A people flow management method and system based on edge computing

Abstract

The application is suitable for the technical field of people flow control, and provides a people flow control method and system based on edge computing, which comprises the following steps: obtaining a video stream from an edge computing node; storing the video stream and generating an original video access address; identifying a human body feature in the video stream and generating a people flow video stream; recording an activity track of the human body feature; storing the people flow video stream and generating a people flow video access address, or storing the people flow video stream after marking the activity track of the human body feature in the people flow video stream and generating a people flow video access address; and realizing the video stream in different states can be viewed, meeting the use in different scenes and being widely applicable.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of people flow control, and particularly relates to a people flow control method and system based on edge computing. BACKGROUND

[0002] In a face recognition system, a video picture of a real area is captured by a camera, and picture information collected by the camera is transmitted to a background face recognition server through an edge node; the background face recognition server extracts feature values, such as facial feature values of a human body, by performing image analysis on the picture information, compares and verifies the feature values with an image library, and feeds back a comparison and verification result to an information screen for display.

[0003] However, in actual application, the system realizes face recognition, but does not perform trajectory identification and tracking on the motion trajectory of the human body, resulting in the need for manual acquisition of the motion trajectory by reviewing monitoring video, and single function; and the system cannot meet the use requirements of people. SUMMARY

[0004] In view of the above problems of the prior art, the present application aims to provide a people flow control method and system based on edge computing, and aims to solve the problem that the prior art cannot provide an effective people flow control method based on edge computing, so that the motion trajectory of a human body cannot be acquired and user experience is poor.

[0005] In one aspect, the present application provides a people flow control method based on edge computing, which comprises the following steps:

[0006] acquiring a video stream;

[0007] storing the video stream and producing an original video access address;

[0008] identifying a human body feature in the video stream and generating a people flow video stream;

[0009] recording a motion trajectory of the human body feature;

[0010] storing the people flow video stream and generating a people flow video access address, or storing and generating the people flow video access address after marking the motion trajectory of the human body feature in the people flow video stream.

[0011] Further, identifying the human body feature in the video stream and generating the people flow video stream comprises:

[0012] detecting the human body feature in the video stream and identifying the human body feature;

[0013] identifying the human body feature comprises:

[0014] labeling the whole body feature with a bounding box, or labeling the face of the body feature with the bounding box.

[0015] Preferably, recording the activity track of the body feature comprises:

[0016] acquiring the latitude and longitude range corresponding to the video stream in a real area;

[0017] obtaining one or more activity latitude and longitude values of the body feature according to the position of the body feature in the video stream and the latitude and longitude range corresponding to the video stream in a real area;

[0018] generating the activity track of the body feature according to the plurality of activity latitude and longitude values of the body feature.

[0019] Further preferably, recording the activity track of the body feature comprises:

[0020] acquiring the latitude and longitude value at the center position corresponding to the video stream in a real area;

[0021] calculating one or more activity latitude and longitude values of the body feature according to the position of the body feature in the video stream and the latitude and longitude value of the center position corresponding to the video stream in a real area;

[0022] generating the activity track of the body feature according to the plurality of activity latitude and longitude values of the body feature.

[0023] Further preferably, the method further comprises:

[0024] labeling the body feature in the people flow video stream with the activity latitude and longitude value.

[0025] Further preferably, the method further comprises:

[0026] extracting the face image of the body feature;

[0027] comparing the face image of the body feature with a preset face recognition image, and if the comparison is consistent, identifying the activity track of the body feature in the people flow video stream.

[0028] Preferably, the method further comprises:

[0029] the edge computing node acquires the video stream;

[0030] obtaining the people flow or the people flow in a certain time period according to one or more body features in the video stream and sending to an external access control unit for people flow control;

[0031] detecting the body feature in the video stream comprises:

[0032] a preset human feature model, and detecting a human feature from the video stream according to the human feature model.

[0033] In another aspect, the present application also provides a crowd management system based on edge computing, comprising at least one processor; and

[0034] a memory in communication connection with the at least one processor; wherein

[0035] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the crowd management method based on edge computing described above.

[0036] In another aspect, the present application also provides a non-volatile computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are executed by one or more processors to enable the one or more processors to perform the crowd management method based on edge computing described above.

[0037] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-volatile computer readable storage medium, and the computer program comprises program instructions, and the program instructions are executed by a processor to enable the processor to perform the crowd management method based on edge computing described above.

[0038] The present application has the beneficial effects that: the video stream is obtained from the edge computing node; the video stream is stored and the original video access address is produced; the human feature in the video stream is identified and the crowd video stream is generated; the activity track of the human feature is recorded; the crowd video stream is stored and the crowd video access address is generated, or the crowd video stream is stored and the crowd video access address is generated after the activity track of the human feature is marked in the crowd video stream; the video stream in different states can be viewed, which meets the use in different scenes and has wide applicability. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is an implementation flowchart of the crowd management method based on edge computing provided by the embodiment one of the present application;

[0040] Figure 2 is a structural schematic diagram of the crowd management device based on edge computing provided by the embodiment two of the present application. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be given to the present application in combination with the accompanying drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and not to limit the present application.

