Safety helmet wearing intelligent monitoring method, device and equipment and medium

Abstract

The invention discloses a safety helmet wearing intelligent monitoring method, device and equipment and a medium, and the method comprises the steps: judging whether a thermal imaging image accords with a monitoring condition or not, and if yes, determining corresponding target image collection equipment and sending an image collection instruction, acquiring an initial image, intercepting to obtain a target contour image, and performing identification according to the wearing identification model to obtain a wearing identification result; and if the identification result is that the safety helmet is not worn, alarm prompt information is sent to a corresponding alarm. According to the safety helmet wearing intelligent monitoring method, whether the thermal imaging image meets the monitoring condition or not is judged firstly, if the thermal imaging image does not meet the monitoring condition, no person exists in the surface area, monitoring is not needed, and therefore the efficiency of monitoring a large number of areas is greatly improved; and if the monitoring condition is met, acquiring a corresponding initial image, and intercepting and identifying the initial image in combination with the thermal imaging image so as to improve the accuracy of identifying whether the person in the area wears the safety helmet or not.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, and in particular to an intelligent monitoring method, device, equipment and medium for helmet wearing. Background Art

[0002] During the operation of nuclear power plant equipment, operators need to wear safety helmets in real time to prevent hazards; however, some operators do not wear safety helmets due to insufficient safety awareness, and administrators need to verify whether the operators are wearing safety helmets to ensure the safe production of nuclear power plants. However, in the actual application process, due to the large area of the nuclear power plant, administrators cannot verify the operators in each area in a timely and effective manner. Although in the prior art, images of each area can be obtained through monitors, and the monitors are viewed by surveillance personnel to verify whether the operators are wearing safety helmets, due to the large number of areas, it is difficult for the surveillance personnel to efficiently monitor a large number of areas. Therefore, there is a problem that the helmet wearing situation in multiple areas of a nuclear power plant cannot be efficiently monitored in the prior art methods. Summary of the Invention

[0003] Embodiments of the present invention provide an intelligent monitoring method, device, equipment and medium for helmet wearing, aiming to solve the problem that the helmet wearing situation in multiple areas of a nuclear power plant cannot be efficiently monitored in the prior art methods.

[0004] In a first aspect, embodiments of the present invention provide an intelligent monitoring method for helmet wearing. The method is applied to a management server, and the management server establishes network connections with each thermal imaging sensor, each image acquisition device and each alarm to realize the transmission of data information. The method includes:

[0005] Obtain the thermal imaging images detected by each of the thermal imaging sensors and determine whether each thermal imaging image meets a preset monitoring condition;

[0006] If the thermal imaging image meets the monitoring condition, determine, according to a preset device registration form, an image acquisition device that matches the thermal imaging image as a corresponding target image acquisition device;

[0007] Send an image acquisition instruction to the target image acquisition device to obtain the feedback initial image;

[0008] Intercept a corresponding target contour image from the initial image according to a preset image interception rule and the thermal imaging image;

[0009] Identify each target contour image according to a preset wearing recognition model to obtain a corresponding wearing recognition result;

[0010] If the helmet wearing recognition result is that the safety helmet is not worn, an alarm prompt message is sent to the alarm corresponding to the helmet wearing recognition result according to the device registration form.

[0011] In a second aspect, an embodiment of the present invention further provides a smart safety helmet wearing monitoring device, which is configured in a management server. The management server establishes network connections with each thermal imaging sensor, each image acquisition device, and each alarm to realize data information transmission. The device is used to execute the smart safety helmet wearing monitoring method described in the first aspect above. The device includes:

[0012] An image judgment unit, which is used to obtain the thermal imaging images detected by each thermal imaging sensor and judge whether each thermal imaging image meets the preset monitoring conditions.

[0013] A target image acquisition device obtaining unit, which is used to, if the thermal imaging image meets the monitoring conditions, determine the image acquisition device that matches the thermal imaging image according to the preset device registration form as the corresponding target image acquisition device.

[0014] An acquisition instruction sending unit, which is used to send an image acquisition instruction to the target image acquisition device to obtain the feedback initial image.

[0015] A target contour image obtaining unit, which is used to intercept the corresponding target contour image from the initial image according to the preset image interception rule and the thermal imaging image.

[0016] A wearing recognition result obtaining unit, which is used to recognize each target contour image according to the preset wearing recognition model to obtain the corresponding wearing recognition result.

[0017] An alarm prompt message sending unit, which is used to, if the wearing recognition result is that the safety helmet is not worn, send an alarm prompt message to the alarm corresponding to the wearing recognition result according to the device registration form.

[0018] In a third aspect, an embodiment of the present invention further provides a computer device. The device includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory complete communication with each other through the communication bus.

