performing edge detection on the target full-view image to obtain an edge detection result; For each target overall defect, determining a relative height of the target overall defect relative to the tower according to the edge detection result; Determine the difference in relative heights corresponding to any two target overall defects based on the relative heights; When the relative height difference is less than a fourth preset threshold, a similarity detection is performed on the corresponding target overall defect, and a repeated overall defect is determined according to the similarity detection result; The target overall defects in the target overall image are deduplicated according to the repeated overall defects to obtain a deduplicated overall image.

9. A defect adjustment device for a tower image, characterized in that: The defect adjustment device of the tower image comprises: An image acquisition module, used for acquiring an initial full-view image and multiple initial local images corresponding to the tower; An image matching module is used to perform image matching between the initial full image and the initial partial image for each initial partial image, so as to obtain a matching area of ​​the initial partial image in the initial full image; A range determination module, used to determine the global defect pixel point range of the initial global defect in the matching area, and determine the local defect pixel point range of the initial local defect corresponding to the initial local image; The defect adjustment module is used to adjust the initial full image and each initial local image according to the full defect pixel point range and the local defect pixel point range to obtain a target full image and multiple target local images.

10. A defect adjustment device for a tower image, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for adjusting defects of a tower image according to any one of claims 1 to 8.

11. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for adjusting defects of a tower image according to any one of claims 1 to 8 are implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for adjusting defects of a tower image according to any one of claims 1 to 8 are implemented.

Images