Intelligent detection method, system and equipment based on survey and maintenance object and medium

Abstract

The invention provides an intelligent detection method, system and device based on a survey and maintenance object, and a medium. The method comprises the following steps: acquiring an image of the survey and maintenance object; carrying out distinguishability detection on the image to obtain an image with qualified distinguishability detection; determining an independent image in the survey and maintenance object after the discernibility detection is qualified; performing anomaly detection on each part in the independent image to obtain an anomaly detection result of the independent image; generating a maintenance report of the survey and maintenance object based on an anomaly detection result of the independent image; and sending the maintenance report and the anomaly detection result to a maintenance center, so that the maintenance center performs maintenance. According to the method, intelligent recognition is carried out on the recognizable degree of the image, image acquisition is allowed to be completed only when the recognizable degree of the image is qualified, the accuracy and effectiveness of image acquisition can be effectively ensured, unqualified image acquisition is reduced, repeated image acquisition is reduced, and survey efficiency and recognition accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an intelligent detection method, system, electronic device and computer-readable storage medium based on survey and maintenance objects. Background Art

[0002] Communications inspection and maintenance typically utilizes artificial intelligence and machine learning to identify and analyze problems and faults in communications equipment. This approach can help locate and resolve equipment problems more efficiently, thereby reducing maintenance time and costs.

[0003] In the related art, when the equipment or buildings in the communication industry are intelligently inspected and identified through image recognition methods, the accuracy of the image is ensured through the operation of the staff. When the staff makes an operational error or an error occurs in the image acquisition device, the clarity of the acquired image is not enough to express the characteristics of the equipment or building in the communication industry. This will cause the background program to perform intelligent processing and analysis and identification of the image. Recognition errors may occur, and even program crashes may occur, thereby reducing the inspection efficiency and recognition accuracy. Summary of the invention

[0004] The present invention provides an intelligent detection method, system, electronic device and computer-readable storage medium based on inspection and maintenance objects, so as to at least solve the problem in the related art that due to the low definition of the collected images, errors are prone to occur in the intelligent processing and analysis and recognition of the images, resulting in reduced inspection efficiency and recognition accuracy. The technical solution of the present invention is as follows:

[0005] According to a first aspect of an embodiment of the present invention, there is provided an intelligent detection method based on surveying and maintaining objects, comprising:

[0006] Collect images of survey and maintenance objects;

[0007] Performing a discriminability test on the acquired image to obtain an image that passes the discriminability test;

[0008] Determining an independent image of the survey and maintenance object after passing the discernibility test;

[0009] Performing anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image;

[0010] generating a maintenance report for the surveyed and maintained object based on the abnormality detection result of the independent image;

[0011] The maintenance report and abnormality detection result are sent to a maintenance center so that the maintenance center can perform maintenance.

[0012] Optionally, the collecting images of the surveyed and maintained objects includes:

[0013] Acquire positioning information of an image acquisition device that acquires images of the survey and maintenance object, and a serial number of the survey and maintenance object;

[0014] The image acquisition device is used to acquire images of the inspection and maintenance objects corresponding to the numbers.

[0015] Optionally, when collecting images of a larger survey and maintenance object, the method further includes:

[0016] Using the image acquisition device to acquire multiple images of the survey and maintenance object corresponding to the number, the multiple images include: images at different angles and different positions;

[0017] The images with repeated features of two adjacent images among the multiple images collected are fused to obtain a fused image.

[0018] Optionally, fusing two adjacent images of the multiple images collected to obtain a fused image includes:

[0019] Extracting feature points of scale invariant feature transform (SIFT) from the multiple images;

[0020] Match the SIFT feature points of all two adjacent images separately;

[0021] Screen the feature point pairs after matching and exclude the wrong feature point pairs;

[0022] The perspective change matrix is ​​estimated for the filtered feature point pairs;

[0023] Based on the estimation results, the optimal stitching seams of all two adjacent images are determined;

[0024] Based on the best stitching seams of all two adjacent images, all images are fused into a fused image.

[0025] Optionally, before fusing the images of repeated features of two adjacent images among the multiple images collected, the method further includes:

[0026] Distortion correction is performed on the collected multiple images to remove distorted images.

[0027] Optionally, performing a discriminability test on the acquired image to obtain an image that passes the discriminability test includes:

[0028] Extracting edge information of the image of the survey and maintenance object;

[0029] Determine the characteristic points of the target image based on the edge information, and perform fuzzy processing on the image of the survey and maintenance object to obtain a fuzzy target image;

[0030] Based on the feature points, determining a first edge statistical feature of the image of the survey and maintenance object and a second edge statistical feature of the target blurred image;

[0031] Based on the similarity between the first edge statistical feature and the second edge statistical feature, obtaining the clarity of the survey and maintenance object image;

[0032] When the clarity reaches a clarity setting threshold, it is determined that the image of the survey and maintenance object is an image that passes the discernibility detection.

[0033] Optionally, the determining that the independent image in the surveyed and maintained object is qualified after the discernibility test includes:

[0034] Recognizing the image contour in the image after passing the discernibility test;

[0035] Dividing the image into a plurality of regions according to the recognition result;

[0036] Recognizing the images of the plurality of regions to obtain image regions of the objects to be inspected and maintained;

[0037] The image is segmented based on the image area to obtain an independent image of the survey and maintenance object.

[0038] Optionally, performing abnormality detection on each part of the independent image to obtain an abnormality detection result of the independent image includes:

[0039] dividing the independent image into a plurality of independent parts;

[0040] Performing abnormality detection on each independent part to determine whether each independent part is in an abnormal state or a working state;

[0041] Based on each of the independent parts being in an abnormal or working state, an abnormality detection result of the independent image is determined.