[0019] The memory is used to store a computer program.

[0020] The processor is used to, when executing the program stored in the memory, implement the steps of the smart safety helmet wearing monitoring method described in the first aspect above.

[0021] Fourthly, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent monitoring method for helmet wearing as described in the first aspect above are implemented.

[0022] An embodiment of the present invention provides an intelligent monitoring method, device, equipment and medium for helmet wearing. The method includes: judging whether a thermal imaging image meets the monitoring conditions. If it meets the conditions, determining the corresponding target image acquisition device and sending an image acquisition instruction, obtaining an initial image, intercepting the target contour image, and then performing identification according to a wearing recognition model to obtain a wearing recognition result; if the recognition result is that the helmet is not worn, sending an alarm prompt message to the corresponding alarm. In the above intelligent monitoring method for helmet wearing, it is first judged whether the thermal imaging image meets the monitoring conditions. If the thermal imaging image does not meet the monitoring conditions, it means that there is no one in the surface area and no monitoring is required, thus greatly improving the monitoring efficiency for a large number of areas; if it meets the monitoring conditions, the corresponding initial image is obtained and the initial image is intercepted and recognized in combination with the thermal imaging image to improve the recognition accuracy of whether the personnel in the area wear helmets, that is, the application effect of efficiently monitoring the helmet wearing situation in multiple areas of a nuclear power plant is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a flowchart of the intelligent monitoring method for helmet wearing provided by an embodiment of the present invention;

[0025] Figure 2 It is a schematic diagram of the application scenario of the intelligent monitoring method for helmet wearing provided by an embodiment of the present invention;

[0026] Figure 3 It is a schematic diagram of the application effect of the intelligent monitoring method for helmet wearing provided by an embodiment of the present invention;

[0027] Figure 4 It is another schematic diagram of the application effect of the intelligent monitoring method for helmet wearing provided by an embodiment of the present invention;

[0028] Figure 5 It is a schematic block diagram of the intelligent monitoring device for helmet wearing provided by an embodiment of the present invention;

[0029] Figure 6 It is a schematic block diagram of the computer equipment provided by an embodiment of the present invention. Detailed implementation manners

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0032] It should also be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0033] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0034] The embodiments of the present invention application provide a smart monitoring method for helmet wearing. This method is applied to the management server 10. The management server 10 executes the stored software program to implement the above smart monitoring method for helmet wearing; the management server 10 can be a server side configured in the machine room of a nuclear power plant for smart monitoring of whether personnel in the area wear helmets. The management server 10 can be a server device such as a cluster server or a parallel processing server. Please refer to Figure 2, as shown in the figure, the management server 10 establishes network connections with each thermal imaging sensor 20, each image acquisition device 30, and each alarm 40 to achieve data information transmission. Among them, the thermal imaging sensor 20 is also a sensor that senses and images objects based on heat generation, such as a thermopile thermal imaging sensor; the higher the temperature of an object, the higher the intensity of the infrared rays it emits, and by detecting the intensity of the infrared rays emitted by the object, corresponding sensing imaging can be performed. The image acquisition device 30 is also a device used to perform visible light imaging on each area within the nuclear power plant, such as a camera. The alarm 40 is also a device configured to give alarm prompts in each area of the nuclear power plant, such as a loudspeaker. There are multiple areas within the nuclear power plant, and at least one thermal imaging sensor 20, at least one image acquisition device 30, and at least one alarm 40 are correspondingly configured in each area.

[0035] Such as Figure 1 shown, this method includes steps S110 to S160.

[0036] S110. Obtain the thermal imaging images detected by each of the thermal imaging sensors and determine whether each thermal imaging image meets a preset monitoring condition.

[0037] Obtain the thermal imaging images detected by each of the thermal imaging sensors and determine whether each thermal imaging image meets a preset monitoring condition. First, the thermal imaging images obtained by each thermal imaging sensor for thermal imaging of different areas can be obtained, and it is determined whether each thermal imaging image meets the monitoring condition. If the monitoring condition is met, it indicates that there are people in the area where the thermal imaging sensor performs imaging detection; if the monitoring condition is not met, it indicates that there are no people in the area where the thermal imaging sensor performs imaging detection.

[0038] In a specific embodiment, step S110 includes sub-steps: obtain the hot spot areas in each of the thermal imaging images according to the temperature threshold in the monitoring condition; determine whether the hot spot areas in the thermal imaging images conform to the hot spot characteristics in the monitoring condition to determine whether the thermal imaging images meet the monitoring condition.

