Personnel safety detection system and method, storage medium and electronic equipment

Abstract

The invention provides a personnel safety detection system and method, a storage medium and electronic equipment, and relates to the technical field of safety detection. The personnel safety detection system comprises an entrance confirmation device which comprises a first camera and a personnel identity binding module; the plurality of second cameras are configured at different positions of the offshore photovoltaic construction site; the safety detection equipment is used for acquiring a video frame image which is acquired by the second camera and contains the portrait of the target person, determining a safety detection area of the target person in the video frame image, determining a safety detection feasibility score of the target person, performing safety classification on the safety detection area under the condition that the score is greater than or equal to a score threshold value, and outputting the safety classification result; and determining contour features of the target personnel, and determining personnel basic information bound with the contour features. According to the invention, personnel safety detection on the construction site can be comprehensively and timely realized.

Description

Background Art

[0002] The construction site is complex, especially for offshore photovoltaic construction sites. In addition to the safety issues that may arise at general construction sites, there are also safety risks related to the sea. When personnel enter the construction site, they can ensure safety as much as possible by wearing safety equipment.

[0003] At present, the safety of personnel entering the construction site is mainly ensured by pre-entry training and pre-entry safety equipment inspection. However, the construction site is large, and after personnel enter the construction site, such manual inspection and supervision can no longer fully and timely discover personnel safety problems.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a personnel safety detection system and method, a storage medium and an electronic device, thereby at least to a certain extent overcoming the situation where manual safety inspections at construction sites cannot comprehensively and timely discover personnel safety issues.

[0006] According to a first aspect of the present disclosure, there is provided a personnel safety detection system applied to an offshore photovoltaic construction site, comprising: an entry confirmation device, comprising a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is located at the entrance of the offshore photovoltaic construction site and is wearing safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features; a plurality of second cameras are configured at different positions of the offshore photovoltaic construction site; a safety detection device is used to obtain a video frame image containing a portrait of a target person collected by the second camera, use a first neural network to determine a safety detection area of ​​the target person in the video frame image and determine a safety detection feasibility score of the target person based on the safety detection area, and when the safety detection feasibility score is greater than or equal to a score threshold, use a second neural network to perform safety classification on the safety detection area, and when the result of the safety classification indicates that the target person has a safety hazard, determine the contour features of the target person, and determine the basic information of the person bound to the contour features of the target person; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

[0007] Optionally, the entry confirmation device also includes an information entry module; the information entry module is used to respond to the information entry operation of the personnel, determine the basic information of the personnel, and pass the basic information of the personnel to the personnel identity binding module; wherein the information entry operation includes a combination of one or more of the personnel QR code scanning operation, the personnel work permit scanning operation, the personnel information typing operation, the face recognition operation, and the personnel fingerprint scanning operation.

[0008] Optionally, in the case where the target personnel's route includes an offshore construction site, the safety detection area includes one or more of a safety helmet area, a life jacket area, a work shoe area, a collar area, a cuff area, and a trouser leg area.

[0009] Optionally, the safety detection device is used to identify the target person in the video frame image using a first neural network to determine the coordinate information of the key points of safety detection, and determine the safety detection area based on the coordinate information of the key points of safety detection.

[0010] Optionally, the security detection device is also used to discard the video frame image when the security detection feasibility score is less than the score threshold; and when the video frame image of the target person is discarded a predetermined number of times, the security detection device issues a security alarm for the target person.

[0011] Optionally, after determining the basic personnel information bound to the target person's profile features, the security detection device is also used to obtain the target person's communication method from the target person's basic personnel information, and send a first security reminder message for the target person to the target person through the target person's communication method.

[0012] Optionally, when the target person has one or more companions, after determining the basic information of the person bound to the profile features of the target person, the security detection device is also used to determine the communication method of the companions, and send a second security reminder message for the target person to the companions through the communication method of the companions.

