Behavior warning method and device, and electronic equipment
By processing image information to identify human behaviors in the campus, timely warning of campus bullying behavior is achieved, the problem of low timeliness in the existing technology is solved, and campus safety is improved.
Patent Information
- Application Number
- CN201910765964.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-08-19
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2039-08-19
AI Technical Summary
The existing technology is difficult to effectively warn of bullying in campuses, resulting in low timeliness and time-consuming and labor-intensive.
By obtaining image information of multiple human objects, processing the human body's contour, relative position and action trajectory, identifying dangerous behavior patterns, and providing sound and action warnings.
It realizes timely identification and early warning of campus bullying, improves safety, and reduces the time and energy of manual patrols.
Smart Images

Figure CN111353365B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a behavior early warning method and device, and electronic equipment. Background Art
[0002] At present, some schools have campus bullying, where the strong party physically or psychologically bullies the weak party once or multiple times, causing serious property losses, physical and mental harm to the weak party. In order to prevent campus bullying, schools monitor the situation on campus through campus monitoring systems and arrange security personnel to patrol at fixed times, which is not only time-consuming and labor-intensive, but also not timely. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide a behavior warning method and device, and electronic equipment, which can provide behavior warning in time.
[0004] Based on the above purpose, the present invention provides a behavior early warning method, comprising:
[0005] Acquiring image information including a plurality of human objects;
[0006] Processing the image information to determine the current behavior of each human object; the current behavior includes a normal behavior pattern and a dangerous behavior pattern;
[0007] When the current behavior of the human subject is the dangerous behavior pattern, an early warning is issued.
[0008] Optionally, the processing the image information to determine the current behavior of each human object includes:
[0009] Processing the image information to extract the human body contour of each human object;
[0010] Determining the number of human objects according to the human body contour of each human object;
[0011] Determining the relative position of each human object according to the human body contour of each human object and the number of the human objects;
[0012] According to the human body contour of each human body object, the movement trajectory of each human body object is tracked;
[0013] According to the relative position and movement trajectory of each human object, the current behavior of each human object is determined.
[0014] Optionally, the relative position includes a dangerous relative position and a normal relative position. When the relative positions of the multiple human objects meet a preset dangerous position condition, they are judged as the dangerous relative position, otherwise they are judged as the normal relative position.
[0015] Optionally, the motion trajectory includes the motion trajectory of upper limbs and lower limbs. If the motion trajectory of the upper limbs belongs to the first warning action and the relative position is a dangerous relative position, the current behavior is determined to be the dangerous behavior pattern; if the motion trajectory of the upper limbs and lower limbs belongs to the second warning action, the range of the motion trajectory of the upper limbs and lower limbs is expanded, the movement frequency is increased, and the relative position is the dangerous relative position, then the current behavior is determined to be the dangerous behavior pattern.
[0016] Optionally, the method further includes:
[0017] When the relative position is the dangerous relative position, facial recognition processing is performed on the human object in the image information to determine whether there is a dangerous object in the image information and the emotion type of the human object. If the dangerous object exists and / or the emotion type is a preset dangerous emotion, an early warning is issued.
[0018] Optionally, the method further includes:
[0019] Acquire infrared image information, process the infrared image information, and determine the emotion type of the human object.
[0020] Optionally, the method further includes:
[0021] The image information is processed to determine whether there are any dangerous items in the image information; when the dangerous items are present, an early warning is issued.
[0022] The embodiment of the present invention further provides a behavior warning device, comprising:
[0023] An image acquisition module, used to acquire image information including a plurality of human objects;
[0024] A behavior recognition module is used to process the image information to determine the current behavior of each human object; the current behavior includes a normal behavior pattern and a dangerous behavior pattern;
[0025] The early warning module is used to issue an early warning when the current behavior of the human subject is in the dangerous behavior mode.
[0026] Optionally, the behavior recognition module includes:
[0027] A contour extraction submodule is used to process the image information and extract the human body contour of each human object;
[0028] A number determination submodule, used to determine the number of human objects according to the human body contour of each human object;
[0029] A position determination submodule, used to determine the relative position of each human object according to the human body contour of each human object and the number of the human objects;
[0030] A trajectory determination submodule, for tracking the movement trajectory of each human object according to the human body contour of each human object;
[0031] The behavior determination submodule is used to determine the current behavior of each human object according to the relative position and movement trajectory of each human object.
