A dynamic tracking and state analysis method and clinical nursing system

Abstract

The present application relates to a dynamic tracking and state analysis method and a clinical nursing system, the method comprising: in response to an acquired connection signal, obtaining an image group associated with the connection signal, the image group comprising a plurality of images; parsing the image group to obtain identification features of the object, the identification features comprising a facial image, a first body feature image, a second body feature image and a body feature image; using the identification features to track the movement trajectory of the object; comparing the movement speed or movement frequency of the body feature image or the minimum straight-line distance in the vertical direction, and issuing an early warning when the change speed of the movement speed, movement frequency or minimum straight-line distance is less than a setting. The dynamic tracking and state analysis method and clinical nursing system disclosed in the present application determine the state of the tracked object by tracking and analyzing the behavior of the tracked object, and can issue an early warning in time when the tracked object encounters danger, so as to reduce the impact of the danger.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a dynamic tracking and status analysis method and a clinical nursing system. Background Art

[0002] When the elderly live alone at home, they will face some unpredictable risks, such as falls and sudden illnesses. When these situations occur, timely measures need to be taken, but there are no caregivers around the elderly at this time, and it is easy for the situation to be discovered only after several hours.

[0003] The current preventive measures include electricity bill monitoring and water usage monitoring, that is, judging whether the above situation has occurred by water and electricity consumption, which also has a certain lag. There is also a video surveillance method to avoid the above situation by remotely viewing the video, but video surveillance requires someone to be on duty all the time, which is also difficult to implement. Summary of the invention

[0004] The present application provides a dynamic tracking and status analysis method and a clinical nursing system, which determine the status of a tracked object by tracking and analyzing the behavior of the tracked object, and can issue a warning in time when the tracked object encounters danger, so as to reduce the impact of the danger.

[0005] The above-mentioned purpose of the present application is achieved through the following technical solutions:

[0006] In a first aspect, the present application provides a dynamic tracking and state analysis method, comprising:

[0007] In response to the acquired connection signal, acquiring an image group associated with the connection signal, the image group including a plurality of images;

[0008] Parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image, and a body feature image;

[0009] Track the movement of objects using identification features;

[0010] comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature images; and

[0011] Issue an early warning when the speed of change of the moving speed, moving frequency or minimum straight-line distance is less than the set speed;

[0012] The facial image and the first body feature image appear in the same image, while the facial image and the second body feature image do not appear in the same image.

[0013] In a possible implementation manner of the first aspect, when the object suddenly disappears from the image group and exceeds a set time, an early warning is issued.

[0014] In a possible implementation of the first aspect, when a moving distance of one of the identification features in the vertical direction exceeds an allowed distance, a stationary time of the object is calculated, and an early warning is issued after the stationary time exceeds the allowed stationary time;

[0015] The trigger condition for calculating the stationary time of the object is that the straight-line distance moved by the multiple identification features in the vertical direction is greater than a set distance.

[0016] In a possible implementation manner of the first aspect, when calculating the stationary time of the object, objects appearing in a set area or an identified safety area are excluded from the calculation range.

[0017] In a possible implementation manner of the first aspect, a process of obtaining the second body shape feature image includes:

[0018] Obtaining an image including a facial image and / or a first body feature image, recorded as a reference image;

[0019] Obtaining a reference image, wherein the reference image includes a portion of the facial image and / or the first body feature image;

[0020] When the facial image and / or the first body feature image disappears in the reference image, a portion of the reference image belonging to the object is selected as the second body feature image.

[0021] In a possible implementation manner of the first aspect, the method further includes:

[0022] Selecting a part of the local image of the object as a moving reference image according to the movement of the object;

[0023] Taking the reference image as a starting point, extending the image belonging to the object to obtain a movement trajectory; and

[0024] When the facial image and / or the first body feature image disappears in the reference image, a portion of the object in the reference image is selected as a second body feature image;

[0025] The selection range of the second body shape characteristic image is the part of the image belonging to the object.