[0013] According to a second aspect of the present disclosure, a personnel safety detection method applied to an offshore photovoltaic construction site is provided, the personnel safety detection method is applied to a personnel safety detection system including an entry confirmation device, the entry confirmation device including a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is located at the entrance of the offshore photovoltaic construction site and is wearing safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features; wherein the personnel safety detection method comprises: obtaining a video frame image containing a portrait of a target person collected by a second camera; wherein the second camera is configured at different positions of the offshore photovoltaic construction site; using a first neural network to determine a safety detection area of ​​the target person in the video frame image and determining a safety detection feasibility score of the target person based on the safety detection area; when the safety detection feasibility score is greater than or equal to a score threshold, using a second neural network to perform safety classification on the safety detection area; when the result of the safety classification indicates that the target person has a safety hazard, determining the contour features of the target person, and determining the basic information of the person bound to the contour features of the target person; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

[0014] According to a third aspect of the present disclosure, there is provided a personnel safety detection device applied to an offshore photovoltaic construction site, the personnel safety detection device being applied to a personnel safety detection system including an entry confirmation device, the entry confirmation device including a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is located at the entrance of the offshore photovoltaic construction site and has worn safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features; wherein the personnel safety detection device includes: an image acquisition module, used to obtain a video frame image containing a portrait of a target person collected by a second camera; In the invention, the second camera is arranged at different positions of the offshore photovoltaic construction site; the scoring determination module is used to determine the safety detection area of ​​the target person in the video frame image by using the first neural network and determine the safety detection feasibility score of the target person based on the safety detection area; the safety classification module is used to use the second neural network to perform safety classification on the safety detection area when the safety detection feasibility score is greater than or equal to the scoring threshold; the personnel information determination module is used to determine the contour features of the target person and determine the basic personnel information bound to the contour features of the target person when the result of the safety classification indicates that the target person has a safety hazard; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

[0015] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the personnel safety detection method applied to an offshore photovoltaic construction site is implemented.

[0016] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; the processor is configured to implement the above-mentioned personnel safety detection method applied to an offshore photovoltaic construction site by executing the executable instructions.

[0017] In the technical solutions provided in some embodiments of the present disclosure, on the one hand, personnel safety detection at offshore photovoltaic construction sites is realized through computer vision technology based on image recognition, without the need for manual safety inspections and supervision, and personnel safety issues can be discovered comprehensively and promptly while saving manpower; on the other hand, the present disclosure takes into account that personnel wearing safety equipment cannot accurately implement solutions such as face recognition. In this case, in order to bind the portrait with the basic information of the personnel, the contour features of the personnel in the image are used. The computing power consumption of extracting the contour features is small, which solves the problem of insufficient face recognition accuracy in the scene, and the contour features of the personnel are sufficient to achieve the purpose of information matching in this process; on the other hand, the present disclosure adopts a two-stage safety evaluation strategy, and further safety classification is performed when the safety detection possibility score is greater than or equal to the score threshold, avoiding the problem of resource consumption caused by performing complex safety detection processes on images that are not suitable for safety classification, and improving the response efficiency of safety detection.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0020] Figure 1 The structure diagram of a personnel safety detection system applied to an offshore photovoltaic construction site according to an exemplary embodiment of the present disclosure is schematically shown.

[0021] Figure 2 A schematic diagram showing the area included in the safety detection area of ​​an embodiment of the present disclosure.

[0022] Figure 3 A schematic diagram showing a first neural network including units according to an embodiment of the present disclosure is shown.

[0023] Figure 4 A schematic diagram of sending a safety reminder message according to an embodiment of the present disclosure is shown.

[0024] Figure 5 A flow chart of a personnel safety detection method applied to an offshore photovoltaic construction site according to an exemplary embodiment of the present disclosure is schematically shown.

[0025] Figure 6 A block diagram of a personnel safety detection device applied to an offshore photovoltaic construction site according to an exemplary embodiment of the present disclosure is schematically shown.