[0032] Optionally, the relative position includes a dangerous relative position and a normal relative position. When the relative positions of the multiple human objects meet a preset dangerous position condition, they are judged as the dangerous relative position, otherwise they are judged as the normal relative position.
[0033] Optionally, the motion trajectory includes the motion trajectory of upper limbs and lower limbs. If the motion trajectory of the upper limbs belongs to the first warning action and the relative position is a dangerous relative position, the current behavior is determined to be the dangerous behavior pattern; if the motion trajectory of the upper limbs and lower limbs belongs to the second warning action, the range of the motion trajectory of the upper limbs and lower limbs is expanded, the movement frequency is increased, and the relative position is the dangerous relative position, then the current behavior is determined to be the dangerous behavior pattern.
[0034] Optionally, the device further comprises:
[0035] A facial recognition module, configured to perform facial recognition processing on a human object in the image information when the relative position belongs to the dangerous relative position, determine whether there is a dangerous object in the image information, and determine the emotion type of the human object;
[0036] The early warning module is used to issue an early warning when the facial recognition module recognizes that the dangerous object exists in the image information and / or the emotion type is a preset dangerous emotion.
[0037] Optionally, the device further comprises:
[0038] The image acquisition module is used to acquire infrared image information including multiple human objects;
[0039] The facial recognition module is used to process the infrared image information to determine the emotion type of the human object.
[0040] Optionally, the device further comprises:
[0041] An object identification module is used to process the image information to determine whether there are dangerous objects in the image information;
[0042] The early warning module is used to issue an early warning when the object recognition module recognizes that the dangerous object exists in the image information.
[0043] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the behavior warning method is implemented when the processor executes the program.
[0044] From the above description, it can be seen that the behavior warning method, device, and electronic device provided by the present invention obtain image information including multiple human objects, process the image information, and determine the current behavior of each human object; when the current behavior of the human object is judged to be a dangerous behavior pattern, a sound warning and an action warning are issued. The present invention can identify dangerous behaviors so as to issue warnings in time. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0046] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present invention;
[0047] Figure 2 A schematic flow chart of a method for identifying the current behavior of a human subject according to an embodiment of the present invention;
[0048] Figure 3 is a structural block diagram of a device according to an embodiment of the present invention;
[0049] Figure 4 4 is a structural block diagram of a behavior recognition module according to an embodiment of the present invention. DETAILED DESCRIPTION
[0050] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0051] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.
[0052] Figure 1Schematic diagram of the method flow of an embodiment of the present invention. As shown in the figure, the behavior warning method provided by the embodiment of the present invention includes:
[0053] S10: Acquire image information including a plurality of human objects;
[0054] In some embodiments, an image acquisition device is used to acquire video information including human objects, and video frame images are extracted from the video information at a predetermined time as image information for subsequent recognition processing. For example, one frame of image information is extracted from the video information every 1.5 seconds.
[0055] In the application scenario of school, image acquisition equipment is installed in multiple specific locations on campus, such as cameras are placed in remote and sparsely populated places such as warehouses, distribution rooms, and corners. The cameras are used to collect video information within the monitoring range and the collected video information is transmitted to the server. The server receives the video information, extracts image information from the video information according to the scheduled time, and then performs subsequent processing on the extracted image information.
[0056] S11: Processing the image information to determine the current behavior of each human object;
[0057] Figure 2 The schematic diagram of the method flow for identifying the current behavior of a human object according to an embodiment of the present invention is shown in the figure. As shown in the figure, the image information is processed to determine the current behavior of each human object, including:
[0058] S110: Processing the image information to extract the human body contour of each human object;
[0059] The image information is processed to identify the key parts of the human body, including the head, shoulders, upper limbs, lower limbs, feet, etc., and the overall outline of the human body is determined based on the positions of the key parts.
[0060] S111: determining the number of human objects according to the human body contour of each human object;
[0061] S112: determining the relative position of each human object according to the human body contour of each human object and the number of human body objects;
[0062] According to the extracted human body contour, the relative position of each human body object is determined. The normal relative position and the dangerous relative position are preset, and according to the relative position of each human body object, the relative position of each human body object is determined to be a normal relative position or a dangerous relative position, wherein the dangerous relative position refers to the relative position of multiple human body objects meeting the preset dangerous position conditions, and the relative position that does not meet the dangerous position conditions is a normal relative position. For example, five human body objects are identified, four of which form a circle, and the fifth person is in the middle of the circle, and the relative position of the five human body objects is determined to be a dangerous relative position; four human body objects are identified, three of which stand in a row, and the fourth person is a certain distance away from the three people, and the relative position of the four human body objects is determined to be a dangerous relative position; two human body objects are identified, and the relative position of the two human body objects changes within the dangerous range, and the relative position of the two human body objects is determined to be a dangerous relative position. If the relative position of the two human body objects changes within the normal range, the relative position of the two human body objects is determined to be a normal relative position.
