Safety access method and system for electric power multi-scene application

Abstract

The embodiment of the invention provides a safety access method and system for electric power multi-scene application, and belongs to the technical field of operation and maintenance of electric power scenes. The method comprises the following steps: determining a current reference image; comparing the reference image with a preset standard image to obtain a state evaluation matrix; selecting an image recognition component according to the state evaluation matrix; performing comparative assignment on the selected image recognition components to obtain the weight of each image recognition component; obtaining a current face image to be recognized; recognizing the face image by adopting the selected image recognition assembly to obtain an output value of each image recognition assembly; and determining a final identification result according to the weight and the output value. According to the method and the system, adaptive adjustment can be carried out according to different environmental conditions, so that intelligent adaptation to diversified power scenes is realized.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance technology of power scenarios, and in particular to a method and system for secure access to power multi-scenario applications. Background Art

[0002] In the modern society where artificial intelligence is becoming more and more popular, face recognition systems are widely used in various scenarios. At the site of power construction, face recognition systems are mostly used for on-site access control or personnel clocking in. However, due to the diverse characteristics of power construction scenes, the lighting of the environment, the complexity of background factors, and the acquisition status of the image acquisition device itself will become factors that restrict the face recognition system.

[0003] First, the ambient lighting conditions at power construction sites vary significantly, from strong direct light to dim indoor lighting. Different lighting conditions will have different degrees of impact on the acquisition of face images. For example, under strong light, faces may appear shadowed and highlighted, while under weak light conditions, the image may become blurred and difficult to recognize. Secondly, the background of power construction sites is usually complex, with various mechanical equipment, cables, tools and other objects. These background elements may be confused with facial features, resulting in recognition errors. In addition, the acquisition status of the image acquisition device is also a key factor. If the angle, focal length or resolution of the camera is not set properly, it will also affect the clarity of the image and the accuracy of recognition. In summary, the diverse environmental factors at power construction sites and the status of image acquisition devices jointly affect the performance and reliability of face recognition systems. Therefore, when applying face recognition systems, these influencing factors must be fully considered to ensure their effectiveness and accuracy in actual use. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for secure access to multi-scenario applications of electric power, which can maintain stable face recognition accuracy in diverse scenarios at the electric power site.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for secure access to power multi-scenario applications, including: Determine the current reference image; Comparing the reference image with a preset standard image to obtain a state assessment matrix; selecting an image recognition component according to the state assessment matrix; Comparatively assigning values ​​to the selected image recognition components to obtain a weight of each image recognition component; Get the current face image to be recognized; Using the selected image recognition components to recognize the face image to obtain an output value of each image recognition component; The final recognition result is determined according to the weight and the output value.

[0006] Optionally, comparing the reference image with a preset standard image to obtain a state assessment matrix includes: Dividing the reference image into a plurality of recognition areas using a preset anchor frame; For each of the identification areas, a corresponding calibration value is calculated respectively, wherein a calibration value of 1 indicates that the corresponding identification area is successfully calibrated, and a calibration value of 0 indicates that the corresponding identification area fails to be calibrated; Counting the number of calibration values ​​being 1; Calculating a calibration ratio according to the number of calibration values ​​1 and the number of identification areas; Determining whether the calibration ratio is greater than or equal to a preset first threshold; In the case where it is determined that the calibration ratio is greater than or equal to the first threshold, determining the row and column coordinates of each calibration value according to the actual position of the recognition area to construct the state evaluation matrix; When it is determined that the calibration ratio is less than the first threshold, it is determined that the current recognition fails.

[0007] Optionally, the anchor frame includes a plurality of squares.

[0008] Optionally, for each of the identified areas, a corresponding calibration value is calculated respectively, including: Divide the recognition area into four rectangular frames of equal size; Performing a binarization operation on the image within each rectangular frame; Calculate the corresponding grayscale ratios according to the results of the binarization operation; Determining whether the grayscale ratio is within a corresponding standard grayscale ratio interval; In the case where it is determined that the grayscale ratio is within the standard grayscale ratio interval, determining the calibration value to be 1; When it is determined that the grayscale ratio is outside the standard grayscale ratio interval, the calibration value is determined to be 0.

[0009] Optionally, the corresponding grayscale ratios are calculated according to the results of the binarization operation, including: The grayscale ratio is calculated according to formula (1): , (1) in, For the Line The grayscale ratio of the rectangular box, The area whose grayscale is greater than the preset value. is the area whose grayscale is less than or equal to the preset value.