[0042] Optionally, the generating a maintenance report based on the abnormality detection result of the independent image includes:

[0043] generating a maintenance report corresponding to the abnormal part based on the abnormality of each part of the independent image;

[0044] An abnormal part is marked in the image of the inspected maintenance object, and the corresponding maintenance report is added to the mark.

[0045] Optionally, it is characterized in that, before performing discernibility detection on the acquired image, the method further comprises:

[0046] A compliance check is performed on the acquired image to obtain an image that passes the compliance check.

[0047] Optionally, performing compliance detection on the acquired image to obtain an image that passes the compliance detection includes:

[0048] Acquire the positioning information of the image acquisition device that acquires the image and the address location information of the survey and maintenance object;

[0049] Compare the positioning information with the address location information to determine whether the address location information is correct;

[0050] When the address location information is correct, determining whether the shooting time of the image is correct and compliant;

[0051] When the shooting time is correct and compliant, determining whether the user identity information of the image acquisition is compliant;

[0052] When the user identity information is compliant, the image is determined to be an image that has passed the compliance detection.

[0053] According to a second aspect of an embodiment of the present invention, there is provided an intelligent detection system based on surveying and maintaining objects, comprising:

[0054] A collection module, used for collecting images of survey and maintenance objects;

[0055] A first detection module is used to perform a discriminability test on the acquired image to obtain an image that passes the discriminability test;

[0056] A first determination module is used to determine the independent images in the survey and maintenance object after the discriminability test is qualified;

[0057] An anomaly detection module, used to perform anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image;

[0058] A generating module, configured to generate a maintenance report of the surveyed and maintained object based on the abnormality detection result of the independent image;

[0059] The sending module is used to send the maintenance report and the abnormality detection result to the maintenance center so that the maintenance center can perform maintenance.

[0060] Optionally, the acquisition module includes:

[0061] An acquisition module, used to acquire positioning information of an image acquisition device for acquiring images of the survey and maintenance object, and a serial number of the survey and maintenance object;

[0062] The first image acquisition module is used to use the image acquisition device to acquire images of the survey and maintenance object corresponding to the number.

[0063] Optionally, the device further comprises:

[0064] A second acquisition module is used to acquire multiple images of the inspection and maintenance object corresponding to the number by using the image acquisition device when acquiring images of a larger inspection and maintenance object, wherein the multiple images include images at different angles and different positions;

[0065] The fusion module is used to fuse the images with repeated features of two adjacent images among the multiple images collected to obtain a fused image.

[0066] Optionally, the device further comprises:

[0067] The distortion correction module is used to perform distortion correction on the multiple images collected to remove the distorted images before the fusion module fuses the images with repeated features of two adjacent images among the multiple images collected.

[0068] Optionally, the fusion module includes:

[0069] A first extraction module is used to extract feature points of scale invariant feature transform (SIFT) from the multiple images;

[0070] The matching module is used to match the SIFT feature points of all two adjacent images respectively;

[0071] A screening module, used for screening the feature point pairs after the matching module completes the matching, and excluding the wrong feature point pairs in the feature point pairs;

[0072] An estimation module, used for estimating a perspective change matrix of the feature point pairs filtered by the filtering module;

[0073] A second determination module is used to determine the best stitching seams of all two adjacent images based on the estimation result;

[0074] The image fusion module is used to fuse all images into a fused image based on the best stitching seams of all two adjacent images.

[0075] Optionally, the first detection module includes:

[0076] A second extraction module, used to extract edge information of the image of the survey and maintenance object;

[0077] A processing module, used for determining feature points of a target image based on the edge information, and performing fuzzy processing on the image of the survey and maintenance object to obtain a fuzzy target image;

[0078] A feature determination module, used to determine a first edge statistical feature of the image of the survey and maintenance object and a second edge statistical feature of the target blurred image based on the feature points;

[0079] A clarity determination module, configured to obtain the clarity of the inspection and maintenance object image based on the similarity between the first edge statistical feature and the second edge statistical feature;

[0080] The qualified detection determination module is used to determine that the image of the surveyed and maintained object is an image that has passed the discernibility detection when the clarity determination module determines that the clarity reaches a set clarity threshold.

[0081] Optionally, the first determining module includes:

[0082] A first recognition module, used for recognizing the image contour in the image after the discernibility test is passed;

[0083] A division module, used for dividing the image into a plurality of regions according to the recognition result;

[0084] A second recognition module is used to recognize the images of the multiple areas to obtain the image area of ​​the object to be inspected and maintained;

[0085] The first segmentation module is used to segment the image based on the image area to obtain an independent image of the survey and maintenance object.

[0086] Optionally, the anomaly detection module includes:

[0087] A second segmentation module, used for segmenting the independent image into a plurality of independent parts;

[0088] An abnormality detection submodule, used to perform abnormality detection on each independent part to determine whether each independent part is in an abnormal state or a working state;

[0089] The abnormal result determination module is used to determine the abnormal detection result of the independent image based on whether each independent part is in an abnormal or working state.

[0090] Optionally, the generating module includes:

[0091] A maintenance report generating module, used for generating a maintenance report corresponding to the abnormal part based on the abnormality of each part of the independent image;

[0092] The marking module is used to mark abnormal parts in the image of the surveyed and maintained object and add the corresponding maintenance report to the mark.

[0093] Optionally, the device further comprises:

[0094] The second detection module is used to perform compliance detection on the acquired image before the first detection module performs discernibility detection on the acquired image, so as to obtain an image that passes the compliance detection.