[0026] Figure 7 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0028] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps may be decomposed, while some steps may be combined or partially combined, so the actual execution order may change according to the actual situation. In addition, all the terms "first", "second", etc. below are only for the purpose of distinction and should not be used as limitations of the present disclosure.

[0030] Figure 1 The schematic diagram shows an architecture diagram of a personnel safety detection system applied to an offshore photovoltaic construction site according to an exemplary embodiment of the present disclosure. Figure 1 The personnel safety detection system 1 of the embodiment of the present disclosure may include an entry confirmation device 11, and the entry confirmation device 11 may include a first camera 111 and a personnel identity binding module 112. In addition to the entry confirmation device 11, the personnel safety detection system 1 may also include a second camera 12 and a safety detection device 13, wherein the number of the second cameras 12 may be multiple and configured at different locations of the offshore photovoltaic construction site.

[0031] The first camera 111 can be used to collect an initial image of a person wearing safety equipment at the entrance of the offshore photovoltaic construction site. The present disclosure does not limit the safety equipment, such as a safety helmet, a life jacket, work shoes, etc.

[0032] The personnel identity binding module 112 can be used to obtain the initial image captured by the first camera 111, extract the outline features of the personnel in the initial image, determine the basic information of the personnel, and bind the basic information of the personnel to the outline features. The present disclosure does not limit the outline extraction algorithm, for example, the Canny algorithm, Fourier transform and other processing methods can be used.

[0033] In an exemplary embodiment of the present disclosure, the outline features of a person may at least characterize one or more of the person's height, fatness, and limb lengths.

[0034] The basic information of a person includes one or more of the person's name, gender, age, position, whether the person is an outsider, the organization to which the outsider belongs, and the person's communication method.

[0035] It can be understood that the binding of basic personnel information with profile features in the present disclosure refers to establishing a one-to-one correspondence between basic personnel information and profile features.

[0036] Regarding the method of determining the basic information of the personnel, the entry confirmation device 11 may further include an information entry module. The information entry module is used to respond to the information entry operation of the personnel, determine the basic information of the personnel, and transmit the basic information of the personnel to the personnel identity binding module 112. Specifically, the above-mentioned information entry operation may include a combination of one or more of a personnel QR code scanning operation, a personnel work card scanning operation, a personnel information input operation, a face recognition operation, and a personnel fingerprint scanning operation.

[0037] According to some embodiments of the present disclosure, while entering the personnel information, the entry confirmation device 11 controls the first camera 111 to capture the above-mentioned initial image of the personnel, so as to correspond the contour features of the personnel in the image with the basic information of the personnel through time.

[0038] The following is an explanation of the process of the safety detection device 13 performing safety detection.

[0039] First, a video frame image containing a portrait of a target person captured by the second camera may be obtained.

[0040] In an exemplary embodiment of the present disclosure, the target person is any person entering the offshore photovoltaic construction site. The second camera can be any camera configured at the offshore photovoltaic construction site. The safety detection device 13 can be connected to the second camera in a wired or wireless manner to obtain a video frame image containing a portrait of the target person taken by the second camera.

[0041] Next, the first neural network may be used to determine a safety detection area for the target person in the video frame image and determine a safety detection feasibility score for the target person based on the safety detection area.

[0042] In an exemplary embodiment of the present disclosure, the safety detection area is an area on the target person's body for checking whether it is safe, that is, by detecting and analyzing the normal safety detection area, it can be determined whether the target person has safety hazards. In the case where the target person's route includes an offshore construction site, the safety detection area includes one or more of a helmet area, a life jacket area, a work shoe area, a collar area, a cuff area, and a trouser leg area. Figure 2 A schematic diagram schematically shows the area included in the safety detection area of ​​an embodiment of the present disclosure.

[0043] The security detection feasibility score represents the feasibility of the security detection. It is understandable that the higher the score, the higher the credibility of using the security detection area for security analysis; the lower the score, the lower the credibility of using the security detection area for security analysis. The disclosed embodiment may, for example, set the range of the security detection feasibility score to 1-10 or 1-100.

