CN111832557A - Power grid inspection method and device, electronic equipment and storage medium - Google Patents
Power grid inspection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111832557A CN111832557A CN202010501342.7A CN202010501342A CN111832557A CN 111832557 A CN111832557 A CN 111832557A CN 202010501342 A CN202010501342 A CN 202010501342A CN 111832557 A CN111832557 A CN 111832557A
- Authority
- CN
- China
- Prior art keywords
- power grid
- model
- detection
- inspection image
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 200
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000001514 detection method Methods 0.000 claims abstract description 262
- 238000005070 sampling Methods 0.000 claims abstract description 31
- 238000012360 testing method Methods 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 36
- 230000035945 sensitivity Effects 0.000 claims description 26
- 230000015654 memory Effects 0.000 claims description 23
- 238000013145 classification model Methods 0.000 claims description 18
- 239000000126 substance Substances 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a power grid inspection method and device, electronic equipment and a storage medium, and relates to the technical field of computer vision and deep learning. The specific implementation scheme is as follows: acquiring at least one first detection frame in a power grid inspection image to be detected, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the interference of a non-target area in the power grid inspection image on the detection effect can be avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to the technical field of computer vision and deep learning, and particularly relates to a power grid inspection method and device, electronic equipment and a storage medium.
Background
The power grid inspection scheme in the related technology mainly utilizes intelligent inspection equipment to conduct inspection. In the power grid inspection scheme, power grid inspection images acquired by intelligent inspection equipment are input into a target detection model, target information is acquired, and whether potential safety hazards exist is determined. A non-target area exists in the power grid inspection image, and the detection process of the target detection model is interfered.
Disclosure of Invention
The disclosure provides a power grid inspection method, a power grid inspection device, electronic equipment and a storage medium.
According to one aspect of the disclosure, a power grid inspection method is provided, which includes acquiring at least one first detection frame in a power grid inspection image to be detected, wherein a detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the interference of a non-target area in the power grid inspection image on the detection effect can be avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
In the second aspect of the application, a power grid inspection device is provided.
In a third aspect of the present application, an electronic device is provided.
In a fourth aspect of the present application, a computer-readable storage medium is provided.
An embodiment of a first aspect of the present application provides a power grid inspection method, including: acquiring a power grid inspection image to be detected; acquiring at least one first detection frame in the power grid inspection image, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to the at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; and determining the target information of the power grid inspection image according to the detection target of the at least one second detection frame.
According to the power grid inspection method, at least one first detection frame in a power grid inspection image to be detected is obtained, wherein the detection score of the first detection frame is larger than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the interference of a non-target area in the power grid inspection image on the detection effect can be avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
The embodiment of the second aspect of the application provides a power grid inspection device, includes: the first acquisition module is used for acquiring a power grid inspection image to be detected; the second acquisition module is used for acquiring at least one first detection frame in the power grid inspection image, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value; the screen capture module is used for capturing the power grid inspection image according to the at least one first detection frame to obtain a sampling image; the third acquisition module is used for acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; and the first determining module is used for determining the target information of the power grid inspection image according to the detection target of the at least one second detection frame.
An embodiment of a third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a grid patrolling method as described above.
A fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the power grid inspection method as described above.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present application;
FIG. 2 is a schematic diagram according to a second embodiment of the present application;
FIG. 3 is a schematic illustration according to a third embodiment of the present application;
FIG. 4 is a schematic illustration according to a fourth embodiment of the present application;
FIG. 5 is a schematic illustration according to a fifth embodiment of the present application;
fig. 6 is a block diagram of an electronic device for implementing the power grid inspection method according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The following describes a power grid inspection method, a power grid inspection device, an electronic device, and a storage medium according to embodiments of the present application with reference to the drawings.
Fig. 1 is a schematic diagram according to a first embodiment of the present application. It should be noted that the main execution body of the power grid inspection method provided in this embodiment is a power grid inspection device, and the power grid inspection device may specifically be a hardware device, or software in a hardware device, or the like. The hardware devices are, for example, terminal devices, servers, and the like. The terminal device may be, for example, a power grid inspection device.