[0095] Optionally, the second detection module includes:

[0096] A location acquisition module, used to acquire the positioning information of the image acquisition device that acquires the image and the address location information of the survey and maintenance object;

[0097] A first judgment module, used to compare the positioning information with the address location information to determine whether the address location information is correct;

[0098] A second judgment module, configured to judge whether the shooting time of the image is correct and compliant when the first judgment module determines that the address location information is correct;

[0099] A third judgment module, configured to judge whether the user identity information of the image acquisition is compliant when the second judgment module determines that the shooting time is correct and compliant;

[0100] A compliance determination module is used to determine that the image is an image that has passed the compliance detection when the third judgment module determines that the user identity information is compliant.

[0101] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0102] processor;

[0103] a memory for storing instructions executable by the processor;

[0104] The processor is configured to execute the instructions to implement the intelligent detection method based on surveying and maintaining objects as described above.

[0105] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the intelligent detection method based on surveying and maintaining objects as described above.

[0106] According to a fifth aspect of an embodiment of the present invention, there is provided a computer program product, comprising a computer program or instructions, which, when executed by a processor of an electronic device, implements the intelligent detection method based on survey and maintenance objects as described above.

[0107] The technical solution provided by the embodiments of the present invention brings at least the following beneficial effects:

[0108] In an embodiment of the present invention, an image of the survey and maintenance object is collected; a discriminability test is performed on the image to obtain an image that passes the discriminability test; an independent image of the survey and maintenance object that passes the discriminability test is determined; an abnormality test is performed on each part of the independent image to obtain an abnormality detection result of the independent image; a maintenance report of the survey and maintenance object is generated based on the abnormality detection result of the independent image; and the maintenance report and the abnormality detection result are sent to a maintenance center so that the maintenance center can perform maintenance. The present invention can effectively ensure the accuracy and effectiveness of image acquisition by intelligently identifying the recognizability of the image and only allowing image acquisition to be completed when the image recognizability passes, thereby reducing the acquisition of unqualified images, reducing repeated image acquisition, and increasing survey efficiency and recognition accuracy.

[0109] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention, and do not constitute an improper limitation of the present invention. In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0111] Figure 1 The present invention provides a flow chart of an intelligent detection method based on inspection and maintenance objects.

[0112] Figure 2 The present invention provides a flowchart of collecting images of an object for inspection and maintenance.

[0113] Figure 3 The present invention provides a flowchart for detecting the discriminability of an image.

[0114] Figure 4The present invention provides a flowchart of image segmentation and extraction.

[0115] Figure 5 The present invention provides a flowchart of an image anomaly detection method.

[0116] Figure 6 This is a flow chart of fusing images based on SIFT feature points provided by an embodiment of the present invention.

[0117] Figure 7 The invention provides a block diagram of an intelligent detection system based on inspection and maintenance objects.

[0118] Figure 8 It is a block diagram of an electronic device provided by an embodiment of the present invention.

[0119] Fig. 9 The invention is a block diagram of a device for intelligent detection based on inspection and maintenance of objects provided by an embodiment of the invention. DETAILED DESCRIPTION

[0120] In order to enable ordinary persons in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0121] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0122] In recent years, research on computer vision, deep learning, machine learning, image processing, image recognition and other technologies based on artificial intelligence has made important progress. Artificial Intelligence (AI) is an emerging science and technology that studies and develops theories, methods, technologies and application systems for simulating and extending human intelligence. Artificial intelligence is a comprehensive discipline involving many types of technologies such as chips, big data, cloud computing, the Internet of Things, distributed storage, deep learning, machine learning, neural networks, etc. Computer vision, as an important branch of artificial intelligence, specifically allows machines to recognize the world. Computer vision technology usually includes face recognition, liveness detection, fingerprint recognition and anti-counterfeiting verification, biometric recognition, face detection, pedestrian detection, target detection, pedestrian recognition, image processing, image recognition, image semantic understanding, image retrieval, text recognition, video processing, video content recognition, behavior recognition, 3D reconstruction, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), computational photography, robot navigation and positioning and other technologies. With the research and advancement of artificial intelligence technology, this technology has been applied in many fields, such as security, urban management, traffic management, building management, park management, facial access, facial attendance, logistics management, warehouse management, robots, intelligent marketing, computational photography, mobile phone imaging, cloud services, smart homes, wearable devices, unmanned driving, automatic driving, smart medical care, facial payment, facial unlocking, fingerprint unlocking, identity verification, smart screens, smart TVs, cameras, mobile Internet, live streaming, beauty, makeup, medical beauty, and smart temperature measurement.

[0123] Please refer to the following technical term explanation first:

[0124] Distortion correction: refers to the technology of correcting the distortion caused by the lens in image processing, photography, or video recording.

[0125] SIFT (Scale Invariant Feature Transform): is an algorithm used in computer vision to detect and describe local image features.

[0126] RANSAC (RANdom SAmple Consensus) algorithm: is an iterative method for estimating the parameters of a mathematical model from a set of data containing "outliers".

[0127] DLT (Direct Linear Transform) algorithm: is a commonly used algorithm in computer vision, mainly used to solve the parameters of imaging transformation or geometric transformation.

[0128] Seam Finding Algorithm: Generally refers to a process in image processing that is used to identify and remove "layers; seams; interface seams" or paths in an image.

[0129] After understanding the above technical terms, please refer to Figure 1 , is a flow chart of an intelligent detection method based on inspection and maintenance objects provided by an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0130] Step 101: Collect images of the object to be inspected and maintained.

[0131] Step 102: Perform a discriminability test on the acquired image to obtain an image that passes the discriminability test.

[0132] Step 103: Determine the independent images in the survey and maintenance object that have passed the discriminability test.