[0044] In an exemplary embodiment of the present disclosure, a first neural network is used to determine a safety detection area and a safety detection feasibility score. Figure 3 The first neural network may include a key point coordinate determination unit 31, a safety detection area determination unit 32 and a safety detection feasibility scoring unit 33.

[0045] Specifically, the key point coordinate determination unit 31 can identify the target person in the video frame image to determine the coordinate information of the key points of security detection. The security detection area determination unit 32 can determine the security detection area according to the coordinate information of the key points of security detection. The security detection feasibility scoring unit 33 can analyze the security detection area to determine the security detection feasibility score.

[0046] The first neural network of the embodiment of the present disclosure can be implemented based on a convolutional neural network, and the present disclosure does not limit the structure and training process of the convolutional neural network. Among them, for the part of the safety detection feasibility scoring unit 33, the analysis items involved include one or more of the degree of occlusion, the size of the safety detection area, and clarity. It can be understood that the smaller the degree of occlusion, the higher the score; the larger the size, the higher the score; the higher the clarity, the higher the score.

[0047] Subsequently, the safety detection feasibility score is compared with the scoring threshold, and when the safety detection feasibility score is greater than or equal to the scoring threshold, the second neural network can be used to perform safety classification on the safety detection area. The present disclosure does not limit the specific value of the scoring threshold.

[0048] In the exemplary embodiment of the present disclosure, different categories of safety detection areas correspond to different second neural networks. That is, for the collar area, a second neural network corresponding to the collar area can be pre-trained; for the cuff area, a second neural network corresponding to the cuff area can be pre-trained; for the trouser leg area, a second neural network corresponding to the trouser leg area can be pre-trained. For the safety requirements of offshore photovoltaic construction scenes, the three tight requirements of tight collar, tight cuffs, and tight trouser legs must be met, and the second neural network can be used to analyze and identify this safety requirement.

[0049] In addition, the second neural network mentioned in the present disclosure may be a classification model based on a convolutional neural network, and its output may be the result of the presence or absence of a safety hazard. For example, through the output of the fully connected layer included therein, the probability value of whether there is a safety hazard can be obtained, and based on the probability value, it can be determined whether the target person has a safety hazard. The present disclosure does not limit the network structure and training process of the second neural network. The network complexity of the second neural network is greater than the network complexity of the first neural network. Among them, the complexity can be characterized by the number of network layers included and the degree of computing power consumption, and the present disclosure does not limit this.

[0050] When the result of the security classification indicates that the target person has a potential security risk, the profile feature of the target person can be determined, and the basic information of the person bound to the profile feature can be determined.

[0051] Specifically, the security detection device 13 can determine the contour features of the target person, and the algorithm used can be the same as the algorithm used by the entry confirmation device 11. The security detection device 13 can compare the contour features extracted by itself with the contour features previously extracted by the entry confirmation device 11. For example, when the contour features are represented as vectors, a vector similarity comparison can be performed, and the present disclosure does not limit the vector similarity comparison algorithm. When the determined similarity is greater than the similarity threshold, it can be determined that the two are for the same person. Therefore, through the mapping relationship between the basic information of the person bound to the entry confirmation device 11 and the contour features, the security detection device 13 can determine the basic information of the target person. For example, the security detection device 13 determines the contour features, and after similarity confirmation, the contour features are used to search in the mapping relationship stored in the entry confirmation device 11 to determine the basic information of the target person.

[0052] That is to say, based on the information interaction between the entry confirmation device 11 and the safety detection device 13, combined with the matching method of feature similarity, the safety detection device 13 can determine the basic information of the target person.

[0053] According to other embodiments of the present disclosure, when the safety detection feasibility score is less than the score threshold, the video frame image can be discarded. At the same time, the number of times the video frame image of the target person is discarded is increased by 1. When the video frame image of the target person is discarded a predetermined number of times, it is considered that the target person may be suspected of intentional occlusion. In this case, a safety warning for the target person can be issued.