[0026] In a possible implementation manner of the first aspect, the number of movement trajectories in the process of generating the movement trajectory is multiple.

[0027] In a second aspect, the present application provides a dynamic tracking and state analysis device, comprising:

[0028] A first acquisition unit, configured to acquire, in response to the acquired connection signal, an image group associated with the connection signal, wherein the image group includes a plurality of images;

[0029] A parsing unit, used for parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image and a body feature image; the facial image and the first body feature image appear in the same image, and the facial image and the second body feature image do not appear in the same image;

[0030] A tracking unit, used to track the movement trajectory of the object using the identification features;

[0031] a comparison unit, used for comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature image; and

[0032] The alarm unit is used to issue an early warning when the speed of change of the moving speed, moving frequency or minimum straight-line distance is less than the set speed.

[0033] In a third aspect, the present application provides a clinical nursing system, the system comprising:

[0034] One or more image collectors, used for collecting images;

[0035] one or more memories for storing instructions; and

[0036] One or more processors are used to call and execute the instructions from the memory to process the acquired images and execute the method as described in the first aspect and any possible implementation of the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0038] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0039] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0040] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0041] The chip system may be composed of chips, or may include chips and other discrete devices.

[0042] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a step flow diagram of a dynamic tracking and state analysis method provided by this application.

[0044] Figure 2 This is a schematic diagram of camera deployment provided by this application.

[0045] Figure 3 This is a schematic diagram of a process of obtaining an object through an image group provided by the present application.

[0046] Figure 4 It is a schematic diagram of a body feature image provided by this application.

[0047] Figure 5 This is a schematic diagram of an alarm processing process provided by this application.

[0048] Figure 6 This is a schematic block diagram of a process for obtaining a second body posture characteristic image provided by the present application.

[0049] Figure 7 This is a schematic diagram of a process for obtaining a second body feature image provided by the present application. DETAILED DESCRIPTION

[0050] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0051] See also Figure 1 , is a dynamic tracking and state analysis method disclosed in this application, comprising the following steps:

[0052] S101, in response to an acquired connection signal, acquiring an image group associated with the connection signal, the image group including a plurality of images;

[0053] S102, parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image and a body feature image;

[0054] S103, using the recognition feature to track the movement trajectory of the object;

[0055] S104, comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature images; and

[0056] S105, issuing an early warning when the speed of change of the moving speed, moving frequency or minimum straight-line distance is less than a set value;

[0057] The facial image and the first body feature image appear in the same image, while the facial image and the second body feature image do not appear in the same image.

[0058] A dynamic tracking and state analysis method disclosed in the present application is applied to a clinical nursing system, which consists of three parts: a bracelet, a camera and an analyzer. The bracelet is worn on the wrist of the subject to send out positioning signals and collect some necessary human signals (such as body temperature and heart rate). The camera is used to obtain a real-time image of the subject. The analyzer analyzes the real-time image to determine the subject's state.

[0059] The number of cameras needs to be determined according to the environment in which the object is located. For example, if there are three rooms in the house, then the number of cameras is three, and a camera needs to be installed in each room. Of course, if a room is not suitable for installing a camera, you can choose not to install it.

[0060] The bracelet will send out signals continuously or intermittently. When a camera receives the signal sent by the bracelet, it will track the object within its coverage environment. For example, if the camera is installed on the wall, when the object moves, the camera will track the movement of the object based on the signal sent by the bracelet and the image obtained.

[0061] For example, Figure 2 As shown, if the object moves in multiple rooms, the location of the object can be quickly determined based on the signal sent by the bracelet. For example, if the object moves to room A, the camera in room A will quickly scan and find the object in room A after receiving the signal.

[0062] Here you may face the situation where multiple cameras receive signals from the bracelet at the same time. The specific solution is that each camera also has a local area network function. When the bracelet moves, it will automatically select the local area network with the strongest connection signal. After the bracelet is connected to a local area network, the camera responsible for the local area network will quickly scan and find the object in its environment.