[0133] Step 104: Perform anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image.

[0134] Step 105: Generate a maintenance report based on the abnormality detection result of the independent image.

[0135] Step 106: Send the maintenance report and abnormality detection result to a maintenance center so that the maintenance center can perform maintenance.

[0136] In the embodiment of the present invention, the image collected of the surveyed and maintained object is first subjected to a recognizability test, which can ensure the real-time image of the surveyed and maintained object, and can effectively ensure the recognizability and analyzability of the image, thereby preventing the subsequent recognition and analysis from causing erroneous recognition and analysis results due to unqualified image clarity, thereby ensuring the accuracy of intelligent image recognition.

[0137] The intelligent detection method based on inspection and maintenance objects described in the present invention can be applied to terminals, servers, etc., without limitation herein. The terminal implementation device can be electronic devices such as smart phones, laptops, tablet computers, desktop computers, personal digital assistants (PDAs) and wearable devices. The server can be an independent server or a server cluster, or a server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, intermediate services, domain name services, security services, content distribution networks, or big data and artificial intelligence platforms, etc., without limitation herein.

[0138] Combine the following Figure 1, the specific implementation steps of an intelligent detection method based on inspection and maintenance objects provided by an embodiment of the present invention are described in detail.

[0139] In step 101, an image of a survey and maintenance object is acquired.

[0140] In this step, firstly, the positioning information of the image acquisition device for acquiring the image of the survey and maintenance object and the number of the survey and maintenance object are acquired; then, the image acquisition device is used to acquire the image of the survey and maintenance object corresponding to the number.

[0141] That is to say, during the inspection and maintenance of the communications industry, the staff can use the image acquisition equipment to acquire images of the objects that need to be inspected and maintained, and the acquired images can be real-time images. Figure 2 As shown, Figure 2 A flowchart of collecting images of an inspection and maintenance object provided by an embodiment of the present invention includes:

[0142] Step 201: Start the image acquisition device, send an image acquisition application to the manager, and after receiving the manager's consent, execute step 202;

[0143] Step 202: collect the location of the image acquisition device and register the number of the object to be inspected and maintained;

[0144] Step 203: Use the image acquisition device to acquire images of the inspection and maintenance objects corresponding to the numbers.

[0145] Optionally, in an embodiment of the present invention, when a staff member uses an image acquisition device to capture images of an object that needs to be inspected and maintained, it can also include: using a recording device to capture images of the staff member and the image acquisition device, and using a template matching method to identify the image acquisition device. When the image captured by the recording device includes the image of the image acquisition device, the image acquisition device can be started normally.

[0146] In step 102, a discriminability test is performed on the acquired image to obtain an image that passes the discriminability test.

[0147] The specific steps are as follows Figure 3 As shown, Figure 3 A flowchart of performing discriminability detection on an image provided by an embodiment of the present invention includes:

[0148] Step 301: extract edge information of the image of the surveyed and maintained object.

[0149] In this step, an image contour detection algorithm based on template matching may be used to extract edge information of the inspection and maintenance object image; the specific extraction process is well known to those skilled in the art and will not be described in detail here.

[0150] Step 302: Determine the feature points of the target image based on the edge information, and perform blurring processing on the image of the surveyed and maintained object to obtain a blurred target image.

[0151] In this step, when the edge information meets the preset edge condition, the feature points of the target image are obtained based on the edge information, and the image of the survey and maintenance object is blurred to obtain a target blurred image.

[0152] Step 303: Based on the feature points, determine a first edge statistical feature of the image of the surveyed and maintained object and a second edge statistical feature of the target blurred image.

[0153] In this step, based on the feature points, a first edge statistical feature of the image of the surveyed and maintained object and a second edge statistical feature of the target blurred image can be obtained.

[0154] Step 304: Based on the similarity between the first edge statistical feature and the second edge statistical feature, the clarity of the survey and maintenance object image is obtained.

[0155] In this step, the similarity between the first edge statistical feature and the second edge statistical feature is determined. Based on the similarity, the clarity of the image to be maintained can be checked.

[0156] Step 305: When the clarity reaches a clarity setting threshold, determine that the image of the surveyed and maintained object is an image that passes the discernibility test.

[0157] In this step, it is determined whether the clarity meets the clarity setting. If so, it means that the image of the inspection and maintenance object is an image that passes the recognizability test. Otherwise, it is an unqualified image.

[0158] In step 103, independent images in the survey and maintenance object that have passed the discriminability test are determined.

[0159] In this step, the image contour detection algorithm can be used to detect the image that has passed the discriminability test, and the image can be segmented according to the detection result. The schematic diagram of image segmentation and extraction is as follows: Figure 4 As shown, Figure 4 A flowchart for image segmentation and extraction provided by an embodiment of the present invention specifically includes:

[0160] Step 401: Identify the image contour in the image that has passed the discernibility test.

[0161] In this step, an image contour recognition algorithm based on depth recognition is used to recognize the image contour in the image that has passed the discernibility test.

[0162] Step 402: Divide the image into multiple regions according to the recognition result.

[0163] The image contour recognition algorithm based on depth recognition divides the image into several areas based on the recognition results.

[0164] Step 403: Identify the images of the multiple regions to obtain image regions of the objects to be inspected and maintained.

[0165] In this step, an image recognition algorithm based on template matching can be used to identify images of several areas in combination with image features of the inspected and maintained objects obtained according to the serial numbers of the inspected and maintained objects, thereby obtaining image areas of the inspected and maintained objects.

[0166] Step 404: Segment the image based on the image area to obtain an independent image of the survey and maintenance object.