[0054] According to some embodiments of the present disclosure, after a target person has a safety hazard and the target person's basic information is determined, the safety detection device 13 can obtain the target person's communication method from the basic information of the person, and send a first safety reminder message for the target person to the target person through the target person's communication method.

[0055] In addition, when the target person is accompanied by one or more companions, after there is a safety hazard to the target person and the basic information of the target person is determined, the safety detection equipment 13 can also determine the communication method of the companions and send a second safety reminder message for the target person to the companions through the communication method of the companions.

[0056] Regarding the determination of the accompanying persons, the safety detection device 13 can query the entry time recorded by the entry confirmation device 11, and determine the persons whose entry time interval with the target person is less than the time period threshold as the accompanying persons of the target person. In order to avoid the erroneous sending of the reminder message, the safety detection device 13 can also obtain multiple video frame images captured by the second camera, and determine the number of accompanying persons corresponding to the target person through these video frame images. In the case where the entry confirmation device 11 records the number of people entering at the same time, the two numbers are compared. If they are consistent, these persons are determined as the accompanying persons of the target person.

[0057] Figure 4 A schematic diagram of sending a safety reminder message according to an embodiment of the present disclosure is shown. Figure 4 The safety detection device 13 can send a first safety reminder message to the communication device 41 of the target person, and send a second safety reminder message to the communication device 42 of the accompanying person.

[0058] Specifically, the first safety reminder message may be different from the second safety reminder message, and the name of the target person may be written in the second safety reminder message so that fellow travelers can be reminded.

[0059] According to other embodiments of the present disclosure, after determining that the target person has a safety hazard, the safety detection device 13 can also determine the position of the second camera that collects the video frame image in the offshore photovoltaic construction site, and then determine the speaker closest to the second camera based on the pre-configured configuration information of the speaker at the offshore photovoltaic construction site. Next, the safety detection device 13 can control the speaker to issue a reminder voice. The present disclosure does not limit the content of the reminder voice.

[0060] Furthermore, the disclosed embodiments also provide a personnel safety detection method applied to an offshore photovoltaic construction site, the personnel safety detection method being applied to a personnel safety detection system including an entry confirmation device, the entry confirmation device including a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is located at the entrance of the offshore photovoltaic construction site and is wearing safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features.

[0061] Figure 5 The flowchart of the personnel safety detection method applied to the offshore photovoltaic construction site according to the exemplary embodiment of the present disclosure is schematically shown. The method is applied to the above-mentioned safety detection equipment. Figure 5 The personnel safety detection method applied to an offshore photovoltaic construction site according to an exemplary embodiment of the present disclosure may include the following steps: S52. Obtaining a video frame image containing a portrait of a target person captured by a second camera; wherein the second camera is configured at different locations of the offshore photovoltaic construction site.

[0062] S54. Using the first neural network to determine a safety detection area for the target person in the video frame image and determining a safety detection feasibility score for the target person based on the safety detection area.

[0063] S56. When the safety detection feasibility score is greater than or equal to the score threshold, a second neural network is used to perform safety classification on the safety detection area; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

[0064] S58. When the result of the security classification indicates that the target person has a security risk, determine the profile features of the target person, and determine the basic information of the person bound to the profile features of the target person.

[0065] According to an exemplary embodiment of the present disclosure, the entry confirmation device also includes an information entry module; the information entry module is used to respond to the information entry operation of the personnel, determine the basic information of the personnel, and pass the basic information of the personnel to the personnel identity binding module; wherein the information entry operation includes one or more combinations of personnel QR code scanning operation, personnel work permit scanning operation, personnel information typing operation, face recognition operation, and personnel fingerprint scanning operation.