[0063] For the bracelet, a similar energy replenishment method as the flywheel and the mainspring can be adopted. The mainspring is tightened by the rotation of the flywheel, and the mainspring drives the gears to rotate to charge the bracelet, so that the bracelet can continue to work.

[0064] The specific dynamic tracking and status analysis process is as follows:

[0065] See also Figure 3In step S101, in response to the acquired connection signal, an image group associated with the connection signal is acquired, the image group includes multiple images, and the images in the image group are divided into two types, the first type includes objects, and the second type does not include objects. Both groups of images in the image group need to be parsed until the object is found.

[0066] In step S102, the image group is parsed and the identification features of the object are obtained. The function of the identification features is to enable the camera to track the movement of the object. There are several types of identification features, namely facial image, first body feature image, second body feature image and body feature image. The function of the facial image is to determine the tracking object. For example, if an object and a visitor exist in a room at the same time, then the camera in the room may track the visitor because the bracelet worn by the object is connected to the local area network of the camera in the room. When two or more people appear in a room at the same time, the above situation may occur.

[0067] The first body feature image and the second body feature image are used to improve the accuracy of camera tracking. For example, when the subject has its back to the camera, is facing the camera sideways, or lowers its head, the first body feature image and the second body feature image are needed for auxiliary tracking.

[0068] The facial image and the first body feature image appear in the same image, which may be patterns, designs on clothes, accessories or supplies carried, etc. These (patterns, designs on clothes, accessories or supplies carried, etc.) appear in the same image at the same time as the facial image. When the face of the object appears in a picture in the image group collected by the camera but the facial image cannot be used for tracking (the facial image is unclear, and the part of the facial image that appears cannot support recognition), the facial image can be replaced.

[0069] The facial image and the second body feature image do not appear in the same image. The second body feature image may be patterns and designs on clothes, accessories or supplies carried, etc. These (patterns and designs on clothes, accessories or supplies carried, etc.) do not appear in the same image at the same time as the facial image. When the face of the object does not appear in the picture in the image group collected by the camera, the camera can still track the movement of the object.

[0070] Or it can be understood that the first body feature image appears on the front of the object, and when the camera can obtain the facial image of the object, one or more first body feature images will be obtained at the same time; the second body feature image appears on the side and / or back of the object, and when the camera cannot obtain the facial image of the object, one or more second body feature images will be picked up on the object in the image.

[0071] Body feature images are used for state analysis of an object. For example, the normal postures of an object include standing, sitting, and lying. Under normal circumstances, the appearance or movement of body feature images should conform to the normal physiological characteristics of a person. However, when a fall or sudden illness occurs, the appearance or movement of body feature images will not conform to the normal physiological characteristics of a person.

[0072] See also Figure 4 ,The body feature images include head, arms and legs, and the number is five. The head body feature image is composed of the head contour of the object, and the arm and leg body feature images are composed of two segments. In the body feature image belonging to the arm, the three points are the palm, elbow joint and shoulder joint, and in the body feature image belonging to the leg, the three points are the foot, knee joint and hip joint.

[0073] During the entire use process, the dynamic tracking and state analysis method disclosed in the present application will continue to use identification features to track the movement trajectory of the object. The living habits of the object are also taken into consideration here. The identification features belonging to the object need to be updated regularly, such as once a day or every few hours.

[0074] The state analysis of the object is carried out in step S104, in which the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature image is compared, and an early warning is issued when the changing speed of the moving speed, moving frequency or minimum straight-line distance is less than the set speed, which is the content of step S105.

[0075] These situations are described below:

[0076] If the body feature image moves too fast, it generally means that the subject has fallen. At this time, the subject's body will move rapidly and uncontrollably. When using the movement speed for judgment, multiple body feature images need to be used synchronously to improve the accuracy of the judgment.

[0077] The moving frequency of the body feature image refers to the tremor of a certain part of the subject's body, which generally means that the subject has a sudden illness, such as a sudden heart attack or an uncontrolled tremor of a certain part of the subject's body after falling.