[0063] S113: Tracking the movement trajectory of each human object according to the human body contour of each human object;
[0064] According to the human body contour of the human body object, the movement trajectory of the human body object is tracked, including the movement trajectory of the upper limbs, lower limbs, head, the movement range of the human body contour, etc.
[0065] S114: Determine the current behavior of each human object according to the relative position and movement trajectory of each human object.
[0066] According to the relative position and movement trajectory of each human object, the current behavior of the human object is determined.
[0067] Specifically, normal behavior patterns and dangerous behavior patterns are preset. According to the movement trajectory of the upper limbs and lower limbs of the human subject, if the movement trajectory of the upper limbs and lower limbs belongs to the normal swing range, the current behavior of the human subject is judged to be a normal behavior pattern (such as normal walking); if the movement trajectory of the upper limbs belongs to the first warning action such as pushing, pulling, and patting, it is identified that the current behavior of the human subject may be a dangerous behavior pattern. At the same time, if the relative position of the human subject is a dangerous relative position, the current behavior of the human subject is determined to be a dangerous behavior pattern. If the relative position of the human subject is a normal relative position, the current behavior of the human subject is determined to be a normal behavior pattern (such as judging it as a fight between classmates); if the movement trajectory of the upper limbs belongs to punching and blocking, and the movement trajectory of the lower limbs belongs to the second warning action such as kicking, and the range of the movement trajectory of the upper limbs and lower limbs is expanded and the movement frequency is increased, it is identified that the current behavior of the human subject may be a dangerous behavior pattern. At the same time, if the relative position of the human subject is a dangerous relative position, the current behavior of the human subject is determined to be a dangerous behavior pattern. If the relative position of the human subject is a normal relative position, the current behavior of the human subject is determined to be a normal behavior pattern.
[0068] S12: When the current behavior of the human subject is a dangerous behavior pattern, an early warning is issued.
[0069] According to the current behavior of each human subject, if the current behavior of the human subject belongs to a normal behavior mode, no warning is required. If the current behavior of the human subject belongs to a dangerous behavior mode, a sound warning can be issued through broadcasting or other means. At the same time, a message can be pushed to the on-duty personnel, who will go to the scene to take action warning.
[0070] In some embodiments, the behavior warning method further includes:
[0071] According to the extracted human body contours of each human object and the number of human objects, the relative position of each human object is determined. If the relative position of each human object belongs to a dangerous relative position, facial recognition processing is performed on the human objects in the image information to identify the key facial features of each human object and the facial expression of each human object. According to the key facial features of each human object, a preset dangerous object database is matched. If there is a matching result, it is determined that there are dangerous objects that need to be paid special attention to in the image information, and a sound warning and an action warning are directly initiated. If there is no matching result, the emotion type is determined according to the facial expression of the identified human object. If the emotion type is a dangerous emotion such as pain, fear, sadness, anger, etc., a sound warning and an action warning are directly initiated.
[0072] Optionally, the image acquisition device uses a focus-adjustable camera. When it is determined that the relative position of each human object is a dangerous relative position, the focal length of the camera is adjusted, and the camera is used to acquire image information including the face of each human object to perform facial recognition processing on the human objects in the image information.
[0073] Optionally, the image acquisition device may be configured with a camera equipped with an infrared sensor, which collects infrared image information through the camera and assists in identifying the emotion type of the human subject based on the infrared image information.
[0074] In some embodiments, the behavior warning method further includes:
[0075] The image information is processed to extract the hand contour of the human subject, and determine whether the hand contour is in a gripping state. If it is in a gripping state, identify whether there are dangerous items near the hand that meet the characteristics of dangerous items. Dangerous items are, for example, weapons such as daggers, sticks, bricks, etc. The characteristics of dangerous items include the length and shape of the item. When dangerous items are identified in the image information, an early warning is initiated.
[0076] Figure 3 As shown in the figure, the behavior warning device provided by the embodiment of the present invention includes:
[0077] An image acquisition module, used to acquire image information including a plurality of human objects;
[0078] A behavior recognition module is used to process the image information and determine the current behavior of each human object;
[0079] The early warning module is used to determine whether to issue an early warning based on the current behavior of each human object.