[0167] In this step, the image of the object to be inspected and maintained is segmented according to the image area obtained in step 403 to obtain an independent image of the object to be inspected and maintained.

[0168] In step 104, abnormality detection is performed on each part of the independent image to obtain an abnormality detection result of the independent image.

[0169] In this step, a variety of image recognition algorithms can be used to detect abnormalities in each part of the independent image to complete the investigation of the independent image. Figure 5 As shown, Figure 5 A flowchart for image anomaly detection provided by an embodiment of the present invention specifically includes:

[0170] Step 501: Segment the independent image into multiple independent parts;

[0171] In this step, the independent image of the survey and maintenance object may be segmented using an image segmentation algorithm based on template matching, and the independent image of the survey and maintenance object may be segmented into a plurality of independent parts.

[0172] Step 502: Perform an abnormality detection on each independent part to determine whether each independent part is in an abnormal state or a working state;

[0173] In this step, an image anomaly recognition algorithm based on image comparison can be used to perform anomaly detection on several independent parts in the independent image of the inspection and maintenance object, detect the anomalies and / or working status of several independent parts, and thus determine whether each independent part is in an abnormal state or a working state, etc.

[0174] Step 503: Determine an abnormality detection result of the independent image based on whether each independent part is in an abnormal or working state.

[0175] In this step, the abnormality of each part is determined by combining the abnormal or working state of each independent part, and the abnormality of the maintenance object as a whole is checked, and the result is recorded. In other words, first determine whether each part in the independent image is abnormal, and then comprehensively check whether the overall image is abnormal.

[0176] In step 105, a maintenance report of the surveyed and maintained object is generated based on the abnormality detection result of the independent image.

[0177] In this step, a maintenance plan for each part is generated based on the abnormality of each part; the abnormal part is marked in the image of the surveyed maintenance object, and the maintenance plan is added to the mark.

[0178] In step 106, the maintenance report and the abnormality detection result are sent to a maintenance center so that the maintenance center can perform maintenance.

[0179] In this step, the marked image is sent to the maintenance center or the staff's equipment to facilitate maintenance.

[0180] Among them, the maintenance process performed by the maintenance center or the staff of the maintenance center includes: the staff views the marked image, and separately views and inspects the inspection and maintenance objects according to the marks in the image; and modifies the marked image according to the results of the viewing and inspection, and generates the final inspection result after the modification is completed.

[0181] In an embodiment of the present invention, an image of the survey and maintenance object is collected; a discriminability test is performed on the acquired image to obtain an image that passes the discriminability test; an independent image of the survey and maintenance object that passes the discriminability test is determined; an abnormality test is performed on each part of the independent image to obtain an abnormality detection result of the independent image; a maintenance report of the survey and maintenance object is generated based on the abnormality detection result of the independent image; and the maintenance report and the abnormality detection result are sent to a maintenance center so that the maintenance center can perform maintenance. In other words, the embodiment of the present invention performs intelligent recognition of the recognizability of the image, and allows image collection to be completed only when the image recognizability passes, which can effectively ensure the accuracy and effectiveness of image collection, effectively prevent the occurrence of unqualified image collection, reduce repeated image collection, and increase survey efficiency and recognition accuracy.

[0182] Compared with the prior art, the embodiments of the present invention ensure the correctness of the image through the operation of the staff when performing intelligent inspection and identification of equipment and buildings in the communication industry through the image recognition method. When the staff makes an operational error or an error occurs in the image acquisition device, the clarity of the acquired image may not be sufficient to express the characteristics of the equipment or building in the communication industry, which may cause recognition errors or even program crashes when the background program performs intelligent processing and analysis and identification of the image. The intelligent recognition method performs intelligent identification on the recognizability of the image, and allows image acquisition to be completed only when the image recognizability is qualified. This can effectively ensure the accuracy and effectiveness of image acquisition, effectively prevent the occurrence of unqualified image acquisition, reduce repeated image acquisition, and increase inspection efficiency and recognition accuracy.

[0183] Optionally, in another embodiment, based on the above embodiment, when performing image acquisition on a larger survey and maintenance object, the method further includes: using the image acquisition device to acquire multiple images of the survey and maintenance object corresponding to the number, the multiple images including: images at different angles and different positions; fusing the images of repeated features of two adjacent images in the multiple images acquired to obtain a fused image. Specifically, the image fusion algorithm based on SIFT feature points can be used to fuse the images of repeated features of two adjacent images in the multiple images acquired.

[0184] Specific as Figure 6 As shown, Figure 6 A flowchart of fusing images based on SIFT feature points provided by an embodiment of the present invention includes:

[0185] Step 601: Utilize the image acquisition device to acquire multiple images of the survey and maintenance object corresponding to the number, wherein the multiple images include images at different angles and different positions.

[0186] In this step, an image acquisition device may be used to acquire images of the survey and maintenance object, and acquire multiple images of the survey and maintenance object at different angles and positions until all images of the survey and maintenance object are acquired.

[0187] Step 602: Perform distortion correction on the collected multiple images to remove image distortion caused by the camera lens structure.

[0188] Step 603: extracting feature points of the scale invariant feature transform (SIFT) from the plurality of images after distortion correction.

[0189] Step 604: Match the SIFT feature points of all two adjacent images respectively.

[0190] Step 605: Screen the matched feature point pairs to exclude erroneous feature point pairs.

[0191] Step 606: Estimating the perspective change matrix of the filtered feature point pairs.

[0192] In this step, the DLT algorithm can be used to estimate the perspective change matrix of the feature point pairs remaining after screening.

[0193] Step 607: Based on the estimation result, determine the best stitching seam between all two adjacent images.