[0042] The specific implementation of the present application will be described in detail in combination with specific examples as follows:

[0043] Example One

[0044] Figure 1 The implementation process of the people flow management method based on edge computing provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the present application are shown, and the details are as follows:

[0045] In step S101, the video stream is acquired.

[0046] In the embodiment of the present application, the video stream is acquired by the edge computing node, for example, the edge computing node acquires the local video stream from the camera and forwards it through the Internet.

[0047] In step S102, the video stream is stored and the original video access address is generated.

[0048] In the embodiment of the present application, the original video can be viewed or downloaded by accessing the original video access address.

[0049] In step S103, the human features in the video stream are identified and the people flow video stream is generated.

[0050] In the embodiment of the present application, identifying the human features in the video stream and generating the people flow video stream include:

[0051] Detecting the human features in the video stream and identifying the human features;

[0052] Further, identifying the human features includes:

[0053] Labeling the overall human features with an identification frame, or labeling the face of the human features with an identification frame;

[0054] Further, detecting the human features in the video stream includes:

[0055] Predefining a human feature model, and detecting the human features from the video stream according to the human feature model;

[0056] Further preferably, the people flow or the people flow in a certain time period is derived according to one or more human features in the video stream and is sent to an external access control unit for people flow management; so as to realize the statistics of the people flow and facilitate the people flow management.

[0057] In step S104, the activity track of the human feature is recorded.

[0058] In the embodiment of the present application, further, the recording of the activity track of the human feature comprises:

[0059] The latitude and longitude range corresponding to the video stream in the real area is obtained.

[0060] According to the position of the human feature in the video stream and the latitude and longitude range corresponding to the video stream in the real area, one or more activity latitude and longitude values of the human feature are obtained; for example, the latitude and longitude of a plurality of points in the real area are measured in a grid shape, and the latitude and longitude of the points near the human body are extracted according to the current position of the human body, and then the latitude and longitude of the human body are obtained; so as to quickly obtain the latitude and longitude of the position of the human body.

[0061] According to the plurality of activity latitude and longitude values of the human feature, the activity track of the human feature is generated.

[0062] Further preferably, the recording of the activity track of the human feature comprises:

[0063] The latitude and longitude value of the center position corresponding to the video stream in the real area is obtained.

[0064] According to the position of the human feature in the video stream and the latitude and longitude value of the center position corresponding to the video stream in the real area, one or more activity latitude and longitude values of the human feature are calculated; for example, the latitude and longitude of the center position are measured, and then the latitude and longitude of the human body are calculated according to the distance and direction of the human body relative to the center position according to a certain proportion.

[0065] According to the plurality of activity latitude and longitude values of the human feature, the activity track of the human feature is generated.

[0066] Preferably, it further comprises: marking the activity latitude and longitude value of the human feature in the people flow video stream; so as to facilitate the administrator to quickly obtain the position of the human body.

[0067] Further preferably, it further comprises: extracting the face image of the human feature.

[0068] The face image of the human feature is compared with the preset face recognition image, and if the comparison is consistent, the activity track of the human feature is marked in the people flow video stream; so as to realize the extraction of the activity track of a specific person.

[0069] In step S105, the people flow video stream is stored and the people flow video access address is generated, or the activity track of the human feature is marked in the people flow video stream and then stored and the people flow video access address is generated.

[0070] In the embodiment of the present application, the people flow video can be viewed or downloaded by accessing the people flow video access address, the human body and the activity track of the human body in the video can be intuitively viewed, the intelligent degree of the face recognition system is improved, and different use requirements are met.

[0071] In the embodiment of the present application, the video stream is acquired from the edge computing node, the video stream is stored and the original video access address is produced, the human body features in the video stream are identified and the people flow video stream is generated, the activity track of the human body features is recorded, the people flow video stream is stored and the people flow video access address is generated, or the people flow video stream is stored after the activity track of the human body features is marked in the people flow video stream and the people flow video access address is generated, the video stream in different states can be viewed, different scenes are met, and the applicability is wide.

[0072] Example Two

[0073] Figure 2 An edge computing-based people flow management and control device provided by the second embodiment of the present application is shown, as shown in the figure, Figure 2 The device 10 includes:

[0074] one or more processors 110 and a memory 120, Figure 2 In the embodiment, the processor 110 is taken as an example for introduction, the processor 110 and the memory 120 can be connected through a bus or other ways, Figure 2 In the embodiment, the connection through the bus is taken as an example.

[0075] The processor 110 is used to complete various control logics of the device 10, which can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine), or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination of these components. In addition, the processor 110 can also be any conventional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.

[0076] The memory 120 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to the edge computing-based people flow management and control method in the embodiment of the present application. The processor 110 executes various function applications and data processing of the device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, the edge computing-based people flow management and control method in the above method embodiment is realized.