The power grid inspection equipment comprises a plurality of power grid inspection equipment, a plurality of power grid inspection equipment and a plurality of monitoring equipment, wherein the power grid inspection equipment is arranged on each node in a power grid or a plurality of positions needing potential safety hazard inspection. The power grid inspection equipment can shoot and collect power grid inspection images at regular time, for example, horizontally rotate an angle every 10 seconds and fix for 3 seconds to shoot.
As shown in fig. 1, the power grid inspection method is implemented as follows:
In the embodiment of the application, the power grid inspection image to be detected can be a power grid inspection image needing target detection. The power grid inspection image needing target detection can be a power grid inspection image acquired by power grid inspection equipment or a power grid inspection image acquired by other equipment such as a user mobile phone.
Step 102, at least one first detection frame in the power grid inspection image is obtained, wherein the detection score of the first detection frame is larger than or equal to a first score threshold value.
In the embodiment of the present application, in order to improve the accuracy of the detected first detection frame, with reference to fig. 2, on the basis of the embodiment shown in fig. 1, the process of the grid inspection device performing step 102 may be, for example,
step 1021, inputting the power grid inspection image into a preset target detection model, and acquiring detection frame information in the power grid inspection image.
And 1022, determining at least one first detection frame in the power grid inspection image according to the detection frame information.
The target detection model may be a model obtained by training an initial target detection model using training data. In this application embodiment, the detection frame information in the power grid inspection image may include: the power grid inspection image detection method comprises a plurality of detection frames, and a detection score and a detection target of each detection frame, wherein the detection score represents the probability that the detection target exists in the detection frame of the power grid inspection image.
And 103, screenshot is carried out on the power grid inspection image according to at least one first detection frame, and a sampling image is obtained.
In this embodiment of the application, in order to avoid missing a certain detection box during screenshot, the process of the target detection model executing step 103 may be, for example, determining a capture box covering at least one first detection box according to the at least one first detection box; and (4) carrying out screenshot on the power grid inspection image according to the screenshot frame to obtain a sampling image.
In the embodiment of the present application, the process of determining the intercepting frame may be, for example, performing union operation on at least one first detection frame to determine a coverage area of the at least one first detection frame; and acquiring a minimum frame comprising the coverage area, and determining the minimum frame as the interception frame. In the embodiment of the application, the process of acquiring the sampling image may be, for example, capturing the power grid inspection image according to a capture frame, acquiring an image area of the power grid inspection image in the capture frame, amplifying the image area according to the size of the power grid inspection image, and determining the amplified image as the sampling image.
And 104, acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value.
In this embodiment of the application, in order to improve the accuracy of the detected second detection frame, the process of the power grid inspection device executing step 104 may be, for example, inputting the sample image into a preset target detection model, and acquiring the detection frame information in the sample image; and determining at least one second detection frame in the power grid inspection image according to the detection frame information in the sampling image.
In the embodiment of the present application, in order to ensure the recall rate of the first detection box and improve the accuracy of the second detection box, the second score threshold may be greater than the first score threshold.
And 105, determining target information of the power grid inspection image according to the detection target of the at least one second detection frame.
In the embodiment of the application, the power grid inspection device can take the detection target of at least one second detection frame as the target in the power grid inspection image; and determining the sum of the targets in the power grid polling image as the target information of the power grid polling image. The target may be, for example, a crane, a construction machine, a mountain fire, smoke, a foreign matter in a wire, or the like.
In the embodiment of the application, whether potential safety hazards exist in the power grid can be determined by combining the target information of the power grid inspection image, so that the potential safety hazards can be found in time and prompted. Thus, after step 105, the method may further comprise the steps of: determining whether a target with potential safety hazard exists in the power grid inspection image according to the target information of the power grid inspection image; when a target with potential safety hazards exists in the power grid inspection image, the potential safety hazards exist in the inspection position corresponding to the power grid inspection image in the power grid, and potential safety hazards are prompted. Among them, objects having potential safety hazards such as cranes, construction machines, mountain fires, smoke, foreign matters of wires, and the like. The hidden danger prompting mode can be, for example, sending prompting information to an inspection worker, and giving a light prompt at a position where the potential safety hazard exists.