[0080] In some embodiments, an image acquisition device is used to acquire video information including human objects, and video frame images are extracted from the video information at a predetermined time as image information for subsequent recognition processing. For example, one frame of image information is extracted from the video information every 1.5 seconds.
[0081] In the application scenario of school, image acquisition equipment is installed in multiple specific locations on campus, such as cameras are placed in remote and sparsely populated places such as warehouses, distribution rooms, and corners. The cameras are used to collect video information within the monitoring range and the collected video information is transmitted to the server. The server receives the video information, extracts image information from the video information at a predetermined time, and uses the image acquisition module to perform subsequent processing on the extracted image information.
[0082] Figure 4 1 is a structural block diagram of a behavior recognition module according to an embodiment of the present invention. As shown in the figure, in some embodiments, the behavior recognition module includes:
[0083] The contour extraction submodule is used to process the image information and extract the human contour of each human object; optionally, the image information is processed to identify the key parts of the human object, including the head, shoulders, upper limbs, lower limbs, feet, etc., and the overall contour of the human object is determined according to the position of the key parts.
[0084] A human body determination submodule is used to determine the number of human body objects according to the human body contour of each human body object;
[0085] A position determination submodule, used to determine the relative position of each human object according to the human body contour of each human object and the number of human objects;
[0086] The trajectory determination submodule is used to track the movement trajectory of each human object according to the human body contour of each human object; optionally, according to the human body contour of the human body object, the movement trajectory of the human body object includes the movement trajectory of the upper limbs, lower limbs, head, the movement range of the human body contour, etc.
[0087] The behavior determination submodule is used to determine the current behavior of each human object according to the relative position and movement trajectory of each human object.
[0088] Among them, the position determination submodule determines the relative position of each human object according to the extracted human body contour. The normal relative position and the dangerous relative position are preset, and the relative position of each human object is determined to be a normal relative position or a dangerous relative position according to the relative position of each human object. For example, five human objects are identified, four of which form a circle, and the fifth person is in the middle of the circle. The relative position of the five human objects is determined to be a dangerous relative position; four human objects are identified, three of which stand in a row, and the fourth person is a certain distance away from the three people. The relative position of the four human objects is determined to be a dangerous relative position; two human objects are identified, and the relative position of the two human objects changes within the dangerous range. The relative position of the two human objects is determined to be a dangerous relative position. If the relative position of the two human objects changes within the normal range, the relative position of the two human objects is determined to be a normal relative position.
[0089] Among them, the behavior determination submodule determines the current behavior of the human body object according to the relative position and movement trajectory of each human body object.
[0090] Specifically, normal behavior patterns and dangerous behavior patterns are preset. According to the movement trajectory of the upper limbs and lower limbs of the human subject, if the movement trajectory of the upper limbs and lower limbs belongs to the normal swing range, the current behavior of the human subject is judged to be a normal behavior pattern (such as normal walking); if the movement trajectory of the upper limbs belongs to the first warning action such as pushing, pulling, and patting, it is identified that the current behavior of the human subject may be a dangerous behavior pattern. At the same time, if the relative position of the human subject is a dangerous relative position, the current behavior of the human subject is determined to be a dangerous behavior pattern. If the relative position of the human subject is a normal relative position, the current behavior of the human subject is determined to be a normal behavior pattern (such as judging it as a fight between classmates); if the movement trajectory of the upper limbs belongs to punching and blocking, and the movement trajectory of the lower limbs belongs to the second warning action such as kicking, and the range of the movement trajectory of the upper limbs and lower limbs is expanded and the movement frequency is increased, it is identified that the current behavior of the human subject may be a dangerous behavior pattern. At the same time, if the relative position of the human subject is a dangerous relative position, the current behavior of the human subject is determined to be a dangerous behavior pattern. If the relative position of the human subject is a normal relative position, the current behavior of the human subject is determined to be a normal behavior pattern.
[0091] Among them, the early warning module determines the current behavior of each human object. If the current behavior of the human object belongs to a normal behavior pattern, no early warning will be issued; if the current behavior of the human object belongs to a dangerous behavior pattern, a sound warning can be issued through broadcasting and other means. At the same time, a message can be pushed to the on-duty personnel, who will go to the scene to issue an action warning.
[0092] In some embodiments, the behavior warning device further includes:
[0093] A facial recognition module is used to perform facial recognition processing on human objects in the image information when the relative position of each human object belongs to a dangerous relative position, identify whether there is a dangerous object in the image information, and identify the emotional type of the human object;
[0094] The early warning module is used to start an early warning when the facial recognition module recognizes that there is a dangerous object and / or the emotion type of the human object in the image information is a dangerous emotion.