[0039] Specifically, the corresponding hot spot areas can be obtained according to the temperature threshold in the monitoring condition. In the thermal imaging image, the closer the color of a pixel point is to red, the higher the temperature value of the pixel point; the closer the color of a pixel point is to blue, the lower the temperature value of the pixel point; the color value of the pixel point corresponds to a temperature value. It can be correspondingly determined whether the temperature value of each pixel point in the thermal imaging image is greater than the temperature threshold, and the continuous area formed by the pixel points with temperature values greater than the temperature threshold is obtained as the hot spot area. For example, the temperature threshold can be set to 35 °C. Further determine whether the hot spot area conforms to the corresponding hot spot characteristics. Since there are other heating devices in the nuclear power plant, in order to avoid misjudgment, the hot spot area can be further judged according to the hot spot characteristics.

[0040] In a specific embodiment, determining whether the hot spot regions in the thermal imaging image conform to the hot spot characteristics in the monitoring conditions includes: determining whether the uniformity of each hot spot region in the thermal imaging image is not less than the uniformity threshold of the hot spot characteristics; determining whether the coverage area of each hot spot region in the thermal imaging image is within the reference area range of the hot spot characteristics; if the uniformity of any hot spot region in the thermal imaging image is not less than the uniformity threshold and the coverage area is within the reference area range, it is determined that the hot spot regions in the thermal imaging image conform to the hot spot characteristics; if the uniformity of each hot spot region in the thermal imaging image is less than the uniformity threshold or the coverage area is not within the reference area range, it is determined that the hot spot regions in the thermal imaging image do not conform to the hot spot characteristics.

[0041] Specifically, the uniformity of the hot spot region can be calculated, and the uniformity can be calculated correspondingly through formula (1):

[0042]

[0043] where J is the uniformity of a certain hot spot region obtained by calculation, N is the number of pixel points in the hot spot region, T c is the average value of the temperature values of all pixel points in the hot spot region, and T i is the temperature value of the i-th pixel point in the hot spot region. The larger the obtained uniformity value, the more balanced the temperature values are everywhere in the hot spot region.

[0044] Determine whether the calculated uniformity of the hot spot region is not less than the set uniformity threshold in the hot spot characteristics. If it is not less than, further determine whether the coverage area of this hot spot region is within the reference area range of the hot spot characteristics. Since the human body needs to occupy a certain space, if the area of the hot spot region is too large or too small, it does not conform to the human body characteristics.

[0045] If the uniformity of the same hot spot region is not less than the uniformity threshold and the coverage area of this hot spot region is within the reference area range, it can be determined that this hot spot region is the target hot spot region, that is, this hot spot region conforms to the hot spot characteristics. If the uniformity of the hot spot region is less than the uniformity threshold, or the coverage area of this hot spot region is not within the reference area range, it can be determined that this hot spot region does not conform to the hot spot characteristics.

[0046] S120. If the thermal imaging image meets the monitoring conditions, determine the image acquisition device that matches the thermal imaging image according to the pre-set device registration form as the corresponding target image acquisition device.

[0047] If the thermal imaging image meets the monitoring conditions, determine the image acquisition device that matches the thermal imaging image according to the pre-set device registration form, and use it as the corresponding target image acquisition device. If the thermal imaging image meets the monitoring conditions, it indicates that there is human activity in the area corresponding to the thermal imaging image, and the target image acquisition device that matches the thermal imaging image can be obtained. If the thermal imaging image does not meet the monitoring conditions, it indicates that there is no human activity in the area corresponding to the thermal imaging image, and step S110 can be executed again after a certain period of time (for example, the period is set to 30 seconds), so as to achieve periodic acquisition of thermal imaging images and perform judgments.

[0048] In a specific embodiment, step S120 includes sub-steps: obtaining the irradiation area corresponding to the thermal imaging sensor to which the thermal imaging image belongs in the device registration form; obtaining the image acquisition device whose shooting area coincides with the irradiation area in the device registration form as the corresponding target image acquisition device.

[0049] Each thermal imaging sensor collects a thermal imaging image. The device registration form includes the registration information of components such as the configured thermal imaging sensors, image acquisition devices, and alarms. Specifically, it includes the sensor number, installation location, and irradiation area of the thermal imaging sensor, etc. At the same time, it also includes the device number, installation location, and shooting area of the image acquisition device, and also includes the equipment number, installation location, and coverage area of the alarm. The thermal imaging sensor and the image acquisition device can be set at the same position in the monitoring area of the nuclear power plant, and the irradiation direction of the thermal imaging sensor is set to be the same as the shooting direction of the image acquisition device, so as to ensure that the two devices can collect images in the same direction.

[0050] Then, the irradiation area corresponding to the thermal imaging sensor to which the thermal imaging image belongs in the device registration form can be obtained, and the image acquisition device whose shooting area coincides with the irradiation area can be obtained as the target image acquisition device. Then, for each thermal imaging image containing the target hot spot area, a target image acquisition device can be correspondingly obtained.