[0194] In this step, the Seam Finding algorithm can be used to find the best stitching seam, and find the best stitching seam of the images collected by two adjacent groups of high-definition cameras.

[0195] Step 608: Based on the best stitching seams of all two adjacent images, all images are fused into a fused image.

[0196] In this step, the Laplacian pyramid can be used to decompose the original image into sub-images of different scales by differentiating the two adjacent layers of the Gaussian pyramid. The weighted average of each sub-image is performed to obtain the fusion result of each layer. Finally, the pyramid is reversely reconstructed to obtain the final fusion effect image.

[0197] Repeat the above steps until all images are fused into one fused image.

[0198] In the embodiment of the present invention, when performing image acquisition on a larger inspection and maintenance object, in order to ensure the clarity and recognizability of the image, it is impossible to perform image acquisition on the inspection and maintenance object at a distant place. Therefore, it is difficult to capture the overall picture of the larger inspection and maintenance object by shooting. By setting an image fusion algorithm based on SIFT feature points, multiple images with repeated features can be fused, so that the image features of the larger inspection and maintenance object can be expressed in one image, thereby preventing the program from calculating too much due to image duplication, and preventing image acquisition omissions due to staff operating errors, thereby ensuring the effectiveness of image acquisition.

[0199] Optionally, in another embodiment, based on the above embodiment, before performing a discernibility test on the acquired image, the method further includes: performing a compliance test on the acquired image to obtain an image that passes the compliance test.

[0200] Among them, the compliance check is performed on the acquired image to obtain an image that passes the compliance check, including: obtaining the positioning information of the image acquisition device that acquires the image and the address location information of the surveyed and maintained object; comparing the positioning information with the address location information to determine whether the address location information is correct; when the address location information is correct, determining whether the shooting time of the image is correct and compliant; when the shooting time is correct and compliant, determining whether the user identity information used to acquire the image is compliant; when the user identity information is compliant, determining that the image is an image that passes the compliance check.

[0201] That is to say, when the present invention performs compliance detection on the image captured by the image acquisition device, it specifically includes:

[0202] 1) Read the number of the object to be inspected and maintained entered by the staff, and obtain the geographical location of the object to be inspected and maintained;

[0203] 2) comparing the positioning information of the image acquisition device obtained in step 1) with the address location information of the survey and maintenance object to determine whether the address location is correct;

[0204] 3) Read the image data collected by the image acquisition device, obtain the shooting time of the image data, and determine whether the time is correct and compliant;

[0205] 4) At the same time, the image recorded by the recorder is identified to obtain the identity of the staff member who collected the image and determine whether the identity of the staff member is compliant.

[0206] In the embodiment of the present invention, by setting up the positioning of the image acquisition device and the identity verification of the staff, it is possible to effectively prevent unauthorized personnel from using the image acquisition device to perform non-compliant operations, resulting in background program errors or even background program crashes. At the same time, it is possible to ensure the correctness and effectiveness of image acquisition and prevent staff from committing fraud for the sake of profit. Intelligent and reliable supervision is achieved through the intelligent identification method based on inspection and maintenance objects provided by the embodiment of the present invention.

[0207] The present invention ensures that the images captured by the image acquisition device are real-time images of the objects to be inspected and maintained by setting up compliance and recognizability detection for the images captured by the image acquisition device, and can effectively ensure the recognizability and analyzability of the images, thereby preventing errors in the recognition and analysis results due to unqualified image clarity during subsequent recognition and analysis, and ensuring the accuracy of intelligent image recognition.

[0208] It should be noted that, for the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that this implementation disclosure is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention.

[0209] See also Figure 7 , is a block diagram of an intelligent detection system based on inspection and maintenance objects provided by an embodiment of the present invention. The system includes: a collection module 701, a first detection module 702, a first determination module 703, an abnormality detection module 704, a generation module 705 and a sending module 706, wherein,

[0210] The acquisition module 701 is used to acquire images of the inspection and maintenance objects;

[0211] A first detection module 702 is used to perform a discriminability test on the acquired image to obtain an image that passes the discriminability test;

[0212] A first determination module 703 is used to determine the independent images in the survey and maintenance object after the discriminability test is qualified;

[0213] An anomaly detection module 704 is used to perform an anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image;

[0214] A generating module 705, configured to generate a maintenance report of the surveyed and maintained object based on the abnormality detection result of the independent image;

[0215] The sending module 706 is used to send the maintenance report and the abnormality detection result to the maintenance center so that the maintenance center can perform maintenance.

[0216] Optionally, in another embodiment, based on the above embodiment, the acquisition module includes:

[0217] An acquisition module, used to acquire positioning information of an image acquisition device for acquiring images of the survey and maintenance object, and a serial number of the survey and maintenance object;

[0218] The first image acquisition module is used to use the image acquisition device to acquire images of the survey and maintenance object corresponding to the number.

[0219] Optionally, in another embodiment, based on the above embodiment, the device further includes:

[0220] A second acquisition module is used to acquire multiple images of the inspection and maintenance object corresponding to the number by using the image acquisition device when acquiring images of a larger inspection and maintenance object, wherein the multiple images include images at different angles and different positions;

[0221] The fusion module is used to fuse the images with repeated features of two adjacent images among the multiple images collected to obtain a fused image.

[0222] Optionally, in another embodiment, based on the above embodiment, the device further includes:

[0223] The distortion correction module is used to perform distortion correction on the multiple images collected to remove the distorted images before the fusion module fuses the images with repeated features of two adjacent images among the multiple images collected.