In the embodiment of the application, under the condition that the power grid inspection device is the power grid inspection equipment, the power grid inspection equipment can shoot and collect power grid inspection images, detect the power grid inspection images, acquire target information in the power grid inspection images, and adopt computer vision to replace human eyes to acquire the target information of each position in the power grid, so that power grid inspection is realized.
In summary, at least one first detection frame in the power grid inspection image to be detected is obtained, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the interference of a non-target area in the power grid inspection image on the detection effect can be avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
Step 102, inputting the power grid inspection image into a preset target detection model, and acquiring detection frame information in the power grid inspection image; in order to further improve the detection efficiency of the target detection model when determining at least one first detection frame in the power grid inspection image according to the detection frame information, the model may be selected and trained according to the performance information of the device to be deployed with the target detection model, and therefore, with reference to fig. 3, on the basis of the embodiment shown in fig. 2, before step 1021, the following steps may be further included:
and step 1023, acquiring the performance information of the equipment to be deployed with the target detection model.
In the embodiment of the application, the device to be deployed with the target detection model may be, for example, a power grid inspection device, or a background server. Taking the power grid inspection equipment as an example, the performance information of the power grid inspection equipment may include any one of the following information: memory, processing speed, battery capacity, etc.
And 1024, selecting a classification model from a plurality of preset classification models according to the performance information, and taking the selected classification model as the target detection model.
In the embodiment of the application, if the device to be deployed with the target detection model is a power grid inspection device, because the power grid inspection device has a small memory, a low processing speed and a small battery capacity, a classification model with a small structure and a high training speed needs to be selected for the power grid inspection device, for example, a YOLOv3 model; if the device to be deployed with the target detection model is a background server, a classification model with a larger structure can be selected for the background server due to the larger memory and the higher processing speed of the background server.
Step 1025, obtaining training data, wherein the training data comprises: and the number of the power grid sample images is larger than a first preset number, and the corresponding target information is obtained.
And step 1026, training the target detection model by using the training data.
In this embodiment, in order to further increase the speed of the target detection model, a less sensitive model layer in the target detection model may be removed, and therefore, after step 1026, the method may further include the following steps: determining the sensitivity of each model layer in the target detection model to the power grid inspection image; acquiring a first model layer with the corresponding sensitivity smaller than a preset sensitivity threshold; and removing the first model layer in the target detection model.
In the embodiment of the application, the sensitivity of the model layer can be determined by combining the power grid inspection image, and the accuracy of the determined sensitivity is improved, so that the mode of determining the sensitivity of each model layer in the target detection model to the power grid inspection image by the power grid inspection device can be, for example, acquiring the target detection model and the first cutting model after removing the model layers aiming at each model layer in the target detection model; acquiring test data, wherein the test data comprises: the power grid sample images with the number larger than a second preset number and the corresponding target information; inputting the test data into a target detection model to obtain the test accuracy of the target detection model; inputting the test data into the first cutting model to obtain the test accuracy of the first cutting model; and determining the sensitivity of the model layer to the power grid inspection image according to the test accuracy of the target detection model and the test accuracy of the first cutting model.
In the embodiment of the application, the process of determining the sensitivity of the model layer to the power grid inspection image by the power grid inspection device according to the test accuracy of the target detection model and the test accuracy of the first cutting model may specifically be to calculate the sensitivity according to the test accuracy of the target detection model, the test accuracy of the first cutting model and a sensitivity calculation formula. The sensitivity calculation formula may be, for example, a difference calculation formula. The smaller the difference between the testing accuracy of the target detection model and the testing accuracy of the first cutting model is, the smaller the sensitivity is; the larger the difference, the greater the sensitivity.
In the embodiment of the application, after the first model layer in the target detection model is removed, the target detection model can be trained again to obtain a trained target detection model; and then deploying the trained target detection model to the equipment so that the equipment can process the power grid inspection image by adopting the target detection model. The method for deploying the trained target detection model to the device may be, for example, a lightweight deployment method, that is, the trained target detection model is packaged in a software development kit SDK manner, and the packaged kit is sent to the device in an online manner for deployment.