[0051] S130. Send an image acquisition instruction to the target image acquisition device to obtain the feedback initial image.

[0052] Send an image acquisition instruction to the target image acquisition device to obtain the feedback initial image. Send an image acquisition instruction to the target image acquisition device, and the target image acquisition device will perform visible light image acquisition according to the acquisition instruction and feedback the initial image to the management server.

[0053] S140. Intercept the corresponding target contour image from the initial image according to the pre-set image interception rule and the thermal imaging image.

[0054] According to the preset image cropping rule and the thermal imaging image, the corresponding target contour image is cropped from the initial image. Further, according to the image cropping rule and the thermal imaging image including the target hot spot area, the initial image is cropped to obtain the partial image that needs to be recognized as the target contour image.

[0055] In a specific embodiment, step S140 includes sub-steps: obtaining the hot spot area that meets the hot spot characteristics in the thermal imaging image as the target hot spot area; cropping the hot spot area image corresponding to the target hot spot area from the initial image; performing pixel dissolution on the hot spot area image according to the regional contour of the target hot spot area and the image cropping rule to obtain the corresponding initial contour; and cropping the image located within the initial contour from the hot spot area image according to the initial contour as the corresponding target contour image.

[0056] Specifically, the hot spot area that meets the hot spot characteristics in the thermal imaging image can be obtained as the target hot spot area, and further, the hot spot area image corresponding to the target hot spot area can be cropped from the initial image. The thermal imaging image and the initial image are superimposed and combined, and the initial image is cropped according to the outer boundary of the target hot spot area to obtain the hot spot area image.

[0057] Further, perform pixel dissolution on the hot spot area image according to the regional contour of the target hot spot area and the image cropping rule, and obtain the initial contour reflecting the human body boundary through pixel dissolution. Then, perform image cropping from the hot spot area image through the initial contour, that is, obtain the pixel points included in the initial contour in the hot spot area image, and these pixel points are combined as the target contour image.

[0058] In a specific embodiment, the performing pixel dissolution on the hot spot area image according to the regional contour of the target hot spot area and the image cropping rule to obtain the corresponding initial contour includes: calculating the contrast value of each pixel point in the hot spot area image; calculating the minimum vertical distance between each pixel point in the hot spot area image and the regional contour of the target hot spot area; calculating the contour coefficient corresponding to each pixel point according to the contour coefficient calculation formula in the image cropping rule for the minimum vertical distance and the contrast value; and performing pixel dissolution on the hot spot area image according to the pixel dissolution ratio in the image cropping rule and the contour coefficient of each pixel point to obtain the remaining pixel points after dissolution as the corresponding initial contour.

[0059] The specific steps of performing pixel dissolution include calculating the contrast value of each pixel point in the hot spot area, and the specific calculation formula of the contrast value is shown in formula (2):

[0060]

[0061] Among them, D is the calculated contrast value corresponding to a certain pixel, M is the number of pixels closely surrounding this pixel, r1 is the first surrounding coefficient, S j is the pixel value of the j-th pixel surrounding this pixel, and S0 is the pixel value of this pixel; G is the number of pixels surrounding this pixel with one layer of pixels spaced apart, r2 is the first surrounding coefficient, S k is the pixel value of the k-th pixel among the outer pixels with one layer of pixels spaced apart from this pixel. The pixel value is also the RGB value of a pixel, and the pixel value of a pixel contains three groups of values corresponding to three color channels. It can be set that the value of r1 is G / M, and the value of r2 is M / G.

[0062] Further, draw a perpendicular line between the pixel and the regional contour of the target hot spot area, and obtain the length of the shortest perpendicular line among them as the minimum vertical distance between the pixel and the regional contour. Specifically, as Figure 3 shown, for point P, one or more perpendicular lines perpendicular to the regional contour can be drawn. If there are multiple perpendicular lines, the intersection points (i.e., the feet of the perpendiculars) of different perpendicular lines with the regional contour are different. Determine the intersection point of the shortest perpendicular line with the regional contour as Q, and obtain the distance between P and Q to get the minimum vertical distance corresponding to point P, denoted as length L.

[0063] Furthermore, the minimum vertical distance and contrast value corresponding to a pixel can be calculated according to the contour coefficient calculation formula, so as to obtain the contour coefficient of this pixel. Then the contour coefficient comprehensively reflects the contrast value and the degree of fit between this point and the regional contour of the target hot spot area. The contour coefficient calculation formula can be as shown in formula (3):

[0064]

[0065] Among them, X is the calculated contour coefficient, D is the contrast value of the pixel, and L is the minimum vertical distance of the pixel.