[0095] According to the extracted human body contours of each human object and the number of human objects, the relative position of each human object is determined. If the relative position of each human object belongs to a dangerous relative position, facial recognition processing is performed on the human objects in the image information to identify the key facial features of each human object and the facial expression of each human object. According to the key facial features of each human object, a preset dangerous object database is matched. If there is a matching result, it is determined that there are dangerous objects that need to be paid special attention to in the image information, and a sound warning and an action warning are directly initiated. If there is no matching result, the emotion type is determined according to the facial expression of the identified human object. If the emotion type is a dangerous emotion such as pain, fear, sadness, anger, etc., a sound warning and an action warning are directly initiated.
[0096] Optionally, the image acquisition device uses a focus-adjustable camera. When it is determined that the relative position of each human object is a dangerous relative position, the focal length of the camera is adjusted, and the camera is used to acquire image information including the face of each human object to perform facial recognition processing on the human objects in the image information.
[0097] Optionally, the image acquisition device may be configured with a camera equipped with an infrared sensor, which collects infrared image information through the camera and assists in identifying the emotion type of the human subject based on the infrared image information.
[0098] In some embodiments, the behavior warning device further includes:
[0099] The object recognition module is used to process the image information and determine whether there are dangerous objects in the image information;
[0100] The early warning module is used to initiate an early warning when the object recognition module recognizes that there are dangerous objects in the image information.
[0101] The object recognition module processes the image information, extracts the hand contour of the human object, and determines whether the hand contour is in a gripping state. If it is in a gripping state, it identifies whether there are dangerous objects near the hand that meet the characteristics of dangerous objects. Dangerous objects include daggers, sticks, bricks and other weapons. The characteristics of dangerous objects include the length, shape and other characteristics of the object.
[0102] Based on the above purpose, the embodiment of the present invention also proposes an embodiment of a device for executing the behavior warning method. The device includes:
[0103] One or more processors and memory.
[0104] The device for executing the behavior warning method may further include: an input device and an output device.
[0105] The processor, memory, input device and output device may be connected via a bus or other means.
[0106] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the behavior warning method in the embodiment of the present invention. The processor executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory, that is, the behavior warning method in the above method embodiment is implemented.
[0107] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the device for executing the behavior early warning method, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the member user behavior monitoring device via 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.
[0108] The input device can receive input digital or character information, and generate key signal input related to user settings and function control of the device for executing the behavior early warning method. The output device can include display devices such as display screens.
[0109] The one or more modules are stored in the memory, and when executed by the one or more processors, the behavior warning method in any of the above method embodiments is executed. The embodiment of the device for executing the behavior warning method has the same or similar technical effect as any of the above method embodiments.
[0110] The embodiment of the present invention further provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the processing method of the list item operation in any of the above method embodiments. The embodiment of the non-transitory computer storage medium has the same or similar technical effect as any of the above method embodiments.
[0111] Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. The technical effect of the embodiment of the computer program is the same or similar to that of any of the above-mentioned method embodiments.
[0112] In addition, typically, the devices and equipment described in the present disclosure may be various electronic terminal devices, such as mobile phones, personal digital assistants (PDAs), tablet computers (PADs), smart TVs, etc., or large terminal devices, such as servers, etc. Therefore, the protection scope of the present disclosure should not be limited to a specific type of device or equipment. The client described in the present disclosure may be applied to any of the above electronic terminal devices in the form of electronic hardware, computer software, or a combination of the two.
[0113] In addition, the method according to the present disclosure may also be implemented as a computer program executed by a CPU, and the computer program may be stored in a computer-readable storage medium. When the computer program is executed by the CPU, the above functions defined in the method of the present disclosure are performed.
[0114] In addition, the above method steps and system units may also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.
[0115] In addition, it should be understood that the computer-readable storage medium (e.g., memory) described herein can be a volatile memory or a non-volatile memory, or can include both a volatile memory and a non-volatile memory. As an example and not by way of limitation, a non-volatile memory can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory can include a random access memory (RAM), which can act as an external cache memory. As an example and not by way of limitation, RAM can be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.