In addition, it should be noted that, in the embodiment of the present application, in the case that the power grid inspection apparatus may be a power grid inspection device or a background server, for example, the power grid inspection device may execute a model training process and a model using process at the same time; or the background server can simultaneously execute the model training process and the model using process; or the model training process can be executed by a background server, and the model using process can be executed by the power grid inspection equipment.
In the embodiment of the application, the power grid sample images with the number larger than the first preset number and the corresponding target information are adopted to train the target detection model, in the specific training process, the training can be performed in a deep learning mode, and compared with other machine learning methods, the deep learning method has the advantage that the performance of the deep learning on a large data set is better. When the target detection model is trained in a deep learning mode, the power grid sample image is used as the input of the target detection model, the target information corresponding to the power grid sample image is used as the output result, iterative training is carried out on the target detection model by continuously adjusting the parameters of the target detection model until the accuracy of the output result of the target detection model meets the preset threshold value, and the trained target detection model is obtained after training is finished.
In conclusion, the performance information of the equipment to be deployed with the target detection model is obtained; selecting a classification model from a plurality of preset classification models according to the performance information, and taking the selected classification model as a target detection model; acquiring training data, wherein the training data comprises: the power grid sample images are larger than a first preset number of power grid sample images and corresponding target information; training the target detection model by adopting training data; inputting the power grid inspection image into a preset target detection model, and acquiring detection frame information in the power grid inspection image; determining at least one first detection frame in the power grid inspection image according to the detection frame information, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the classification model can be selected and trained by combining the performance information of the equipment to be deployed with the target detection model, the target detection model is obtained, the accuracy of the target detection model is improved, the power grid inspection image can be captured according to the first detection frame, the interference of a non-target area in the power grid inspection image on the detection effect is avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
In order to realize the above embodiment, the embodiment of the application further provides a power grid inspection device.
Fig. 4 is a schematic diagram according to a fourth embodiment of the present application. As shown in fig. 4, the power grid inspection device 400 includes: a first capture module 410, a second capture module 420, a screenshot module 430, a third capture module 440, and a first determination module 450.
The first obtaining module 410 is configured to obtain a power grid inspection image to be detected;
a second obtaining module 420, configured to obtain at least one first detection frame in the power grid inspection image, where a detection score of the first detection frame is greater than or equal to a first score threshold;
the screenshot module 430 is configured to screenshot the power grid inspection image according to the at least one first detection frame to obtain a sampling image;
a third obtaining module 440, configured to obtain at least one second detection frame in the sample image, where a detection score of the second detection frame is greater than or equal to a second score threshold;
the first determining module 450 is configured to determine target information of the power grid inspection image according to the detection target of the at least one second detection frame.
As a possible implementation manner of the embodiment of the present application, on the basis of the embodiment shown in fig. 4, the screenshot module 430 includes: the system comprises a first determining unit and a screenshot unit;
the first determining unit is configured to determine, according to the at least one first detection box, a capture box covering the at least one first detection box;
and the screenshot unit is used for screenshot the power grid inspection image according to the screenshot frame to obtain the sampling image.
As a possible implementation manner of the embodiment of the present application, the second score threshold is greater than the first score threshold.
As a possible implementation manner of the embodiment of the present application, with reference to fig. 5, on the basis of the embodiment shown in fig. 4, the apparatus may further include: a second determination module 460 and a prompt module 470;
the second determining module 460 is configured to determine whether a target with a potential safety hazard exists in the power grid inspection image according to the target information of the power grid inspection image;
and the prompting module 470 is used for determining that potential safety hazards exist in the inspection position corresponding to the power grid inspection image in the power grid when the target with the potential safety hazards exists in the power grid inspection image and prompting the potential safety hazards.
As a possible implementation manner of the embodiment of the present application, the second obtaining module 420 includes: an acquisition unit and a second determination unit;
the acquisition unit is used for inputting the power grid inspection image into a preset target detection model and acquiring detection frame information in the power grid inspection image;
and the second determining unit is used for determining at least one first detection frame in the power grid inspection image according to the detection frame information.