[0224] Optionally, in another embodiment, based on the above embodiment, the fusion module includes:

[0225] A first extraction module is used to extract feature points of scale invariant feature transform (SIFT) from the multiple images;

[0226] The matching module is used to match the SIFT feature points of all two adjacent images respectively;

[0227] A screening module, used for screening the feature point pairs after the matching module completes the matching, and excluding the wrong feature point pairs in the feature point pairs;

[0228] An estimation module, used for estimating a perspective change matrix of the feature point pairs filtered by the filtering module;

[0229] A second determination module is used to determine the best stitching seams of all two adjacent images based on the estimation result;

[0230] The image fusion module is used to fuse all images into a fused image based on the best stitching seams of all two adjacent images.

[0231] Optionally, in another embodiment, based on the above embodiment, the first detection module includes:

[0232] A second extraction module, used to extract edge information of the image of the survey and maintenance object;

[0233] A processing module, used for determining feature points of a target image based on the edge information, and performing fuzzy processing on the image of the survey and maintenance object to obtain a fuzzy target image;

[0234] A feature determination module, used to determine a first edge statistical feature of the image of the survey and maintenance object and a second edge statistical feature of the target blurred image based on the feature points;

[0235] A clarity determination module, configured to obtain the clarity of the inspection and maintenance object image based on the similarity between the first edge statistical feature and the second edge statistical feature;

[0236] The qualified detection determination module is used to determine that the image of the surveyed and maintained object is an image that has passed the discernibility detection when the clarity determination module determines that the clarity reaches a set clarity threshold.

[0237] Optionally, in another embodiment, based on the above embodiment, the first determining module includes:

[0238] A first recognition module, used for recognizing the image contour in the image after the discernibility test is passed;

[0239] A division module, used for dividing the image into a plurality of regions according to the recognition result;

[0240] A second recognition module is used to recognize the images of the multiple areas to obtain the image area of ​​the object to be inspected and maintained;

[0241] The first segmentation module is used to segment the image based on the image area to obtain an independent image of the survey and maintenance object.

[0242] Optionally, in another embodiment, based on the above embodiment, the abnormality detection module includes:

[0243] A second segmentation module, used for segmenting the independent image into a plurality of independent parts;

[0244] An abnormality detection submodule, used to perform abnormality detection on each independent part to determine whether each independent part is in an abnormal state or a working state;

[0245] The abnormal result determination module is used to determine the abnormal detection result of the independent image based on whether each independent part is in an abnormal or working state.

[0246] Optionally, in another embodiment, based on the above embodiment, the generating module includes:

[0247] A maintenance report generating module, used for generating a maintenance report of a corresponding part based on the abnormality of each part of the independent image;

[0248] The marking module is used to mark the abnormal part in the image of the surveyed and maintained object, and add the maintenance report corresponding to the abnormal part to the mark.

[0249] Optionally, in another embodiment, based on the above embodiment, the device further includes:

[0250] The second detection module is used to perform compliance detection on the acquired image before the first detection module performs discernibility detection on the acquired image, so as to obtain an image that passes the compliance detection.

[0251] Optionally, in another embodiment, based on the above embodiment, the second detection module includes:

[0252] A location acquisition module, used to acquire the positioning information of the image acquisition device that acquires the image and the address location information of the survey and maintenance object;

[0253] A first judgment module, used to compare the positioning information with the address location information to determine whether the address location information is correct;

[0254] A second judgment module, configured to judge whether the shooting time of the image is correct and compliant when the first judgment module determines that the address location information is correct;

[0255] A third judgment module, configured to judge whether the user identity information of the image acquisition is compliant when the second judgment module determines that the shooting time is correct and compliant;

[0256] The compliance determination module is used to determine that the image is an image that has passed the compliance detection when the third judgment module determines that the user identity information is compliant.

[0257] Optionally, an embodiment of the present invention further provides an electronic device, including:

[0258] processor;

[0259] a memory for storing instructions executable by the processor;

[0260] The processor is configured to execute the instructions to implement the intelligent detection method based on surveying and maintaining objects as described above.

[0261] An embodiment of the present invention further provides a computer-readable storage medium. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the intelligent detection method based on surveying and maintaining objects as described above.

[0262] An embodiment of the present invention further provides a computer program product, including a computer program or instructions, which, when executed by a processor of an electronic device, implements the intelligent detection method based on surveying and maintaining objects as described above.

[0263] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0264] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0265] Figure 8 800 is a block diagram of an electronic device 800 provided in an embodiment of the present invention. For example, the electronic device 800 may be a mobile terminal or a server, and the electronic device is a mobile terminal as an example for explanation in the embodiment of the present invention. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a message transceiver device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0266] Reference Figure 8 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0267] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0268] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0269] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0270] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0271] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0272] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0273] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0274] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0275] In an embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the intelligent detection method based on inspection and maintenance objects shown above.

[0276] In an embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device 800 can execute the intelligent detection method based on the inspection and maintenance object shown above. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0277] In an embodiment, a computer program product is also provided, including a computer program or instructions. When the computer program or instructions are executed by the processor 820 of the electronic device 800, the electronic device 800 executes the above-mentioned intelligent detection method based on inspection and maintenance objects.

[0278] Fig. 9 is a block diagram of a device 900 for intelligent detection based on inspection and maintenance of objects provided by an embodiment of the present invention. For example, the device 900 may be provided as a server. Fig. 9 , the apparatus 900 includes a processing component 922, which further includes one or more processors, and a memory resource represented by a memory 932 for storing instructions, such as an application, that can be executed by the processing component 922. The application stored in the memory 932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 922 is configured to execute the instructions to perform the above method.