[0010] Optionally, the standard grayscale ratio interval is and .

[0011] Optionally, comparatively assigning values ​​to the selected image recognition components to obtain a weight of each image recognition component includes: Determining a confidence value for each of the image recognition components respectively; The weight is calculated according to the confidence value.

[0012] Optionally, calculating the weight according to the confidence value includes: The weight is calculated according to formula (2): , (2) in, For the The weights of the image recognition components, For the The confidence value of the image recognition component, The number of components to identify for the selected image.

[0013] On the other hand, the present invention also provides a security access system for power multi-scenario applications, the system comprising a processor, and the processor is configured to execute any of the methods described above.

[0014] Through the above technical solution, the embodiment of the present invention provides a method and system for safe access to multi-scenario applications of electric power. The method and system select image recognition components based on the state evaluation matrix of the current scene to achieve adaptive adjustment to different environmental conditions. Compared with the prior art, the method and system provided by the present invention can achieve intelligent adaptation to diversified electric power scenarios because they can be adaptively adjusted to different environmental conditions.

[0015] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of a method for secure access to power multi-scenario applications according to an embodiment of the present invention; Figure 2 is an example diagram of a reference image according to an embodiment of the present invention; Figure 3 is a flow chart of a method for obtaining a state assessment matrix according to one embodiment of the present invention; Figure 4 is a flow chart of a method for calculating a calibration value according to one embodiment of the present invention. DETAILED DESCRIPTION

[0017] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0018] like Figure 1 The figure is a flow chart of a method for secure access to power multi-scenario applications according to an embodiment of the present invention. Figure 1 In the method, the method may include the following steps: In step S10, a current reference image is determined; In step S11, a comparison is performed between the reference image and the preset standard image to obtain a state evaluation matrix; In step S12, an image recognition component is selected according to the state evaluation matrix; In step S13, comparative values ​​are assigned to the selected image recognition components to obtain the weight of each image recognition component; In step S14, a face image to be recognized is obtained; In step S15, the facial image is recognized using the selected image recognition components to obtain an output value of each image recognition component; In step S16, the final recognition result is determined according to the weight and the output value.

[0019] In this Figure 1 In the method shown, step S10 may be used to determine a current reference image. The reference image may be used to determine a test image of the current state of the image acquisition device. In one example of the present invention, the reference image may be, for example, Figure 2 shown.

[0020] Step S11 may be used to compare the reference image with the preset standard image to obtain a state evaluation matrix. Specifically, in one example of the present invention, step S11 may further include: Figure 3 The steps shown. Figure 3 In the step S11, the step S11 may further include the following steps: In step S20, the reference image is divided into a plurality of recognition areas using a preset anchor frame; In step S21, for each recognition area, a corresponding calibration value is calculated, wherein a calibration value of 1 indicates that the corresponding recognition area is calibrated successfully, and a calibration value of 0 indicates that the corresponding recognition area fails to be calibrated; In step S22, the number of calibration values ​​1 is counted; In step S23, a calibration ratio is calculated according to the number of calibration values ​​1 and the number of identification areas; In step S24, it is determined whether the calibration ratio is greater than or equal to a preset first threshold; In step S25, when it is determined that the calibration ratio is greater than or equal to the first threshold, the row and column coordinates of each calibration value are determined according to the actual position of the recognition area to construct a state evaluation matrix; In step S26, when it is determined that the calibration ratio is less than the first threshold, it is determined that the current recognition fails.

[0021] In this Figure 3 In the method shown, step S20 can be used to divide the reference image into multiple recognition areas using a preset anchor frame. The anchor frame can be in various forms known to those skilled in the art. In this example, the anchor frame can include multiple squares.

[0022] Step S21 is used to calculate the corresponding calibration value for each identification area. The specific calculation method of the calibration value can be various forms known to those skilled in the art. In one example of the present invention, the calculation method of the calibration value can include: Figure 4 In the steps shown in Figure 4 In the method for calculating the calibration value, the calibration value may include the following steps: In step S30, the recognition area is divided into four rectangular frames of equal size; In step S31, a binarization operation is performed on the image in each rectangular frame; In step S32, the corresponding grayscale ratios are calculated according to the results of the binarization operation. Specifically, in this example, the grayscale ratio can be calculated using the following formula (1): , (1) in, For the Line The grayscale ratio of the rectangular box, The area whose grayscale is greater than the preset value. It is the area whose grayscale is less than or equal to the preset value.