As a possible implementation manner of the embodiment of the present application, the second obtaining module 420 further includes: a selection unit and a training unit;
the acquiring unit is further configured to acquire performance information of a device to which the target detection model is to be deployed;
the selection unit is used for selecting a classification model from a plurality of preset classification models according to the performance information and taking the selected classification model as the target detection model;
the obtaining unit is further configured to obtain training data, where the training data includes: the power grid sample images are larger than a first preset number of power grid sample images and corresponding target information;
and the training unit is used for training the target detection model by adopting the training data.
As a possible implementation manner of the embodiment of the present application, the second obtaining module 420 further includes: a removal unit;
the second determining unit is further configured to determine the sensitivity of each model layer in the target detection model to the power grid inspection image;
the acquiring unit is further configured to acquire a first model layer with a corresponding sensitivity smaller than a preset sensitivity threshold;
the removing unit is configured to remove the first model layer in the target detection model.
As a possible implementation manner of the embodiment of the application, the obtaining unit is further configured to obtain, for each model layer in the target detection model, the target detection model and the first clipping model after the model layer is removed;
the obtaining unit is further configured to obtain test data, where the test data includes: the power grid sample images with the number larger than a second preset number and the corresponding target information;
the obtaining unit is further configured to input the test data into the target detection model, and obtain the test accuracy of the target detection model;
the obtaining unit is further configured to input the test data into the first clipping model, and obtain the test accuracy of the first clipping model;
the second determining unit is further used for determining the sensitivity of the model layer to the power grid inspection image according to the testing accuracy of the target detection model and the testing accuracy of the first cutting model.
The power grid inspection device comprises a power grid inspection image acquisition unit, a power grid inspection image acquisition unit and a power grid inspection image acquisition unit, wherein the power grid inspection image acquisition unit acquires at least one first detection frame in the power grid inspection image to be detected, and the detection score of the first detection frame is greater than or equal to a first score threshold value; capturing the power grid inspection image according to at least one first detection frame to obtain a sampling image; acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; according to the detection target of the at least one second detection frame, the target information of the power grid inspection image is determined, the interference of a non-target area in the power grid inspection image on the detection effect can be avoided, and the detection accuracy of the target information of the power grid inspection image is improved.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 6, the electronic device is a block diagram of an electronic device according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the grid patrol method provided by the present application. A non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the power grid inspection method provided herein.
The memory 602, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the power grid inspection method in the embodiment of the present application (for example, the first obtaining module 410, the second obtaining module 420, the screenshot module 430, the third obtaining module 440, and the first determining module 450 shown in fig. 4). The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, that is, implementing the power grid inspection method in the above method embodiments.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the electronic device for power grid inspection, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, and these remote memories may be connected to the grid patrol electronics over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic equipment of the power grid inspection method can also comprise: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the grid patrol electronic device, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (18)
1. A power grid inspection method comprises the following steps:
acquiring a power grid inspection image to be detected;
acquiring at least one first detection frame in the power grid inspection image, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value;
capturing the power grid inspection image according to the at least one first detection frame to obtain a sampling image;
acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value; and the number of the first and second groups,
and determining the target information of the power grid inspection image according to the detection target of the at least one second detection frame.
2. The method according to claim 1, wherein the capturing the power grid inspection image according to the at least one first detection box to obtain a sampling image comprises:
according to the at least one first detection frame, determining a truncation frame covering the at least one first detection frame;
and capturing the power grid inspection image according to the capturing frame to obtain the sampling image.
3. The method of claim 1, wherein the second score threshold is greater than the first score threshold.
4. The method according to claim 1, wherein after determining the target information of the grid inspection image according to the detection target of the at least one second detection box, the method further comprises:
determining whether a target with potential safety hazard exists in the power grid inspection image according to the target information of the power grid inspection image;
when a target with potential safety hazards exists in the power grid inspection image, the potential safety hazards exist in the inspection position corresponding to the power grid inspection image in the power grid, and potential safety hazards are prompted.
5. The method of claim 1, wherein the obtaining at least one first detection box in the grid inspection image comprises:
inputting the power grid inspection image into a preset target detection model, and acquiring detection frame information in the power grid inspection image;
and determining at least one first detection frame in the power grid inspection image according to the detection frame information.