[0279] The device 900 may also include a power supply component 926 configured to perform power management of the device 900, a wired or wireless network interface 950 configured to connect the device 900 to a network, and an input / output (I / O) interface 958. The device 900 may operate based on an operating system stored in the memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0280] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0281] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An intelligent detection method based on survey and maintenance objects, characterized in that: include: Collect images of survey and maintenance objects; Performing a discriminability test on the acquired image to obtain an image that passes the discriminability test; Determining an independent image of the survey and maintenance object after passing the discernibility test; Performing anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image; generating a maintenance report for the surveyed and maintained object based on the abnormality detection result of the independent image; The maintenance report and abnormality detection result are sent to a maintenance center so that the maintenance center can perform maintenance.

2. The intelligent detection method based on inspection and maintenance object according to claim 1 is characterized in that: The collecting of images of the surveyed and maintained objects includes: Acquire positioning information of an image acquisition device that acquires images of the survey and maintenance object, and a serial number of the survey and maintenance object; The image acquisition device is used to acquire images of the inspection and maintenance objects corresponding to the numbers.

3. The intelligent detection method based on inspection and maintenance object according to claim 2 is characterized in that: When collecting images of a larger survey and maintenance object, the method further includes: Using the image acquisition device to acquire multiple images of the survey and maintenance object corresponding to the number, the multiple images include: images at different angles and different positions; The images with repeated features of two adjacent images among the multiple images collected are fused to obtain a fused image.

4. The intelligent detection method based on inspection and maintenance object according to claim 3 is characterized in that: The step of fusing two adjacent images of the plurality of images to obtain a fused image comprises: Extracting feature points of scale invariant feature transform (SIFT) from the multiple images; Match the SIFT feature points of all two adjacent images separately; Screen the feature point pairs after matching and exclude the wrong feature point pairs; The perspective change matrix is ​​estimated for the filtered feature point pairs; Based on the estimation results, the optimal stitching seams of all two adjacent images are determined; Based on the best stitching seams of all two adjacent images, all images are fused into a fused image.

5. The intelligent detection method based on inspection and maintenance object according to claim 3 is characterized in that: Before fusing the images of repeated features of two adjacent images among the multiple images collected, the method further includes: Distortion correction is performed on the collected multiple images to remove distorted images.

6. The intelligent detection method based on inspection and maintenance object according to claim 1 is characterized in that: The step of performing a discriminability test on the acquired image to obtain an image that passes the discriminability test includes: Extracting edge information of the image of the survey and maintenance object; Determine the characteristic points of the target image based on the edge information, and perform fuzzy processing on the image of the survey and maintenance object to obtain a fuzzy target image; Based on the feature points, determining a first edge statistical feature of the image of the survey and maintenance object and a second edge statistical feature of the target blurred image; Based on the similarity between the first edge statistical feature and the second edge statistical feature, obtaining the clarity of the survey and maintenance object image; When the clarity reaches a clarity setting threshold, it is determined that the image of the survey and maintenance object is an image that passes the discernibility detection.

7. The intelligent detection method based on inspection and maintenance object according to claim 1 is characterized in that: The determining that the independent image in the survey and maintenance object is qualified after the discernibility test comprises: Recognizing the image contour in the image after passing the discernibility test; Dividing the image into a plurality of regions according to the recognition result; Recognizing the images of the plurality of regions to obtain image regions of the objects to be inspected and maintained; The image is segmented based on the image area to obtain an independent image of the survey and maintenance object.

8. The intelligent detection method based on inspection and maintenance object according to claim 1 is characterized in that: The performing abnormality detection on each part of the independent image to obtain the abnormality detection result of the independent image includes: dividing the independent image into a plurality of independent parts; Performing abnormality detection on each independent part to determine whether each independent part is in an abnormal state or a working state; Based on each of the independent parts being in an abnormal or working state, an abnormality detection result of the independent image is determined.

9. The intelligent detection method based on inspection and maintenance object according to claim 1 is characterized in that: The generating of the maintenance report based on the abnormality detection result of the independent image comprises: generating a maintenance report corresponding to the abnormal part based on the abnormality of each part of the independent image; An abnormal part is marked in the image of the inspected maintenance object, and the corresponding maintenance report is added to the mark.

10. The intelligent detection method based on inspection and maintenance object according to any one of claims 1 to 9, characterized in that: Before performing discriminability detection on the acquired image, the method further includes: A compliance check is performed on the acquired image to obtain an image that passes the compliance check.

11. The intelligent detection method based on inspection and maintenance object according to claim 10, characterized in that: The step of performing compliance detection on the acquired image to obtain an image that passes the compliance detection includes: Acquire the positioning information of the image acquisition device that acquires the image and the address location information of the survey and maintenance object; Compare the positioning information with the address location information to determine whether the address location information is correct; When the address location information is correct, determining whether the shooting time of the image is correct and compliant; When the shooting time is correct and compliant, determining whether the user identity information of the image acquisition is compliant; When the user identity information is compliant, the image is determined to be an image that has passed the compliance detection.

12. An intelligent detection system based on inspection and maintenance of objects, characterized in that: include: A collection module, used for collecting images of survey and maintenance objects; A first detection module is used to perform a discriminability test on the acquired image to obtain an image that passes the discriminability test; A first determination module is used to determine the independent images in the survey and maintenance object after the discriminability test is qualified; An anomaly detection module, used to perform anomaly detection on each part of the independent image to obtain an anomaly detection result of the independent image; A generating module, configured to generate a maintenance report of the surveyed and maintained object based on the abnormality detection result of the independent image; The sending module is used to send the maintenance report and the abnormality detection result to the maintenance center so that the maintenance center can perform maintenance.

13. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the intelligent detection method based on survey and maintenance objects as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the intelligent detection method based on surveying and maintaining objects as described in any one of claims 1 to 11.

Images