[0078] The speed of change of the minimum straight-line distance in the vertical direction is too fast, which often occurs when the subject suddenly sits down, lies down or falls down. Under normal circumstances, the sitting and lying down speed of the subject is constant. When the speed of change of the minimum straight-line distance in the vertical direction is too fast, it means that the subject's body is out of control at this time.

[0079] When the movement speed, movement frequency or the change rate of the minimum straight-line distance is less than any of the set conditions, the clinical care system will issue an early warning.

[0080] For example, the clinical care system is connected to the cloud. After an early warning is issued, the cloud will issue an alarm to remind the staff to conduct manual inspection and give treatment suggestions after manual judgment. They can choose to ignore or send someone to further confirm or call 120. For example, if the subject can stand up on his own after a sudden fall, it can be ignored. Alternatively, the cloud will send a message to the subject's family's mobile phone or push a reminder to the app on the mobile phone, and the subject's family will handle it, such as Figure 5 shown.

[0081] As a specific implementation of the dynamic tracking and state analysis method provided in the application, when an object suddenly disappears from the image group and exceeds the set time, an alarm is issued. This is mainly to avoid the situation where the camera cannot collect images and cannot judge the state of the object because the object falls and is behind furniture or other objects.

[0082] For example, if the subject falls in front of a sofa, the camera's field of view may be blocked by a coffee table or a desk, causing the camera to be unable to capture images or the captured images to be missing. Here, the missing images are judged as the sudden disappearance of the subject in the image group.

[0083] In addition to the above determination method, the present application also provides another determination method. When the moving distance of one of the identification features in the vertical direction exceeds the allowed distance, the stationary time of the object is calculated, and an early warning is issued after the stationary time exceeds the allowed stationary time.

[0084] This determination method expands the determination method when an accident occurs, and uses the vertical movement distance of the facial image, the first body feature image, and the second body feature image to make a judgment. This determination method serves as a supplement to the determination method described in the above content.

[0085] For example, if an object falls and has cabinets, walls, and chairs as support, its speed may be reduced. At this time, if speed is used for judgment, misjudgment may occur. When the vertical moving distance of the moving facial image, the first body feature image, and the second body feature image is used as the judgment method, when the moving distance exceeds the allowed distance, the timing will be triggered, that is, the static time of the object will be calculated, and an early warning will be issued after the static time exceeds the allowed static time.

[0086] For example, if the subject is 1.7 meters tall and his height when squatting is 0.5 meters, when it is detected that the facial image has moved less than 0.5 meters in the vertical direction, it means that the subject may be in danger. At this time, the timer starts. If the subject has not stood up after exceeding the allowed still time, an early warning will be issued.

[0087] Furthermore, when calculating the stationary time of an object, the object will be excluded from the calculation range if it appears in a set area or a recognized safe area. The set area or recognized safe area here refers to resting areas such as beds and sofas. In these areas, if the object lies flat, the vertical movement distance of the recognition feature will exceed the allowed distance. Excluding it can avoid false alarms.

[0088] Safety monitoring in these areas can be achieved through wristbands, which can monitor parameters such as the subject's body temperature and heart rate. Analysis of these parameters can detect problems in time and issue warnings when the subject is in a lying position.

[0089] See also Figure 6 As a specific implementation of the dynamic tracking and state analysis method provided by the application, the process of obtaining the second body posture characteristic image includes the following steps:

[0090] S201, obtaining an image including a facial image and / or a first body feature image, recorded as a reference image;

[0091] S202, obtaining a reference image, wherein the reference image includes a portion of the facial image and / or the first body feature image;

[0092] S203, when the facial image and / or the first body feature image disappears in the reference image, a part of the object in the reference image is selected as a second body feature image.

[0093] Specifically, the process of obtaining the second body feature image needs to be obtained with the help of the facial image and / or the first body feature image. It should be understood that the multiple images in the image group are continuous in time sequence, and when the facial image and / or the first body feature image appears in one of the images, the object can be determined and the movement of the object can be tracked.

[0094] When the movement of the facial image and / or the first body feature image is tracked, the object can be continuously tracked through the facial image and / or the first body feature image, and then a part of the object in the reference image is taken as the second body feature image.

[0095] During the continuous tracking of the object, the following steps are also used to track the movement of the facial image and / or the first body feature image:

[0096] S301, selecting a part of the local image of the object as a moving reference image according to the movement of the object;

[0097] S302, extending the reference image as a starting point on the image belonging to the object to obtain a movement trajectory; and

[0098] S303, when the facial image and / or the first body feature image disappears in the reference image, selecting a part of the object in the reference image as a second body feature image;

[0099] The selection range of the second body shape characteristic image is the part of the image belonging to the object.

[0100] See also Figure 7 In step S301 to step S303, when the facial image and / or the first body feature image (1 in the figure) belonging to the object moves, a part of the local image is selected from the object as a moving reference (2 to 6 in the image diagram), and the moving reference image is updated as the facial image and / or the first body feature image moves. When the facial image and / or the first body feature image disappears in the reference image, a part of the reference image belonging to the object is selected as the second body feature image (7 in the figure).

[0101] Here, the moving reference image can be considered to include a first part and a second part, which are connected. When the third part appears, the second part is converted to the first part, and the third part is converted to the second part, that is, the first part and the second part are in a continuous updating process.

[0102] Furthermore, the number of movement trajectories generated is multiple.

[0103] The present application also provides a dynamic tracking and state analysis device, comprising:

[0104] A first acquisition unit, configured to acquire, in response to the acquired connection signal, an image group associated with the connection signal, wherein the image group includes a plurality of images;

[0105] A parsing unit, used for parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image and a body feature image; the facial image and the first body feature image appear in the same image, and the facial image and the second body feature image do not appear in the same image;

[0106] A tracking unit, used to track the movement trajectory of the object using the identification features;

[0107] a comparison unit, used for comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature image; and

[0108] The alarm unit is used to issue an early warning when the speed of change of the moving speed, moving frequency or minimum straight-line distance is less than the set speed.

[0109] Furthermore, when the object suddenly disappears from the image group and exceeds a set time, an early warning is issued.

[0110] Further, when the moving distance of one of the identification features in the vertical direction exceeds the allowed distance, the stationary time of the object is calculated, and an early warning is issued after the stationary time exceeds the allowed stationary time;

[0111] The trigger condition for calculating the stationary time of the object is that the straight-line distance moved by the multiple identification features in the vertical direction is greater than a set distance.

[0112] Furthermore, when calculating the stationary time of the object, the object appearing in the set area or the identified safe area is excluded from the calculation range.

[0113] Furthermore, it also includes:

[0114] A second acquisition unit, used to obtain an image including a facial image and / or a first body feature image, recorded as a reference image;

[0115] A third acquisition unit, configured to obtain a reference image, wherein the reference image includes a portion of the facial image and / or the first body feature image;

[0116] The first selection unit is used to select a part of the object in the reference image as the second body feature image after the facial image and / or the first body feature image disappears in the reference image.

[0117] Furthermore, it also includes:

[0118] A second selection unit, used for selecting a part of the local image of the object as a moving reference image according to the movement of the object;

[0119] a movement trajectory generating unit, configured to extend the movement trajectory on the image belonging to the object from the reference image as a starting point, to obtain the movement trajectory; and

[0120] A third selection unit, configured to select a portion of the object in the reference image as a second body feature image after the facial image and / or the first body feature image disappears in the reference image;

[0121] The selection range of the second body shape characteristic image is the part of the image belonging to the object.

[0122] Furthermore, the number of movement trajectories generated is multiple.

[0123] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0124] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0125] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0130] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0131] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0132] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0133] The present application also provides a clinical care system, the system comprising:

[0134] One or more image collectors, used for collecting images;

[0135] one or more memories for storing instructions; and

[0136] One or more processors are used to call and run the instructions from the memory to process the acquired images and execute the method as described above.

[0137] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the clinical care system performs operations of the clinical care system corresponding to the above method.

[0138] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0139] The chip system may be composed of chips, or may include chips and other discrete devices.

[0140] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0141] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0142] Optionally, the computer instructions are stored in a memory.

[0143] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0144] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0145] The nonvolatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0146] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0147] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A dynamic tracking and state analysis method, characterized in that: include: In response to the acquired connection signal, acquiring an image group associated with the connection signal, the image group including a plurality of images; Parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image, and a body feature image; Track the movement of objects using identification features; Comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature images; When any of the change speed of the minimum straight-line distance, the moving speed or the moving frequency is greater than the setting, an alarm is issued; Wherein, the facial image and the first body feature image appear in the same image, and the facial image and the second body feature image do not appear in the same image; The process of obtaining the second body feature image includes: Obtaining an image including a facial image and / or a first body feature image, recorded as a reference image; Obtaining a reference image, wherein the reference image includes a portion of the facial image and / or the first body feature image; When the facial image and / or the first body feature image disappears in the reference image, a portion of the object in the reference image is selected as a second body feature image; Also includes: Selecting a part of the local image of the object as a moving reference image according to the movement of the object; Taking the reference image as the starting point, extend it on the image belonging to the object to obtain the movement trajectory; When the facial image and / or the first body feature image disappears in the reference image, a portion of the object in the reference image is selected as a second body feature image; The selection range of the second body shape characteristic image is the part of the image belonging to the object.

2. The dynamic tracking and state analysis method according to claim 1, characterized in that: When an object suddenly disappears from the image group and exceeds the set time, an alarm is issued.

3. The dynamic tracking and state analysis method according to claim 1 or 2, characterized in that: When the moving distance of one of the recognition features in the vertical direction exceeds the allowed distance, the stationary time of the object is calculated, and an early warning is issued after the stationary time exceeds the allowed stationary time; The trigger condition for calculating the stationary time of the object is that the straight-line distance moved by the plurality of identification features in the vertical direction is greater than a set distance.

4. The dynamic tracking and state analysis method according to claim 3, characterized in that: When calculating the stationary time of an object, the object that appears in the set area or the recognized safe area is excluded from the calculation range.

5. The dynamic tracking and state analysis method according to claim 1, characterized in that: The number of moving trajectories in the process of generating is multiple.

6. A dynamic tracking and state analysis device, characterized in that: include: A first acquisition unit, configured to acquire, in response to the acquired connection signal, an image group associated with the connection signal, wherein the image group includes a plurality of images; A parsing unit, used for parsing the image group to obtain identification features of the object, the identification features including a facial image, a first body feature image, a second body feature image and a body feature image; the facial image and the first body feature image appear in the same image, and the facial image and the second body feature image do not appear in the same image; A tracking unit, used to track the movement trajectory of the object using the identification features; A comparison unit, used for comparing the moving speed or moving frequency or the minimum straight-line distance in the vertical direction of the body feature image; An alarm unit is used to issue an early warning when any one of the change speed of the minimum straight-line distance, the moving speed or the moving frequency is greater than a setting; The process of obtaining the second body feature image includes: Obtaining an image including a facial image and / or a first body feature image, recorded as a reference image; Obtaining a reference image, wherein the reference image includes a portion of the facial image and / or the first body feature image; When the facial image and / or the first body feature image disappears in the reference image, a portion of the object in the reference image is selected as a second body feature image; Also includes: Selecting a part of the local image of the object as a moving reference image according to the movement of the object; Taking the reference image as the starting point, extend it on the image belonging to the object to obtain the movement trajectory; When the facial image and / or the first body feature image disappears in the reference image, a portion of the object in the reference image is selected as a second body feature image; The selection range of the second body shape characteristic image is the part of the image belonging to the object.

7. A clinical nursing system, characterized in that: The system comprises: One or more image collectors, used for collecting images; one or more memories for storing instructions; One or more processors, configured to call and execute the instructions from the memory to process the acquired images and execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images