[0023] In step S33, it is determined whether the grayscale ratio is within the corresponding standard grayscale ratio interval. Considering the recognition error of the grayscale area, the standard grayscale ratio interval can be, for example and .

[0024] In step S34, when it is determined that the grayscale ratio is within the standard grayscale ratio range, the calibration value is determined to be 1; In step S35, when it is determined that the grayscale ratio is outside the standard grayscale ratio interval, the calibration value is determined to be 0.

[0025] Step S12 may be used to select an image recognition component according to the state evaluation matrix. The image recognition component may include multiple image recognition models set for different weather and lighting conditions. Considering the actual recognition accuracy of each image recognition model, corresponding confidence values ​​may be set respectively.

[0026] Step S13 may be used to comparatively assign values ​​to the selected image recognition components to obtain the weight of each image recognition component. Specifically, in this embodiment, the weight may be calculated using the following formula (2): , (2) in, For the The weights of the image recognition components, For the The confidence value of the image recognition component, The number of components to identify for the selected image.

[0027] On the other hand, the present invention also provides a security access system for power multi-scenario applications, the system comprising a processor, the processor being configured to execute any of the above methods. Specifically, the method may include the following steps: In step S10, a current reference image is determined; In step S11, a comparison is performed between the reference image and the preset standard image to obtain a state evaluation matrix; In step S12, an image recognition component is selected according to the state evaluation matrix; In step S13, comparative values ​​are assigned to the selected image recognition components to obtain the weight of each image recognition component; In step S14, a face image to be recognized is obtained; In step S15, the facial image is recognized using the selected image recognition components to obtain an output value of each image recognition component; In step S16, the final recognition result is determined according to the weight and the output value.

[0028] In this Figure 1In the method shown, step S10 may be used to determine a current reference image. The reference image may be used to determine a test image of the current state of the image acquisition device. In one example of the present invention, the reference image may be, for example, Figure 2 shown.

[0029] Step S11 may be used to compare the reference image with the preset standard image to obtain a state evaluation matrix. Specifically, in one example of the present invention, step S11 may further include: Figure 3 The steps shown. Figure 3 In the step S11, the step S11 may further include the following steps: In step S20, the reference image is divided into a plurality of recognition areas using a preset anchor frame; In step S21, for each recognition area, a corresponding calibration value is calculated, wherein a calibration value of 1 indicates that the corresponding recognition area is calibrated successfully, and a calibration value of 0 indicates that the corresponding recognition area fails to be calibrated; In step S22, the number of calibration values ​​1 is counted; In step S23, a calibration ratio is calculated according to the number of calibration values ​​1 and the number of identification areas; In step S24, it is determined whether the calibration ratio is greater than or equal to a preset first threshold; In step S25, when it is determined that the calibration ratio is greater than or equal to the first threshold, the row and column coordinates of each calibration value are determined according to the actual position of the recognition area to construct a state evaluation matrix; In step S26, when it is determined that the calibration ratio is less than the first threshold, it is determined that the current recognition fails.

[0030] In this Figure 3 In the method shown, step S20 can be used to divide the reference image into multiple recognition areas using a preset anchor frame. The anchor frame can be in various forms known to those skilled in the art. In this example, the anchor frame can include multiple squares.

[0031] Step S21 is used to calculate the corresponding calibration value for each identification area. The specific calculation method of the calibration value can be various forms known to those skilled in the art. In one example of the present invention, the calculation method of the calibration value can include: Figure 4 In the steps shown in Figure 4 In the method for calculating the calibration value, the calibration value may include the following steps: In step S30, the recognition area is divided into four rectangular frames of equal size; In step S31, a binarization operation is performed on the image in each rectangular frame; In step S32, the corresponding grayscale ratios are calculated according to the results of the binarization operation. Specifically, in this example, the grayscale ratio can be calculated using the following formula (1): , (1) in, For the Line The grayscale ratio of the rectangular box, The area whose grayscale is greater than the preset value. It is the area whose grayscale is less than or equal to the preset value.

[0032] In step S33, it is determined whether the grayscale ratio is within the corresponding standard grayscale ratio interval. Considering the recognition error of the grayscale area, the standard grayscale ratio interval can be, for example and .