6. The method according to claim 5, wherein before inputting the power grid inspection image into a preset target detection model and acquiring detection frame information in the power grid inspection image, the method further comprises:
acquiring performance information of equipment to be deployed with a target detection model;
selecting a classification model from a plurality of preset classification models according to the performance information, and taking the selected classification model as the target detection model;
obtaining training data, wherein the training data comprises: the power grid sample images are larger than a first preset number of power grid sample images and corresponding target information;
and training the target detection model by adopting the training data.
7. The method of claim 6, wherein after training the target detection model using the training data, further comprising:
determining the sensitivity of each model layer in the target detection model to a power grid inspection image;
acquiring a first model layer with the corresponding sensitivity smaller than a preset sensitivity threshold;
and removing the first model layer in the target detection model.
8. The method of claim 7, wherein the determining the sensitivity of each model layer in the target detection model to grid inspection images comprises:
aiming at each model layer in the target detection model, acquiring the target detection model and a first cutting model after the model layer is removed;
obtaining test data, wherein the test data comprises: the power grid sample images with the number larger than a second preset number and the corresponding target information;
inputting the test data into the target detection model to obtain the test accuracy of the target detection model;
inputting the test data into the first cutting model to obtain the test accuracy of the first cutting model;
and determining the sensitivity of the model layer to the power grid inspection image according to the test accuracy of the target detection model and the test accuracy of the first cutting model.
9. An electric wire netting inspection device includes:
the first acquisition module is used for acquiring a power grid inspection image to be detected;
the second acquisition module is used for acquiring at least one first detection frame in the power grid inspection image, wherein the detection score of the first detection frame is greater than or equal to a first score threshold value;
the screen capture module is used for capturing the power grid inspection image according to the at least one first detection frame to obtain a sampling image;
the third acquisition module is used for acquiring at least one second detection frame in the sampling image, wherein the detection score of the second detection frame is greater than or equal to a second score threshold value;
and the first determining module is used for determining the target information of the power grid inspection image according to the detection target of the at least one second detection frame.
10. The apparatus of claim 9, wherein the screenshot module comprises: the system comprises a first determining unit and a screenshot unit;
the first determining unit is configured to determine, according to the at least one first detection box, a capture box covering the at least one first detection box;
and the screenshot unit is used for screenshot the power grid inspection image according to the screenshot frame to obtain the sampling image.
11. The apparatus of claim 9, wherein the second score threshold is greater than the first score threshold.
12. The apparatus of claim 9, further comprising: a second determining module and a prompting module;
the second determining module is used for determining whether a target with potential safety hazard exists in the power grid inspection image according to the target information of the power grid inspection image;
and the prompting module is used for determining that potential safety hazards exist in the inspection position corresponding to the power grid inspection image in the power grid when the target with the potential safety hazards exists in the power grid inspection image and prompting the potential safety hazards.
13. The apparatus of claim 9, wherein the second obtaining means comprises: an acquisition unit and a second determination unit;
the acquisition unit is used for inputting the power grid inspection image into a preset target detection model and acquiring detection frame information in the power grid inspection image;
and the second determining unit is used for determining at least one first detection frame in the power grid inspection image according to the detection frame information.
14. The apparatus of claim 13, wherein the second obtaining means further comprises: a selection unit and a training unit;
the acquiring unit is further configured to acquire performance information of a device to which the target detection model is to be deployed;
the selection unit is used for selecting a classification model from a plurality of preset classification models according to the performance information and taking the selected classification model as the target detection model;
the obtaining unit is further configured to obtain training data, where the training data includes: the power grid sample images are larger than a first preset number of power grid sample images and corresponding target information;
and the training unit is used for training the target detection model by adopting the training data.
15. The apparatus of claim 14, wherein the second obtaining means further comprises: a removal unit;
the second determining unit is further configured to determine the sensitivity of each model layer in the target detection model to the power grid inspection image;
the acquiring unit is further configured to acquire a first model layer with a corresponding sensitivity smaller than a preset sensitivity threshold;
the removing unit is configured to remove the first model layer in the target detection model.