[0116] The apparatus of the above-mentioned embodiment is used to implement the corresponding method in the above-mentioned embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0117] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Within the scope of the present invention, the above embodiments or technical features in different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
[0118] In addition, to simplify the description and discussion, and in order not to obscure the present invention, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the devices may be shown in the form of block diagrams to avoid obscuring the present invention, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the present invention will be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that the present invention may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0119] Although the invention has been described in conjunction with specific embodiments of the invention, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
[0120] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A behavior early warning method, characterized in that: include: Acquiring image information including a plurality of human objects; Processing the image information to determine the current behavior of each human object includes: processing the image information to extract the human body contour of each human object; determining the number of the human body objects according to the human body contour of each human body object; determining the relative position of each human body object according to the human body contour of each human body object and the number of human body objects; tracking the movement trajectory of each human body object according to the human body contour of each human body object; determining the current behavior of each human body object according to the relative position and movement trajectory of each human body object; the current behavior includes a normal behavior mode and a dangerous behavior mode; Wherein, the relative position includes a dangerous relative position and a normal relative position. When the relative positions of the multiple human objects meet the preset dangerous position conditions, they are judged as the dangerous relative positions, otherwise they are normal relative positions; the action trajectories include upper limb and lower limb action trajectories. If the upper limb action trajectory belongs to the first warning action and the relative position is a dangerous relative position, the current behavior is determined to be the dangerous behavior mode; if the upper limb and lower limb action trajectories belong to the second warning action, the range of the upper limb and lower limb action trajectories is expanded, the action frequency is increased, and the relative position is the dangerous relative position, the current behavior is determined to be the dangerous behavior mode; When the current behavior of the human subject is the dangerous behavior pattern, an early warning is issued.
2. The method according to claim 1, characterized in that Also includes: When the relative position is the dangerous relative position, facial recognition processing is performed on the human object in the image information to determine whether there is a dangerous object in the image information and the emotion type of the human object. If the dangerous object exists and / or the emotion type is a preset dangerous emotion, an early warning is issued.
3. The method according to claim 2, characterized in that Also includes: Acquire infrared image information, process the infrared image information, and determine the emotion type of the human object.
4. The method according to claim 1, characterized in that Also includes: Processing the image information to determine whether there are any dangerous items in the image information; When the dangerous goods are present, an early warning is issued.
5. A behavior warning device, characterized in that: include: An image acquisition module, used to acquire image information including a plurality of human objects; A behavior recognition module is used to process the image information to determine the current behavior of each human object; the current behavior includes a normal behavior mode and a dangerous behavior mode; wherein the behavior recognition module includes: A contour extraction submodule, used to process the image information and extract the human body contour of each human object; A number determination submodule, used to determine the number of human objects according to the human body contour of each human object; A position determination submodule, used to determine the relative position of each human object according to the human body contour of each human object and the number of the human objects; wherein the relative position includes a dangerous relative position and a normal relative position, and when the relative position of the multiple human objects meets the preset dangerous position condition, it is determined to be the dangerous relative position, otherwise it is a normal relative position; The trajectory determination submodule is used to track the motion trajectory of each human object according to the human body contour of each human object; wherein the motion trajectory includes the motion trajectory of the upper limbs and the lower limbs, and if the motion trajectory of the upper limbs belongs to the first warning action, and the relative position is a dangerous relative position, then the current behavior is determined to be the dangerous behavior mode; if the motion trajectory of the upper limbs and the lower limbs belongs to the second warning action, the range of the motion trajectory of the upper limbs and the lower limbs is expanded, the motion frequency is increased, and the relative position is the dangerous relative position, then the current behavior is determined to be the dangerous behavior mode; A behavior determination submodule is used to determine the current behavior of each human object according to the relative position and action trajectory of each human object; The early warning module is used to issue an early warning when the current behavior of the human subject is in the dangerous behavior mode.
6. The device according to claim 5, characterized in that Also includes: A facial recognition module, configured to perform facial recognition processing on a human object in the image information when the relative position belongs to the dangerous relative position, determine whether there is a dangerous object in the image information, and determine the emotion type of the human object; The early warning module is used to issue an early warning when the facial recognition module recognizes that the dangerous object exists in the image information and / or the emotion type is a preset dangerous emotion.
7. The device according to claim 6, characterized in that Also includes: The image acquisition module is used to acquire infrared image information including multiple human objects; The facial recognition module is used to process the infrared image information to determine the emotion type of the human object.
8. The device according to claim 5, characterized in that Also includes: An object identification module is used to process the image information to determine whether there are dangerous objects in the image information; The early warning module is used to issue an early warning when the object recognition module recognizes that the dangerous object exists in the image information.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.