[0033] In step S34, when it is determined that the grayscale ratio is within the standard grayscale ratio range, the calibration value is determined to be 1; In step S35, when it is determined that the grayscale ratio is outside the standard grayscale ratio interval, the calibration value is determined to be 0.

[0034] Step S12 may be used to select an image recognition component according to the state evaluation matrix. The image recognition component may include multiple image recognition models set for different weather and lighting conditions. Considering the actual recognition accuracy of each image recognition model, corresponding confidence values ​​may be set respectively.

[0035] Step S13 may be used to comparatively assign values ​​to the selected image recognition components to obtain the weight of each image recognition component. Specifically, in this embodiment, the weight may be calculated using the following formula (2): , (2) in, For the The weights of the image recognition components, For the The confidence value of the image recognition component, The number of components to identify for the selected image.

[0036] Through the above technical solution, the embodiment of the present invention provides a method and system for safe access to multi-scenario applications of electric power. The method and system select image recognition components based on the state evaluation matrix of the current scene to achieve adaptive adjustment to different environmental conditions. Compared with the prior art, the method and system provided by the present invention can achieve intelligent adaptation to diversified electric power scenarios because they can be adaptively adjusted to different environmental conditions.

[0037] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0038] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0039] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0040] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0041] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0042] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0043] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0044] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0045] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A secure access method for multi-scenario power applications, characterized in that: The method comprises: Determine the current reference image; Comparing the reference image with a preset standard image to obtain a state assessment matrix; selecting an image recognition component according to the state assessment matrix; Comparatively assigning values ​​to the selected image recognition components to obtain a weight of each image recognition component; Get the current face image to be recognized; Using the selected image recognition components to recognize the face image to obtain an output value of each image recognition component; The final recognition result is determined according to the weight and the output value.

2. The method according to claim 1, characterized in that Comparing the reference image with a preset standard image to obtain a state assessment matrix includes: Dividing the reference image into a plurality of recognition areas using a preset anchor frame; For each of the identification areas, a corresponding calibration value is calculated respectively, wherein a calibration value of 1 indicates that the corresponding identification area is successfully calibrated, and a calibration value of 0 indicates that the corresponding identification area fails to be calibrated; Counting the number of calibration values ​​being 1; Calculating a calibration ratio according to the number of calibration values ​​1 and the number of identification areas; Determining whether the calibration ratio is greater than or equal to a preset first threshold; In the case where it is determined that the calibration ratio is greater than or equal to the first threshold, determining the row and column coordinates of each calibration value according to the actual position of the recognition area to construct the state evaluation matrix; When it is determined that the calibration ratio is less than the first threshold, it is determined that the current recognition fails.

3. The method according to claim 2, characterized in that The anchor frame includes a plurality of squares.

4. The method according to claim 2, characterized in that: For each of the identified areas, a corresponding calibration value is calculated respectively, including: Dividing the identification area into four rectangular frames of equal size; Performing a binarization operation on the image within each rectangular frame; Calculate the corresponding grayscale ratios according to the results of the binarization operation; Determining whether the grayscale ratio is within a corresponding standard grayscale ratio interval; In the case where it is determined that the grayscale ratio is within the standard grayscale ratio interval, determining the calibration value to be 1; When it is determined that the grayscale ratio is outside the standard grayscale ratio interval, the calibration value is determined to be 0.

5. The method according to claim 4, characterized in that According to the results of the binarization operation, the corresponding grayscale ratios are calculated respectively, including: The grayscale ratio is calculated according to formula (1): ，（1） in, For the Line The grayscale ratio of the rectangular box, The area whose grayscale is greater than the preset value. is the area whose grayscale is less than or equal to the preset value.

6. The method according to claim 4, characterized in that The standard grayscale ratio interval is and .

7. The method according to claim 1, characterized in that Comparatively assigning values ​​to the selected image recognition components to obtain the weight of each image recognition component includes: Determining a confidence value for each of the image recognition components respectively; The weight is calculated according to the confidence value.

8. The method according to claim 7, characterized in that Calculating the weight according to the confidence value includes: The weight is calculated according to formula (2): ，（2） in, For the The weights of the image recognition components, For the The confidence value of the image recognition component, The number of components to identify for the selected image.

9. A security access system for power multi-scenario applications, characterized in that: The system comprises a processor configured to execute the method according to any one of claims 1 to 8.

Images