16. The apparatus of claim 15, wherein,
the obtaining unit is further configured to obtain, for each model layer in the target detection model, the target detection model and the first cutting model from which the model layer is removed;
the obtaining unit is further configured to obtain test data, where the test data includes: the power grid sample images with the number larger than a second preset number and the corresponding target information;
the obtaining unit is further configured to input the test data into the target detection model, and obtain the test accuracy of the target detection model;
the obtaining unit is further configured to input the test data into the first clipping model, and obtain the test accuracy of the first clipping model;
the second determining unit is further used for determining the sensitivity of the model layer to the power grid inspection image according to the testing accuracy of the target detection model and the testing accuracy of the first cutting model.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501342.7A CN111832557A (en) | 2020-06-04 | 2020-06-04 | Power grid inspection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501342.7A CN111832557A (en) | 2020-06-04 | 2020-06-04 | Power grid inspection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111832557A true CN111832557A (en) | 2020-10-27 |
Family
ID=72897583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010501342.7A Pending CN111832557A (en) | 2020-06-04 | 2020-06-04 | Power grid inspection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832557A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633496A (en) * | 2020-12-18 | 2021-04-09 | 杭州海康威视数字技术股份有限公司 | Detection model processing method and device |
| CN113129303A (en) * | 2021-05-18 | 2021-07-16 | 广州市吉华勘测股份有限公司 | Automatic marking method and device for inspection pictures, storage medium and electronic equipment |
| CN113361413A (en) * | 2021-06-08 | 2021-09-07 | 南京三百云信息科技有限公司 | Mileage display area detection method, device, equipment and storage medium |
| CN114222181A (en) * | 2021-11-11 | 2022-03-22 | 北京达佳互联信息技术有限公司 | Image processing method, device, equipment and medium |
| CN115249339A (en) * | 2022-06-10 | 2022-10-28 | 广州中科云图智能科技有限公司 | River floating object identification system, method, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108307146A (en) * | 2017-12-12 | 2018-07-20 | 张宝泽 | A kind of ultra-high-tension power transmission line Security Vulnerability Detecting System and method |
| CN109376684A (en) * | 2018-11-13 | 2019-02-22 | 广州市百果园信息技术有限公司 | A kind of face critical point detection method, apparatus, computer equipment and storage medium |
| CN109711276A (en) * | 2018-12-06 | 2019-05-03 | 新华三技术有限公司 | A kind of deck detection method and device |
| US20190228519A1 (en) * | 2018-01-25 | 2019-07-25 | International Business Machines Corporation | Anomaly detection using image-based physical characterization |
| CN110127475A (en) * | 2019-03-27 | 2019-08-16 | 浙江新再灵科技股份有限公司 | A kind of method and system of elevator riding personnel classification and its boarding law-analysing |
| CN110705708A (en) * | 2019-10-10 | 2020-01-17 | 上海交通大学 | Compression method and device of convolutional neural network model and computer storage medium |
| CN111178192A (en) * | 2019-12-18 | 2020-05-19 | 北京达佳互联信息技术有限公司 | Position identification method and device for target object in image |
| CN111199230A (en) * | 2020-01-03 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Target detection method and device, electronic equipment and computer readable storage medium |
-
2020
- 2020-06-04 CN CN202010501342.7A patent/CN111832557A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108307146A (en) * | 2017-12-12 | 2018-07-20 | 张宝泽 | A kind of ultra-high-tension power transmission line Security Vulnerability Detecting System and method |
| US20190228519A1 (en) * | 2018-01-25 | 2019-07-25 | International Business Machines Corporation | Anomaly detection using image-based physical characterization |
| CN109376684A (en) * | 2018-11-13 | 2019-02-22 | 广州市百果园信息技术有限公司 | A kind of face critical point detection method, apparatus, computer equipment and storage medium |
| CN109711276A (en) * | 2018-12-06 | 2019-05-03 | 新华三技术有限公司 | A kind of deck detection method and device |
| CN110127475A (en) * | 2019-03-27 | 2019-08-16 | 浙江新再灵科技股份有限公司 | A kind of method and system of elevator riding personnel classification and its boarding law-analysing |