[0066] The pixels in the hot spot area image can be sorted according to the contour coefficient. The larger the contour coefficient, the higher the ranking. Then, according to the pixel dissolution ratio in the image cropping rule, the sorted pixels are sequentially cropped. For example, if the pixel dissolution ratio is 0.15, then 15% of the pixels with higher rankings are cropped proportionally as the remaining pixels after dissolution, and the remaining pixels after dissolution are correspondingly combined into the initial contour.

[0067] S150. Identify each target contour image according to the preset wearing recognition model to obtain the corresponding wearing recognition result.

[0068] Identify each target contour image according to a preset wearing identification model to obtain corresponding wearing identification results. To identify whether the operator in the target contour image wears a safety helmet accurately, the wearing identification model can be used to identify each obtained target contour image, so as to obtain the wearing identification result of whether a safety helmet is worn. Then, each target contour image can correspond to a wearing identification result. An initial image may contain one or more target contour images. The technical method of this application focuses on the process of identifying a target contour image, and the identification of multiple target contour images included in the same initial image can be inferred by analogy.

[0069] In a specific embodiment, step S150 includes sub-steps: obtaining the morphological vertices in the target contour image and calculating the morphological center point of the morphological vertices; obtaining the dispersion coefficient of the corresponding pixel region corresponding to the morphological vertices in the target contour image; determining the morphological vertex with the smallest dispersion coefficient in the target contour image as the target vertex; obtaining the target limb image corresponding to the target vertex in the target contour image; judging whether the target limb image contains a block corresponding to the preset color in the wearing identification model; if the target limb image contains a block corresponding to the preset color, judging whether the outer contour of the block matches the preset contour in the wearing identification model; if the outer contour of the block matches the preset contour, judging whether the convex direction of the outer contour of the block matches the vertex direction corresponding to the target vertex; the vertex direction is the direction from the morphological center point to the target vertex; if the convex direction of the outer contour matches the vertex direction, obtain the wearing identification result of wearing a safety helmet.

[0070] The morphological vertices in the target contour image can be obtained. The morphological vertices are also the vertices of the convex parts formed by protruding outward from the central area of the target contour image. As Figure 4 shown by points A, B, C, D, and E in. Further calculate the dispersion coefficient of the corresponding pixel region corresponding to the morphological vertices in the target contour image. The pixel regions between the connection points of the morphological vertices and the central area of the target contour image can be intercepted respectively, and the dispersion coefficient of the pixel points in the pixel region can be calculated correspondingly. For example, the pixel region corresponding to point B is the left arm region, the pixel region corresponding to point A is the head region, and the pixel region corresponding to point C is the right arm region. The steps of calculating the dispersion coefficient include calculating the average value of the coordinate positions of all pixel points in each pixel region to obtain the center point of each pixel region, calculating the geometric distance between all pixel points in the pixel region and this center point, accumulating them, and then dividing by the total number of pixel points in the pixel region, so as to obtain the dispersion coefficient of the pixel region. The larger the dispersion coefficient, the more dispersed the positions of the pixel points in the pixel region; the smaller the dispersion coefficient, the more concentrated the positions of the pixel points in the pixel region.

[0071] After calculating the discrete coefficients corresponding to each morphological vertex, further determine that the morphological vertex with the smallest discrete coefficient in the target contour image is the target vertex, and obtain the target limb image corresponding to the target vertex in the target contour image, that is, obtain the pixel region corresponding to the target vertex as the target limb image.

[0072] Further determine whether the target limb image contains a block corresponding to a preset color in the wearing recognition model. The color of the safety helmet is usually a fixed color such as red, white, or yellow. Therefore, the corresponding preset color can be set based on the color of the safety helmet. Determine whether the target limb image contains pixel points whose pixel values are within the pixel value range corresponding to the preset color. If it contains pixel points within the pixel value range corresponding to the preset color, it is determined that the target limb image contains a block corresponding to the preset color; otherwise, it is determined that the target limb image does not contain a block corresponding to the preset color.

[0073] If the target limb image contains a block corresponding to the preset color, further determine whether the outer contour of the block matches the preset contour in the wearing recognition model. The preset contour can be a semi-circular contour, so it can be determined whether the outer contour of the block matches the preset contour. Specifically, use the preset contour as a layer mask to calculate the coincidence degree between the block and the preset contour. If the coincidence degree is greater than the corresponding coincidence degree threshold, it is determined that the block matches the preset contour; otherwise, it is determined that the block does not match the preset contour.

[0074] If the outer contour of the block matches the preset contour, further determine whether the convex direction of the outer contour of the block matches the vertex direction corresponding to the target vertex. Specifically, the average value of the positions of each morphological vertex can be calculated to obtain the corresponding reference coordinate point, such as the S point in Figure 4 Further, draw a normal line pointing to the target vertex starting from the S point, and the direction of this normal line is the vertex direction. Determine whether the convex direction matches the vertex direction of the target vertex. Specifically, the absolute value of the angle between the convex direction and the vertex direction of the target vertex can be calculated, and determine whether the absolute value of this angle is less than the preset angle threshold; if the absolute value of the angle is less than the angle threshold, it is determined that the convex direction matches the vertex direction of the target vertex; otherwise, it is determined that the convex direction does not match the vertex direction of the target vertex.

[0075] If the convex direction of the outer contour matches the vertex direction, the wearing recognition result of the target contour image corresponding to the outer contour is that the safety helmet is worn. If the target limb image does not contain a block corresponding to the preset color, or the outer contour does not match the preset contour, or the convex direction of the outer contour does not match the corresponding vertex direction, the wearing recognition result of the target contour image corresponding to the outer contour is that the safety helmet is not worn.

[0076] S160. If the wearing recognition result is that the safety helmet is not worn, send an alarm prompt message to the alarm corresponding to the wearing recognition result according to the device registration form.

[0077] If the wearing recognition result is that the safety helmet is not worn, send an alarm prompt message to the alarm corresponding to the wearing recognition result according to the device registration form. If the wearing recognition result of any target contour image is that the safety helmet is not worn, obtain the shooting area of the initial image to which the target contour image belongs, and obtain the alarm whose coverage area coincides with the shooting area. This alarm is also the alarm corresponding to the current wearing recognition result, and send an alarm prompt message to this alarm to remind the personnel in the corresponding area. The alarm prompt message can be a voice prompt message, for example, the content is "Please ask the operators in the area to wear safety helmets in time."

[0078] In the intelligent safety helmet wearing monitoring method disclosed in the above embodiment, the method includes: judging whether the thermal imaging image meets the monitoring conditions. If it meets, determine the corresponding target image acquisition device and send an image acquisition instruction, obtain the initial image, intercept the target contour image, and then perform recognition according to the wearing recognition model to obtain the wearing recognition result; if the recognition result is that the safety helmet is not worn, send an alarm prompt message to the corresponding alarm. In the above intelligent safety helmet wearing monitoring method, first judge whether the thermal imaging image meets the monitoring conditions. If the thermal imaging image does not meet the monitoring conditions, it means there is no one in the surface area and there is no need to monitor, thus greatly improving the monitoring efficiency for a large number of areas; if it meets the monitoring conditions, obtain the corresponding initial image and combine it with the thermal imaging image to intercept and recognize the initial image, so as to improve the recognition accuracy of whether the personnel in the area wear safety helmets, that is, achieve the application effect of efficiently monitoring the wearing situation of safety helmets in multiple areas of the nuclear power plant.

[0079] An embodiment of the present invention further provides an intelligent safety helmet wearing monitoring device. This intelligent safety helmet wearing monitoring device can be configured in a management server and is used to execute any embodiment of the foregoing intelligent safety helmet wearing monitoring method. Specifically, please refer to Figure 5 , Figure 5 which is a schematic block diagram of the intelligent safety helmet wearing monitoring device provided by the embodiment of the present invention.

[0080] As shown Figure 5 in the figure, the intelligent monitoring device 100 for helmet wearing includes an image judgment unit 110, a target image acquisition device obtaining unit 120, a collection instruction sending unit 130, a target contour image obtaining unit 140, a wearing recognition result obtaining unit 150, and an alarm prompt information sending unit 160.

[0081] The image judgment unit 110 is configured to obtain the thermal imaging images detected by each of the thermal imaging sensors and determine whether each thermal imaging image meets a preset monitoring condition.

[0082] The target image acquisition device obtaining unit 120 is configured to, if the thermal imaging image meets the monitoring condition, determine an image acquisition device matching the thermal imaging image according to a preset device registration form as a corresponding target image acquisition device.

[0083] The collection instruction sending unit 130 is configured to send an image collection instruction to the target image acquisition device to obtain the feedback initial image.

[0084] The target contour image obtaining unit 140 is configured to intercept a corresponding target contour image from the initial image according to a preset image interception rule and the thermal imaging image.

[0085] The wearing recognition result obtaining unit 150 is configured to recognize each target contour image according to a preset wearing recognition model to obtain a corresponding wearing recognition result.

[0086] The alarm prompt information sending unit 160 is configured to, if the wearing recognition result is that the helmet is not worn, send an alarm prompt information to an alarm corresponding to the wearing recognition result according to the device registration form.

[0087] In the intelligent monitoring device for helmet wearing provided by the embodiment of the present invention, the above-mentioned intelligent monitoring method for helmet wearing is applied to judge whether the thermal imaging image meets the monitoring condition. If it meets, the corresponding target image acquisition device is determined and an image acquisition instruction is sent, the initial image is obtained and intercepted to obtain the target contour image, and then recognition is performed according to the wearing recognition model to obtain the wearing recognition result. If the recognition result is that the helmet is not worn, an alarm prompt information is sent to the corresponding alarm. The above-mentioned intelligent monitoring method for helmet wearing first judges whether the thermal imaging image meets the monitoring condition. If the thermal imaging image does not meet the monitoring condition, it means that there is no one in the surface area and there is no need to perform monitoring, thus greatly improving the efficiency of monitoring a large number of areas. If it meets the monitoring condition, the corresponding initial image is obtained and the initial image is intercepted and recognized in combination with the thermal imaging image to improve the recognition accuracy of whether the personnel in the area wear helmets, that is, the application effect of efficiently monitoring the helmet wearing situation in multiple areas of the nuclear power plant is achieved.

[0088] The above intelligent monitoring device for helmet wearing can be implemented in the form of a computer program, which can run on a computer device as shown below. Figure 6 shown.

[0089] Please refer to Figure 6 , Figure 6 which is a schematic block diagram of the computer device provided by an embodiment of the present invention. The computer device may be a management server for executing the intelligent monitoring method for helmet wearing to intelligently monitor whether personnel in a region wear helmets.

[0090] Refer to Figure 6 , the computer device 500 includes a processor 502, a memory, and a communication interface 505 connected through a communication bus 501. Among them, the memory may include a storage medium 503 and an internal memory 504.

[0091] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it can cause the processor 502 to execute the intelligent monitoring method for helmet wearing. Among them, the storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0092] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0093] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, it can cause the processor 502 to execute the intelligent monitoring method for helmet wearing.

[0094] The communication interface 505 is used for network communication, such as providing the transmission of data information, etc. Those skilled in the art can understand that Figure 6 the structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0095] Among them, the processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above intelligent monitoring method for helmet wearing.

[0096] Those skilled in the art can understand that Figure 6The embodiments of the computer device shown do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are the same as those in Figure 6 the shown embodiment and will not be described in detail here.

[0097] It should be understood that in the embodiments of the present invention, the processor 502 may be a central processing unit (CPU), and this processor 502 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0098] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps included in the above-mentioned intelligent monitoring method for helmet wearing are implemented.

[0099] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described in detail here. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0100] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, or units with the same function can be aggregated into one unit. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections between each other can be indirect couplings or communication connections through some interfaces, devices, or units, or can be electrical, mechanical, or other forms of connection.

[0101] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0102] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0103] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0104] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent monitoring method for helmet wearing, characterized in that, The method is applied to a management server, which establishes network connections with various thermal imaging sensors, various image acquisition devices, and various alarms to achieve data information transmission. The method includes: Obtaining the thermal imaging images detected by each of the thermal imaging sensors and determining whether each thermal imaging image meets a preset monitoring condition; If the thermal imaging image meets the monitoring condition, determining, according to a preset device registration form, an image acquisition device that matches the thermal imaging image as a corresponding target image acquisition device; Sending an image acquisition instruction to the target image acquisition device to obtain a feedback initial image; Intercepting a corresponding target contour image from the initial image according to a preset image interception rule and the thermal imaging image; Identifying each target contour image according to a preset wearing identification model to obtain a corresponding wearing identification result; If the wearing identification result is that a safety helmet is not worn, sending an alarm prompt message to the alarm corresponding to the wearing identification result according to the device registration form.

2. The intelligent monitoring method for helmet wearing according to claim 1, wherein, The obtaining the thermal imaging images detected by each of the thermal imaging sensors and determining whether each thermal imaging image meets a preset monitoring condition includes: Obtaining a hot spot area in each of the thermal imaging images according to a temperature threshold in the monitoring condition; Determining whether the hot spot area in the thermal imaging image conforms to a hot spot feature in the monitoring condition to determine whether the thermal imaging image meets the monitoring condition.

3. The intelligent monitoring method for safety helmet wearing according to claim 2, wherein, The determining whether the hot spot area in the thermal imaging image conforms to a hot spot feature in the monitoring condition includes: Determining whether the uniformity of each hot spot area in the thermal imaging image is not less than a uniformity threshold of the hot spot feature; Determining whether the coverage area of each hot spot area in the thermal imaging image is within a reference area interval of the hot spot feature; If the uniformity of any hot spot area in the thermal imaging image is not less than the uniformity threshold and the coverage area is within the reference area interval, determining that the hot spot area in the thermal imaging image conforms to the hot spot feature; If the uniformity of each hot spot area in the thermal imaging image is less than the uniformity threshold or the coverage area is not within the reference area interval, determining that the hot spot area in the thermal imaging image does not conform to the hot spot feature.

4. The intelligent monitoring method for safety helmet wearing according to claim 1, wherein The determining, according to a preset device registration form, an image acquisition device that matches the thermal imaging image as a corresponding target image acquisition device includes: Obtaining an irradiation area corresponding to the thermal imaging sensor to which the thermal imaging image belongs in the device registration form; Obtaining an image acquisition device whose shooting area coincides with the irradiation area in the device registration form as a corresponding target image acquisition device.

5. The intelligent monitoring method for safety helmet wearing according to claim 2 or 3, characterized in that, The intercepting a corresponding target contour image from the initial image according to a preset image interception rule and the thermal imaging image includes: Obtaining a hot spot area that conforms to the hot spot feature in the thermal imaging image as a target hot spot area; Intercepting a hot spot area image corresponding to the target hot spot area from the initial image; Perform pixel dissolution on the hotspot area image according to the regional contour of the target hotspot area and the image cropping rule to obtain a corresponding initial contour; Crop the image within the initial contour from the hotspot area image according to the initial contour as the corresponding target contour image.

6. The intelligent monitoring method for helmet wearing according to claim 5, characterized in that, The performing pixel dissolution on the hotspot area image according to the regional contour of the target hotspot area and the image cropping rule to obtain a corresponding initial contour includes: Calculate the contrast value of each pixel point in the hotspot area image; Calculate the minimum vertical distance between each pixel point in the hotspot area image and the regional contour of the target hotspot area; Calculate the minimum vertical distance and the contrast value according to the contour coefficient calculation formula in the image cropping rule to obtain the contour coefficient corresponding to each pixel point; Perform pixel dissolution on the hotspot area image according to the pixel dissolution ratio in the image cropping rule and the contour coefficient of each pixel point to obtain the combination of remaining pixel points after dissolution as the corresponding initial contour.

7. The intelligent monitoring method for helmet wearing according to claim 2 or 3, characterized in that, The performing recognition on each target contour image according to a preset wearing recognition model to obtain a corresponding wearing recognition result includes: Obtain the morphological vertices in the target contour image and calculate the morphological center point of the morphological vertices; Obtain the discrete coefficient of the corresponding pixel area corresponding to the morphological vertices in the target contour image; Determine the morphological vertex with the smallest discrete coefficient in the target contour image as the target vertex; Obtain the target limb image corresponding to the target vertex in the target contour image; Judge whether the target limb image contains a block corresponding to the preset color in the wearing recognition model; If the target limb image contains a block corresponding to the preset color, judge whether the outer contour of the block matches the preset contour in the wearing recognition model; If the outer contour of the block matches the preset contour, judge whether the convex direction of the outer contour of the block matches the vertex direction corresponding to the target vertex; the vertex direction is the direction from the morphological center point to the target vertex; If the convex direction of the outer contour matches the vertex direction, obtain the wearing recognition result of wearing a safety helmet.

8. An intelligent monitoring device for helmet wearing, characterized in that, The device is configured in a management server, and the management server establishes network connections with each thermal imaging sensor, each image acquisition device, and each alarm to realize data information transmission. The device is used to execute the intelligent monitoring method for safety helmet wearing according to any one of claims 1-7. The device includes: An image judgment unit, configured to obtain the thermal imaging images detected by each thermal imaging sensor and judge whether each thermal imaging image meets the preset monitoring conditions; A target image acquisition device acquisition unit, configured to, if the thermal imaging image meets the monitoring conditions, determine the image acquisition device matching the thermal imaging image according to a preset device registration form as the corresponding target image acquisition device; An acquisition instruction sending unit, configured to send an image acquisition instruction to the target image acquisition device to obtain the feedback initial image; A target contour image acquisition unit, configured to intercept a corresponding target contour image from the initial image according to a preset image interception rule and the thermal imaging image; A wearing recognition result acquisition unit, configured to recognize each target contour image according to a preset wearing recognition model to obtain a corresponding wearing recognition result; An alarm prompt information sending unit, configured to, if the wearing recognition result is not wearing a safety helmet, send alarm prompt information to an alarm corresponding to the wearing recognition result according to the device registration form.

9. A computer device, characterized in that, The device includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus; The memory is used to store a computer program; The processor is configured to, when executing the program stored on the memory, implement the steps of the intelligent monitoring method for safety helmet wearing described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent monitoring method for safety helmet wearing described in any one of claims 1-7.

Images