[0066] According to an exemplary embodiment of the present disclosure, when the target personnel's travel route includes an offshore construction site, the safety detection area includes one or more of a safety helmet area, a life jacket area, a work shoe area, a collar area, a cuff area, and a trouser leg area.

[0067] According to an exemplary embodiment of the present disclosure, a first neural network is used to identify a target person in a video frame image to determine coordinate information of key safety detection points, and a safety detection area is determined based on the coordinate information of the key safety detection points.

[0068] According to an exemplary embodiment of the present disclosure, the method also includes: when the security detection feasibility score is less than a score threshold, discarding the video frame image; and when the video frame image for the target person is discarded a predetermined number of times, the security detection device issues a security alarm for the target person.

[0069] According to an exemplary embodiment of the present disclosure, after determining the basic personnel information bound to the profile features of the target person, the communication method of the target person is obtained from the basic personnel information of the target person, and a first safety reminder message for the target person is sent to the target person through the communication method of the target person.

[0070] According to an exemplary embodiment of the present disclosure, when the target person has one or more companions, after determining the basic information of the person bound to the profile features of the target person, the communication method of the companions is determined, and a second safety reminder message for the target person is sent to the companions through the communication method of the companions.

[0071] Since the various steps of the personnel safety detection method applied to the offshore photovoltaic construction site in the embodiment of the present disclosure are the same as those in the above-mentioned system implementation, they will not be repeated here.

[0072] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0073] Furthermore, this example embodiment also provides a personnel safety detection device applied to an offshore photovoltaic construction site. The personnel safety detection device is applied to a personnel safety detection system including an entry confirmation device, the entry confirmation device including a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is at the entrance of the offshore photovoltaic construction site and has worn safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features.

[0074] Figure 6 The block diagram of the personnel safety detection device at the offshore photovoltaic construction site according to the exemplary embodiment of the present disclosure is schematically shown. Figure 6 According to an exemplary embodiment of the present disclosure, a personnel safety detection device 6 for an offshore photovoltaic construction site may include an image acquisition module 61 , a score determination module 63 , a safety classification module 65 and a personnel information determination module 67 .

[0075] Specifically, the image acquisition module 61 can be used to acquire a video frame image containing a portrait of a target person captured by a second camera; wherein the second camera is configured at different locations at the offshore photovoltaic construction site; the score determination module 63 can be used to use the first neural network to determine the safety detection area of ​​the target person in the video frame image and determine the safety detection feasibility score of the target person based on the safety detection area; the safety classification module 65 can be used to use the second neural network to perform safety classification on the safety detection area when the safety detection feasibility score is greater than or equal to the score threshold; the personnel information determination module 67 can be used to determine the contour features of the target person and determine the basic personnel information bound to the contour features of the target person when the result of the safety classification indicates that the target person has a safety hazard; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

[0076] Since the functional modules of the personnel safety detection device applied to the offshore photovoltaic construction site in the embodiment of the present disclosure are the same as those in the above-mentioned system implementation, they will not be described in detail here.

[0077] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0078] The program product for implementing the above method according to the embodiment of the present disclosure can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0079] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical disk, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0080] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0082] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0083] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0084] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0085] Refer to the following Figure 7 An electronic device 700 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0086] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include but are not limited to: the at least one processing unit 710, the at least one storage unit 720, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), and a display unit 740.

[0087] The storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 710 can execute various steps of the personnel safety detection method applied to an offshore photovoltaic construction site according to an embodiment of the present disclosure.

[0088] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 7201 and / or a cache memory unit 7202 , and may further include a read-only memory unit (ROM) 7203 .