| CN110705708A (en) * | 2019-10-10 | 2020-01-17 | 上海交通大学 | Compression method and device of convolutional neural network model and computer storage medium |
| CN111178192A (en) * | 2019-12-18 | 2020-05-19 | 北京达佳互联信息技术有限公司 | Position identification method and device for target object in image |
| CN111199230A (en) * | 2020-01-03 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Target detection method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| SHI CHEN等: "Shallowing Deep Networks： Layer-Wise Pruning Based on Feature Representations", IEEE, pages 3048 - 3056 * |
| 林刚;王波;彭辉;王晓阳;陈思远;张黎明;: "基于改进Faster-RCNN的输电线巡检图像多目标检测及定位", 电力自动化设备, no. 05, pages 220 - 225 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633496A (en) * | 2020-12-18 | 2021-04-09 | 杭州海康威视数字技术股份有限公司 | Detection model processing method and device |
| CN112633496B (en) * | 2020-12-18 | 2023-08-08 | 杭州海康威视数字技术股份有限公司 | Processing method and device for detection model |
| CN113129303A (en) * | 2021-05-18 | 2021-07-16 | 广州市吉华勘测股份有限公司 | Automatic marking method and device for inspection pictures, storage medium and electronic equipment |
| CN113361413A (en) * | 2021-06-08 | 2021-09-07 | 南京三百云信息科技有限公司 | Mileage display area detection method, device, equipment and storage medium |
| CN114222181A (en) * | 2021-11-11 | 2022-03-22 | 北京达佳互联信息技术有限公司 | Image processing method, device, equipment and medium |
| CN114222181B (en) * | 2021-11-11 | 2024-03-12 | 北京达佳互联信息技术有限公司 | Image processing method, device, equipment and medium |
| CN115249339A (en) * | 2022-06-10 | 2022-10-28 | 广州中科云图智能科技有限公司 | River floating object identification system, method, equipment and storage medium |
| CN115249339B (en) * | 2022-06-10 | 2024-05-28 | 广州中科云图智能科技有限公司 | River float recognition system, method, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832557A (en) | Power grid inspection method and device, electronic equipment and storage medium | |
| CN111757098B (en) | Debugging method and device after installation of intelligent face monitoring camera, camera and medium | |
| CN111178323B (en) | Group behavior recognition method, device, equipment and storage medium based on video | |
| CN111783225A (en) | Method and device for processing scenes in simulation system | |
| CN111688580B (en) | Method and device for picking up sound by intelligent rearview mirror | |
| CN110717933B (en) | Post-processing method, device, equipment and medium for moving object missed detection | |
| CN111738072A (en) | Training method and device of target detection model and electronic equipment | |
| CN112153343B (en) | Elevator safety monitoring method and device, monitoring camera and storage medium | |
| CN111753701A (en) | Violation detection method, device and equipment of application program and readable storage medium | |
| KR20220149508A (en) | Event detection method, apparatus, electronic device and readable recording medium | |
| CN111738263A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN111611767B (en) | Verification method and device | |
| CN111773721A (en) | Game screen display method and device, electronic device and storage medium | |
| CN110866504B (en) | Method, device and equipment for acquiring annotation data | |
| CN112101288A (en) | Method, device and equipment for detecting wearing of safety helmet and storage medium | |
| CN111783644B (en) | Detection method, detection device, detection equipment and computer storage medium | |
| CN111783600B (en) | Face recognition model training method, device, equipment and medium | |
| CN110995687B (en) | Cat pool equipment identification method, device, equipment and storage medium | |
| CN112560772A (en) | Face recognition method, device, equipment and storage medium | |
| CN112270303A (en) | Image recognition method and device and electronic equipment | |
| CN112149828A (en) | Operator precision detection method and device based on deep learning framework | |
| CN111581518A (en) | Information pushing method and device | |
| CN111783591B (en) | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and recording medium | |
| CN111967299B (en) | Unmanned aerial vehicle inspection method, unmanned aerial vehicle inspection device, unmanned aerial vehicle inspection equipment and storage medium | |
| CN113361455B (en) | Training method of face counterfeit identification model, related device and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |