Method and apparatus for detecting backward sliding behavior

Abstract

The present disclosure relates to the technical field of behavior detection, and provides a detection method and device for reverse climbing a slide. The method comprises: collecting an image of a target object on a target slide; compiling the image to obtain first packet information, and determining first point cloud data corresponding to the image according to the first packet information; identifying the first point cloud data through a neural network model to determine whether the target object has a behavior of reverse climbing the slide; and issuing an alarm in the case that the target object has the behavior of reverse climbing the slide. The above technical means solves the problem that an alarm cannot be automatically issued when a child reverse climbs a slide in the prior art.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of behavior detection, and particularly relates to a detection method and device for reverse climbing a slide. BACKGROUND

[0002] In places such as amusement parks, kindergartens and communities, children's slides are very common. Children slide from the upper end to the lower end of the slide, which is called normal climbing a slide, and children climb from the lower end to the upper end of the slide, which is called reverse climbing a slide. Children playing a slide should be normal climbing a slide, and reverse climbing a slide is risky and should be prohibited. At present, regarding children playing a slide, only parents or staff can warn and watch beside the slide to regulate the behavior of children playing a slide and avoid safety hazards. However, this requires manpower, and there is currently no method to issue an alarm when a child reverses a slide.

[0003] In the process of implementing the present disclosure, the inventors have found that at least the following technical problem exists in the related art: When a child reverses a slide, an alarm cannot be automatically issued. SUMMARY

[0004] Therefore, the embodiments of the present disclosure provide a detection method and device for reverse climbing a slide, an electronic device and a computer readable storage medium to solve the problem that an alarm cannot be automatically issued when a child reverses a slide in the prior art.

[0005] In a first aspect, the embodiments of the present disclosure provide a detection method for reverse climbing a slide, comprising: collecting an image of a target object on a target slide; compiling the image to obtain first packet information, and determining first point cloud data corresponding to the image according to the first packet information; identifying the first point cloud data through a neural network model to determine whether the target object has a behavior of reverse climbing a slide, wherein the neural network model has learned and saved a corresponding relationship between the first point cloud data and whether the target object has the behavior of reverse climbing a slide through training; and issuing an alarm in the case that the target object has the behavior of reverse climbing a slide.

[0006] In a second aspect, the embodiments of the present disclosure provide a detection device for reverse climbing a slide, comprising: a collection module configured to collect an image of a target object on a target slide; a determination module configured to compile the image to obtain first packet information, and determine first point cloud data corresponding to the image according to the first packet information; an identification module configured to identify the first point cloud data through a neural network model to determine whether the target object has a behavior of reverse climbing a slide, wherein the neural network model has learned and saved a corresponding relationship between the first point cloud data and whether the target object has the behavior of reverse climbing a slide through training; and a warning module configured to issue an alarm in the case that the target object has the behavior of reverse climbing a slide.

[0007] In a third aspect, the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method.

[0008] In a fourth aspect, the present disclosure provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the steps of the method.

[0009] Compared with the prior art, the present disclosure has the beneficial effects that: the present disclosure collects images of a target object on a target slide; compiles the images to obtain first packet information, and determines first point cloud data corresponding to the images according to the first packet information; identifies the first point cloud data through a neural network model to determine whether the target object has a behavior of climbing the slide in reverse; and in the case that the target object has the behavior of climbing the slide in reverse, an alarm is issued. Therefore, the above technical means can solve the problem in the prior art that an alarm cannot be automatically issued when a child climbs a slide in reverse, thereby avoiding safety hazards when a child plays on a slide. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0011] Figure 1 is a scene schematic diagram of an application scenario of the present disclosure;

[0012] Figure 2 is a flow schematic diagram of a method for detecting a behavior of climbing a slide in reverse provided by the present disclosure;

[0013] Figure 3 is a structural schematic diagram of a device for detecting a behavior of climbing a slide in reverse provided by the present disclosure;

[0014] Figure 4 is a structural schematic diagram of an electronic device provided by the present disclosure. DETAILED DESCRIPTION

[0015] In the following description, for the purposes of explanation, numerous specific details are set forth in order to thoroughly describe certain embodiments of the present disclosure. It should be understood, however, that the present disclosure can be practiced in other embodiments that do not require all of the specific details described. In other instances, well-known systems, structures, circuits, and methods have not been described in detail since it would be understood that from the description of the present disclosure.

[0016] A method and apparatus for detecting a reverse sliding behavior will be described in detail below with reference to the accompanying drawings.

[0017] Figure 1 is a scenario diagram of an application scenario of embodiments of the present disclosure. The application scenario can include terminal devices 1, 2, and 3, a server 4, and a network 5.

[0018] The terminal devices 1, 2, and 3 can be hardware or software. When the terminal devices 1, 2, and 3 are hardware, they can be various electronic devices with a display screen and supporting communication with the server 4, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like; when the terminal devices 1, 2, and 3 are software, they can be installed in the electronic devices as above. The terminal devices 1, 2, and 3 can be implemented as multiple software or software modules, or as a single software or software module, and the present disclosure does not limit the terminal devices 1, 2, and 3 in this regard. Further, the terminal devices 1, 2, and 3 can have various applications installed thereon, such as a data processing application, an instant messaging tool, a social platform software, a search application, a shopping application, and the like.

[0019] The server 4 can be a server providing various services, for example, a background server receiving a request sent by a terminal device establishing a communication connection therewith. The background server can receive and analyze the request sent by the terminal device, and generate a processing result. The server 4 can be a single server, a server cluster composed of several servers, or a cloud computing service center, and the present disclosure does not limit the server 4 in this regard.

[0020] It should be noted that the server 4 can be hardware or software. When the server 4 is hardware, it can be various electronic devices providing various services for the terminal devices 1, 2, and 3. When the server 4 is software, it can be multiple software or software modules providing various services for the terminal devices 1, 2, and 3, or a single software or software module providing various services for the terminal devices 1, 2, and 3, and the present disclosure does not limit the server 4 in this regard.

[0021] The network 5 can be a wired network using coaxial cables, twisted-pair cables and optical fibers, or a wireless network that can realize interconnection of various communication devices without wiring, for example, Bluetooth, Near Field Communication (NFC), Infrared, etc., and the embodiments of the present disclosure do not make any limitation in this regard.

[0022] The user can establish a communication connection with the server 4 via the network 5 through the terminal devices 1, 2 and 3 to receive or send information, etc. It should be noted that the specific types, quantities and combinations of the terminal devices 1, 2 and 3, the server 4 and the network 5 can be adjusted according to the actual needs of the application scenario, and the embodiments of the present disclosure do not make any limitation in this regard.

[0023] Figure 2 is a flowchart of a method for detecting reverse sliding behavior of a slide provided by an embodiment of the present disclosure. Figure 2 The method for detecting reverse sliding behavior of a slide can be executed by Figure 1 a terminal device or a server. As Figure 2 indicated, the method for detecting reverse sliding behavior of a slide includes:

[0024] S201, collecting an image of a target object on a target slide;

[0025] S202, compiling the image to obtain first packet information, and determining first point cloud data corresponding to the image according to the first packet information;

[0026] S203, identifying the first point cloud data through a neural network model to determine whether the target object has reverse sliding behavior of a slide, wherein the neural network model has learned and saved a corresponding relationship between the first point cloud data and whether the target object has reverse sliding behavior of a slide through training;

[0027] S204, issuing an alarm in the case that the target object has reverse sliding behavior of a slide.

[0028] An image of a target object on a target slide is collected through a visual collection device, wherein the visual collection device can be a visual sensing device; the image is compiled through a communication transmission device to obtain first packet information, and the communication transmission device is further configured to transmit the packet information to a cloud computing platform. Since the image is compiled to obtain packet information, which is a common method in the field of image processing and will not be described here. First point cloud data corresponding to the image is determined through the cloud computing platform according to the first packet information, wherein the packet information can be understood as a kind of streaming media information. The first point cloud data is identified through a neural network model to determine whether the target object has reverse sliding behavior of a slide, and an alarm is issued in the case that the target object has reverse sliding behavior of a slide.

[0029] According to the technical scheme provided by the embodiments of the present disclosure, because the embodiments of the present disclosure collect the image of the target object on the target slide; compile the image to obtain first package information, and determine first point cloud data corresponding to the image according to the first package information; identify the first point cloud data through a neural network model to determine whether the target object has the behavior of climbing the slide in reverse; and in the case that the target object has the behavior of climbing the slide in reverse, an alarm is sent. Therefore, by using the above technical means, the problem that an alarm cannot be automatically sent when a child climbs a slide in reverse in the prior art can be solved, and the safety hazard when a child plays on a slide can be avoided.

[0030] In step S202, the first point cloud data corresponding to the image is determined according to the first package information, including: counting the first package information to obtain statistical information; analyzing the first package information according to the statistical information to obtain analysis information; performing a selection operation on the first package information according to the analysis information; and determining the first point cloud data corresponding to the image according to the first package information after the selection operation.

[0031] The package information corresponding to the image may contain useless information. In order to improve the efficiency of the neural network model identification, the present disclosure provides a method for selecting the package information. The statistical information is a summary of the package information. For example, some information in the package information is the information corresponding to the image background, and some information is the information corresponding to the target object in the image. The analysis of the first package information is to analyze which information in the package information is needed and which information is not needed. The neural network model detects whether the target object has the behavior of climbing the slide in reverse. The information of the target object is the most important, so the information corresponding to the image background can be deleted from the package information, and only the information of the target object is retained.

[0032] In step S203, the first point cloud data is identified through the neural network model to determine whether the target object has the behavior of climbing the slide in reverse, including: the first point cloud data includes: first joint point cloud data, first head point cloud data and first foot point cloud data; at least one of the following data is input into the neural network model: the first joint point cloud data, the first head point cloud data and the first foot point cloud data, and a judgment result is output, wherein the judgment result is used to indicate whether the target object has the behavior of climbing the slide in reverse.

[0033] The joints, head and feet of children climbing a slide in reverse and in normal are different, so whether the child is climbing the slide in reverse can be determined by detecting the joint point cloud data, head point cloud data and foot point cloud data. The target object includes but is not limited to children. For example, the head of a child climbing a slide in reverse is face down and the skull is up, and the face of a child climbing a slide in normal will not be down, so whether the child is climbing the slide in reverse can be determined by the information of the head of the child. The head of the child should be understood as the part above the shoulder of the child. For example, the feet of a child climbing a slide in reverse are toe down and heel up, and the feet of a child climbing a slide in normal are toe up and heel down, so whether the child is climbing the slide in reverse can be determined by the information of the feet of the child.

[0034] In an optional embodiment, the method comprises: acquiring multiple images of the target object at different angles; compiling the multiple images to obtain second packet information, and determining second point cloud data corresponding to the multiple images according to the second packet information; identifying the second point cloud data through a neural network model to determine whether the target object is climbing the slide in reverse, wherein the neural network model has learned and saved the corresponding relationship between the second point cloud data and whether the target object is climbing the slide in reverse through training; and issuing an alarm in the case that the target object is climbing the slide in reverse.

[0035] Because the acquisition angle relative to the target object will produce a certain shielding, for example, some information cannot be captured in the picture taken from the side of the slide. In order to solve this problem, the embodiment of the disclosure acquires multiple images of the target object at different angles, and reduces the shielding part and increases the useful information through processing of the multiple images at different angles, thereby improving the detection accuracy. It should be noted that the second point cloud data also includes joint point cloud data, head point cloud data and foot point cloud data.

[0036] In an optional embodiment, the method comprises: acquiring multiple images of the target object; compiling the multiple images to obtain third packet information, and determining first displacement point cloud data corresponding to the multiple images according to the third packet information; identifying the first displacement point cloud data through a neural network model to determine whether the target object is climbing the slide in reverse, wherein the neural network model has learned and saved the corresponding relationship between the first displacement point cloud data and whether the target object is climbing the slide in reverse through training; and issuing an alarm in the case that the target object is climbing the slide in reverse.

[0037] The displacement of the target object can also be used to determine whether the target object is climbing the slide in reverse. For example, the displacement of the target object climbing the slide in reverse is upward, and the displacement of the target object climbing the slide is downward (here, upward and downward are inclined, for example, upward can be thirty degrees upward horizontally). The first displacement point cloud data includes the direction of the displacement.

[0038] In an optional embodiment, the method comprises: obtaining a training data set, wherein the training data set comprises a plurality of images of people climbing a slide in reverse and a plurality of images of people climbing a slide normally; compiling the training data set to obtain fourth package information, and determining third point cloud data corresponding to the training data set according to the fourth package information; and training a neural network model using the third point cloud data.

[0039] Before training the neural network model using the third point cloud data, the third point cloud data should be labeled. Training the neural network model using the third point cloud data enables the neural network model to learn and save the correspondence between the point cloud data and whether the person is climbing the slide in reverse through training.

[0040] Training the neural network model using the third point cloud data comprises: the third point cloud data comprises: second joint point cloud data, second head point cloud data, second foot point cloud data, second displacement point cloud data, and multi-angle point cloud data; and training the neural network model using at least one of the following data: the second joint point cloud data, the second head point cloud data, the second foot point cloud data, the second displacement point cloud data, and the multi-angle point cloud data.

[0041] The second joint point cloud data, the second head point cloud data, the second foot point cloud data, and the second displacement point cloud data are similar to the first joint point cloud data, the first head point cloud data, the first foot point cloud data, and the first displacement point cloud data, respectively. The first and second only indicate that the images corresponding to the point cloud data are different. The multi-angle point cloud data is similar to the second point cloud data, and the multi-angle point cloud data is point cloud data corresponding to a training image collected at different angles.

[0042] All the optional technical solutions described above can be combined to form optional embodiments of the present application, which will not be described again.

[0043] The following is an embodiment of the device of the present disclosure, which can be used to execute the method embodiments of the present disclosure. For details not disclosed in the device embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

[0044] Figure 3 is a schematic diagram of a detection device for reverse slide climbing behavior provided by an embodiment of the present disclosure. As shown in Figure 3 The detection device for reverse slide climbing behavior comprises:

[0045] The collection module 301 is configured to collect an image of a target object on a target slide;

[0046] The determination module 302 is configured to compile the image to obtain first packet information, and determine first point cloud data corresponding to the image according to the first packet information.

[0047] The recognition module 303 is configured to recognize the first point cloud data through a neural network model to determine whether the target object has a behavior of climbing the slide in reverse.

[0048] The warning module 304 is configured to issue an alarm in the case that the target object has the behavior of climbing the slide in reverse.

[0049] An image of a target object on a target slide is collected through a visual collection device, wherein the visual collection device can be a visual sensing device; the image is compiled through a communication transmission device to obtain first packet information, and the communication transmission device is also used to transmit the packet information to a cloud computing platform; because the image is compiled to obtain the packet information, which is a common method in the field of image processing, and will not be described here; the cloud computing platform is used to determine first point cloud data corresponding to the image according to the first packet information, wherein the packet information can be understood as a kind of streaming media information; the neural network model is used to recognize the first point cloud data to determine whether the target object has a behavior of climbing the slide in reverse, and an alarm is issued in the case that the target object has the behavior of climbing the slide in reverse.

[0050] According to the technical scheme provided by the embodiment of the present disclosure, because the image of the target object on the target slide is collected; the image is compiled to obtain the first packet information, and the first point cloud data corresponding to the image is determined according to the first packet information; the first point cloud data is recognized through the neural network model to determine whether the target object has a behavior of climbing the slide in reverse; and an alarm is issued in the case that the target object has the behavior of climbing the slide in reverse, therefore, by using the above technical means, the problem that an alarm cannot be automatically issued when a child climbs the slide in reverse in the prior art can be solved, and the safety hazard when the child plays the slide can be avoided.

[0051] Optionally, the determination module 302 is further configured to count the first packet information to obtain statistical information; analyze the first packet information according to the statistical information to obtain analysis information; perform a selection operation on the first packet information according to the analysis information; and determine the first point cloud data corresponding to the image according to the first packet information after the selection operation.

[0052] The packet information corresponding to the image can contain useless information. In order to improve the efficiency of the neural network model identification, the present disclosure provides a method for screening the packet information. The statistical information is a summary of the packet information. For example, some information in the packet information is the information corresponding to the image background, and some information is the information corresponding to the target object in the image. The analysis of the first packet information is to analyze which information in the packet information is needed and which information is not needed. The neural network model detects whether the target object has the behavior of climbing down the slide. The information of the target object is the most important, so the information corresponding to the image background can be deleted from the packet information, and only the information of the target object is retained.

[0053] The first point cloud data includes: first joint point cloud data, first head point cloud data and first foot point cloud data.

[0054] Optionally, the recognition module 303 is further configured to input at least one of the following data into the neural network model: the first joint point cloud data, the first head point cloud data and the first foot point cloud data, and output a judgment result, wherein the judgment result is used to indicate whether the target object has the behavior of climbing down the slide.

[0055] The joints, head and feet of children climbing down the slide and children climbing up the slide are different, so the behavior of climbing down the slide can be judged by detecting the joint point cloud data, the head point cloud data and the foot point cloud data. The target object includes but is not limited to children. For example, the head of the child climbing down the slide is face down, and the skull is on the top, while the face of the child climbing up the slide will not be down. By the information of the head of the child, it can be judged whether the behavior of climbing down the slide exists. The head of the child should be understood as the part above the shoulder of the child. For example, the foot of the child climbing down the slide is toe down and heel up, while the foot of the child climbing up the slide is toe up and heel down. By the information of the foot of the child, it can be judged whether the behavior of climbing down the slide exists.

[0056] Optionally, the recognition module 303 is further configured to acquire a plurality of images of the target object at different angles; compile the plurality of images to obtain second packet information, and determine second point cloud data corresponding to the plurality of images according to the second packet information; identify the second point cloud data through the neural network model to judge whether the target object has the behavior of climbing down the slide, wherein the neural network model has learned and saved the corresponding relationship between the second point cloud data and whether the target object has the behavior of climbing down the slide through training; and in the case that the target object has the behavior of climbing down the slide, an alarm is issued.

[0057] Because the collection angle relative to the target object will produce a certain shielding, such as the picture of the slide side, some information cannot be taken. In order to solve this problem, the embodiment of the disclosure collects multiple images of the target object at different angles, and through processing of the multiple images at different angles, the shielding part is reduced, the useful information is increased, and the detection accuracy is improved. It should be noted that the second point cloud data also includes: joint point cloud data, head point cloud data and foot point cloud data.

[0058] Optionally, the recognition module 303 is further configured to collect multiple images of the target object; compile the multiple images to obtain third package information, and determine first displacement point cloud data corresponding to the multiple images according to the third package information; identify the first displacement point cloud data through the neural network model to determine whether the target object has the behavior of climbing the slide backwards, wherein the neural network model has learned and saved the corresponding relationship between the first displacement point cloud data and whether the target object has the behavior of climbing the slide backwards through training; and in the case that the target object has the behavior of climbing the slide backwards, issue an alarm.

[0059] Through the displacement of the target object, it can also be determined whether the target object has the behavior of climbing the slide backwards. For example, the direction of the displacement of the target object climbing the slide backwards is upward, and the direction of the displacement of the target object climbing the slide normally is downward (here, upward and downward are both inclined, for example, upward can be thirty degrees horizontally upward). The first displacement point cloud data includes the direction of the displacement.

[0060] Optionally, the recognition module 303 is further configured to obtain a training data set, wherein the training data set contains: multiple images of people climbing the slide backwards and multiple images of people climbing the slide normally; compile the training data set to obtain fourth package information, and determine third point cloud data corresponding to the training data set according to the fourth package information; and train the neural network model by using the third point cloud data.

[0061] Before training the neural network model by using the third point cloud data, the third point cloud data should be labeled and processed. Training the neural network model by using the third point cloud data enables the neural network model to learn and save the corresponding relationship between the point cloud data and whether the person has the behavior of climbing the slide backwards through training.

[0062] The third point cloud data includes: second joint point cloud data, second head point cloud data, second foot point cloud data, second displacement point cloud data and multi-angle point cloud data.

[0063] Optionally, the recognition module 303 is further configured to train the neural network model by using at least one of the following data: second joint point cloud data, second head point cloud data, second foot point cloud data, second displacement point cloud data and multi-angle point cloud data.

[0064] The second joint point cloud data, the second head point cloud data, the second foot point cloud data, and the second displacement point cloud data are similar to the first joint point cloud data, the first head point cloud data, the first foot point cloud data, and the first displacement point cloud data, respectively. The first and the second only indicate that the point cloud data correspond to different images. The multi-angle point cloud data is similar to the second point cloud data. The multi-angle point cloud data is point cloud data corresponding to training images collected at different angles.

[0065] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution. The execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0066] Figure 4 FIG. 4 is a schematic diagram of an electronic device 4 provided by an embodiment of the present disclosure. As shown in the figure, the electronic device 4 of this embodiment includes a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. The processor 401 implements the steps in each of the above method embodiments when executing the computer program 403. Alternatively, the processor 401 implements the functions of each module / unit in each of the above device embodiments when executing the computer program 403. Figure 4

[0067] By way of example, the computer program 403 can be divided into one or more modules / units, which are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 403 in the electronic device 4.

[0068] The electronic device 4 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The electronic device 4 can include but is not limited to the processor 401 and the memory 402. Those skilled in the art can understand that the electronic device 4 can include more or fewer components, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, and the like. Figure 4 The electronic device 4 is only an example and does not constitute a limitation on the electronic device 4, and can include more or fewer components than the diagram, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, and the like.

[0069] ​The processor 401 can be a central processing unit (CPU), or other general purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like. The general purpose processor can be a microprocessor, or the processor can be any conventional processor, etc.

[0070] The memory 402 can be an internal storage unit of the electronic device 4, for example, a hard disk or a memory of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like equipped on the electronic device 4. Further, the memory 402 can include both the internal storage unit and the external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0072] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0073] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0074] In the embodiments provided by the present disclosure, it should be understood that the disclosed apparatus / equipment and method can be implemented in other ways. For example, the apparatus / equipment embodiments described above are merely schematic, for example, the division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0075] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0076] In addition, each functional unit in each embodiment of the present disclosure can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0077] The integrated modules / units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program can include computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier signal and telecommunication signal.

[0078] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure.

Claims

1. A method of detecting a backward sliding behavior, characterized by, The method comprises the following steps: collecting an image of a target object on a target slide; compiling the image to obtain first packet information, and determining first point cloud data corresponding to the image according to the first packet information; identifying the first point cloud data through a neural network model to determine whether the target object has a behavior of climbing the slide in reverse, wherein the neural network model has learned and saved a corresponding relationship between the first point cloud data and whether the target object has the behavior of climbing the slide in reverse through training; in the case that the target object has the behavior of climbing the slide in reverse, issuing an alarm; the step of identifying the first point cloud data through the neural network model to determine whether the target object has the behavior of climbing the slide in reverse comprises: the first point cloud data comprises first joint point cloud data, first head point cloud data and first foot point cloud data; inputting at least one of the first joint point cloud data, the first head point cloud data and the first foot point cloud data into the neural network model to output a judgment result, wherein the judgment result is used to indicate whether the target object has the behavior of climbing the slide in reverse; collecting multiple images of the target object; compiling the multiple images to obtain third packet information, and determining first displacement point cloud data corresponding to the multiple images according to the third packet information; identifying the first displacement point cloud data through a neural network model to determine whether the target object has a behavior of climbing the slide in reverse, wherein the neural network model has learned and saved a corresponding relationship between the first displacement point cloud data and whether the target object has the behavior of climbing the slide in reverse through training; in the case that the target object has the behavior of climbing the slide in reverse, issuing an alarm; obtaining a training data set, wherein the training data set comprises multiple images of a person climbing the slide in reverse and multiple images of a person climbing the slide normally; compiling the training data set to obtain fourth packet information, and determining third point cloud data corresponding to the training data set according to the fourth packet information; training the neural network model using the third point cloud data; the step of training the neural network model using the third point cloud data comprises: the third point cloud data comprises second joint point cloud data, second head point cloud data, second foot point cloud data, second displacement point cloud data and multi-angle point cloud data; training the neural network model using at least one of the second joint point cloud data, the second head point cloud data, the second foot point cloud data, the second displacement point cloud data and the multi-angle point cloud data.

2. The method of claim 1, wherein, the step of determining the first point cloud data corresponding to the image according to the first packet information comprises: statistically analyzing the first packet information to obtain statistical information; analyzing the first packet information according to the statistical information to obtain analysis information; performing a selection operation on the first packet information according to the analysis information; determining the first point cloud data corresponding to the image according to the first packet information after the selection operation.

3. The method of claim 1, wherein, The method comprises the following steps: collecting multiple images of the target object from different angles; compile the plurality of images to obtain second packet information, and determine second point cloud data corresponding to the plurality of images according to the second packet information; identify the second point cloud data through a neural network model to determine whether the target object has the behavior of climbing a slide in reverse, wherein the neural network model has learned and stored a corresponding relationship between the second point cloud data and whether the target object has the behavior of climbing a slide in reverse through training; in a case where the target object has the behavior of climbing a slide in reverse, issue an alarm.

4. A device for detecting a backward sliding behavior, characterized in that The device adopts the method of any one of claims 1-3, and the device comprises: a collection module configured to collect images of a target object on a target slide; a determination module configured to compile the images to obtain first packet information, and determine first point cloud data corresponding to the images according to the first packet information; an identification module configured to identify the first point cloud data through a neural network model to determine whether the target object has the behavior of climbing a slide in reverse, wherein the neural network model has learned and stored a corresponding relationship between the first point cloud data and whether the target object has the behavior of climbing a slide in reverse through training; a warning module configured to issue an alarm in a case where the target object has the behavior of climbing a slide in reverse.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 5. The computer program is executed by the processor to implement the steps of the method of any one of claims 1-3.

Images