[0089] The storage unit 720 may also include a program / utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0090] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0091] The electronic device 700 may also communicate with one or more external devices 800 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 700, and / or any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 750. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 760. Figure 7 As shown, the network adapter 760 communicates with other modules of the electronic device 700 via the bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0092] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0093] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0094] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0095] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing what is disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be considered merely as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0096] It should be understood that the present disclosure is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A personnel safety detection system applied to an offshore photovoltaic construction site, characterized in that: include: The entry confirmation device comprises a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is at the entrance of an offshore photovoltaic construction site and is wearing safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features; Multiple second cameras are deployed at different locations on the offshore photovoltaic construction site; A safety detection device is used to obtain a video frame image containing a portrait of a target person collected by the second camera, use a first neural network to determine a safety detection area for the target person in the video frame image and determine a safety detection feasibility score for the target person based on the safety detection area, and when the safety detection feasibility score is greater than or equal to a score threshold, use a second neural network to perform safety classification on the safety detection area, and when the result of the safety classification indicates that the target person has a safety hazard, determine the contour features of the target person and determine the basic information of the person bound to the contour features of the target person; wherein the network complexity of the second neural network is greater than the network complexity of the first neural network.

2. The personnel safety detection system according to claim 1, characterized in that: The entry confirmation device also includes an information entry module; The information entry module is used to respond to the information entry operation of the personnel, determine the basic information of the personnel, and transmit the basic information of the personnel to the personnel identity binding module; Among them, the information entry operation includes one or more combinations of personnel QR code scanning operation, personnel work card scanning operation, personnel information typing operation, face recognition operation, and personnel fingerprint scanning operation.

3. The personnel safety detection system according to claim 1, characterized in that: In the case where the target personnel's route includes an offshore construction site, the safety detection area includes one or more of a safety helmet area, a life jacket area, a work shoe area, a collar area, a cuff area, and a trouser leg area.

4. The personnel safety detection system according to claim 1 or 3, characterized in that: The safety detection device is used to use a first neural network to identify a target person in the video frame image to determine coordinate information of key safety detection points, and determine a safety detection area based on the coordinate information of the key safety detection points.

5. The personnel safety detection system according to claim 1, characterized in that: The security detection device is also used to discard the video frame image when the security detection feasibility score is less than the score threshold; and when the video frame image for the target person is discarded a predetermined number of times, the security detection device issues a security alarm for the target person.

6. The personnel safety detection system according to claim 1, characterized in that: After determining the basic information of the target person bound to the profile features of the target person, the security detection device is also used to obtain the communication method of the target person from the basic information of the target person, and send a first security reminder message for the target person to the target person through the communication method of the target person.

7. The personnel safety detection system according to claim 1 or 6, characterized in that: In the case that the target person has one or more companions, after determining the basic information of the person bound to the profile features of the target person, the security detection device is also used to determine the communication method of the companions, and send a second security reminder message for the target person to the companions through the communication method of the companions.

8. A personnel safety detection method applied to an offshore photovoltaic construction site, characterized in that: The personnel safety detection method is applied to a personnel safety detection system including an entry confirmation device, wherein the entry confirmation device includes a first camera and a personnel identity binding module; the first camera is used to collect an initial image of a person who is located at the entrance of an offshore photovoltaic construction site and is wearing safety equipment; the personnel identity binding module is used to obtain the initial image, extract the contour features of the person in the initial image, determine the basic information of the person, and bind the basic information of the person to the contour features; wherein the personnel safety detection method includes: Acquire a video frame image containing a portrait of a target person captured by a second camera; wherein the second camera is configured at different locations of an offshore photovoltaic construction site; Determine a safety detection area of ​​the target person in the video frame image using a first neural network and determine a safety detection feasibility score of the target person based on the safety detection area; When the safety detection feasibility score is greater than or equal to the score threshold, using a second neural network to perform safety classification on the safety detection area; In the case where the result of the security classification indicates that the target person has a security risk, determining the profile features of the target person, and determining the basic information of the person bound to the profile features of the target person; The network complexity of the second neural network is greater than the network complexity of the first neural network.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the personnel safety detection method applied to the offshore photovoltaic construction site described in claim 8 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to implement the personnel safety detection method applied to an offshore photovoltaic construction site as described in claim 8 by executing the executable instructions.

Images