[0077] The memory 120 can include a program storage area and a data storage area, where the program storage area can store application programs required by the operation of the device, at least one function, and the data storage area can store data created according to the use of the device 10, etc. In addition, the memory 120 can include a high-speed random access memory, and can also include a nonvolatile memory such as at least one of a magnetic disk storage device, a flash memory device, or other nonvolatile solid-state memory device. In some embodiments, the memory 120 can optionally include a memory disposed remotely with respect to the processor 110, which can be connected to the device 10 through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] One or more units are stored in the memory 120, and when executed by the one or more processors 110, perform the crowd flow management method based on edge computing in any of the above-mentioned method embodiments, for example, perform the method steps S101 to S105 in the above-described Figure 1 .

[0079] Example Three

[0080] Embodiment three of the present application provides a non-volatile computer readable storage medium, the computer readable storage medium stores computer executable instructions, the computer executable instructions are executed by one or more processors, for example, the method steps S101 to S105 in the above-described Figure 1 .

[0081] By way of example, non-volatile storage can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM), which acts as external cache memory. By way of illustration, and not limitation, RAM can be available in many forms such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memory of the operational environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0082] Example Four

[0083] Embodiment four of the present application provides a computer program product, the computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform the edge computing-based crowd management method of the above-mentioned method embodiments. For example, the processor executes the method steps S101 to S105 in the above description. Figure 1

[0084] The above-described embodiments are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0085] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions or the part that contributes to the related art can be embodied in the form of a software product, which can exist in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions to make a computer electronic device (which can be a personal computer, a server, or a network electronic device, etc.) execute the method of each embodiment or some part of the embodiment.

[0086] Conditional language such as, among others, "can," "could," "might" or "may," unless specifically stated otherwise, generally are intended to convey that a certain embodiment could include, while other embodiments do not include, a certain feature, element or operation. Thus, such conditional language generally is not intended to imply that a feature, element or operation is required in one or more embodiments or that a feature, element or operation is necessary for one or more embodiments to work properly or that a feature, element or operation is needed for one or more embodiments to work at all. Further, unless otherwise noted, terms such as "first" and "second" are used merely as labels, and are not intended to impose ordinal or numerical requirements on a feature, element or operation.

[0087] ​What has been described herein in the specification and drawings includes examples of a crowd flow management method and system that can provide edge computing based. Of course, not every conceivable combination of elements and / or method can be described for purposes of describing the various features of the present disclosure, but it can be recognized that many additional combinations and permutations of the disclosed features are possible. It is intended, therefore, to be true that alterations and modifications to this disclosure can be practiced by a person of ordinary skill in the art without departing from the scope or spirit of the disclosure. Moreover, or in the alternative, other embodiments of the disclosure can be apparent from consideration of the specification and drawings, and practice of the disclosure as presented herein. It is intended that the specification and drawings presented an example in all respects, and not as limiting. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims

1. A people flow management method based on edge computing, characterized in that, The method comprises the following steps: acquiring a video stream; storing the video stream and generating an original video access address; identifying a human body feature in the video stream and generating a human flow video stream; recording an activity track of the human body feature; storing the human flow video stream and generating a human flow video access address, or storing and generating the human flow video access address after marking the activity track of the human body feature in the human flow video stream; Identifying the human body feature in the video stream and generating the human flow video stream comprises: detecting the human body feature in the video stream and identifying the human body feature; identifying the human body feature comprises: marking the whole human body feature with an identification frame, or marking the face of the human body feature with the identification frame; Recording the activity track of the human body feature comprises: acquiring a latitude and longitude range corresponding to the video stream in a real area; obtaining one or more activity latitude and longitude values of the human body feature according to the position of the human body feature in the video stream and the latitude and longitude range corresponding to the video stream in the real area; and generating the activity track of the human body feature according to the plurality of activity latitude and longitude values of the human body feature; The method further comprises: an edge computing node acquiring the video stream; deriving a human flow or a human flow in a certain time period according to one or more human body features in the video stream and sending to an external access control unit for human flow control; detecting the human body feature in the video stream comprises: presetting a human body feature model and detecting the human body feature from the video stream according to the human body feature model; Recording the activity track of the human body feature comprises: acquiring a latitude and longitude value at a central position corresponding to the video stream in a real area; calculating one or more activity latitude and longitude values of the human body feature according to the position of the human body feature in the video stream and the latitude and longitude value of the central position corresponding to the video stream in the real area; and generating the activity track of the human body feature according to the plurality of activity latitude and longitude values of the human body feature; The method further comprises: marking the activity latitude and longitude value of the human body feature in the human flow video stream; The method further comprises: extracting a face image of the human body feature; comparing the face image of the human body feature with a preset face recognition image, and if the comparison is consistent, marking the activity track of the human body feature in the human flow video stream.

2. An edge computing-based people flow management device, characterized in that, The device comprises at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the human flow control method based on edge computing of claim 1.

3. A non-transitory computer readable storage medium, comprising: The non-volatile computer readable storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors to enable the one or more processors to execute the human flow control method based on edge computing of claim 1.

4. A computer program product, characterized by The computer program product comprises a computer program stored on a nonvolatile computer readable storage medium, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform the edge computing-based crowd flow management method of claim 1.

Images