Interference Prompting Method and Device

Abstract

This application relates to the field of gesture recognition technology, and in particular, to an interference prompt method and device. Among them, the method includes: determining a human body area and a background area from the detected user image; determining the interference degree of the background area on the recognition of the user's action from the human body area; generating interference prompt information according to the interference degree. The interference prompt method and device of the embodiments of this application can determine the interference of background factors on the gesture recognition result in a gesture recognition scenario and prompt the user with interference information.

Description

Technical Field

[0001] This application relates to the technical field of gesture recognition, and in particular, to an interference prompt method and device. Background Art

[0002] With the development of computer vision technology, human body gesture recognition has been applied in fields such as intelligent video surveillance, smart home, sports fitness, human-computer interaction, and medical rehabilitation. Human body gesture recognition mainly takes an image related to the human body gesture as input data and inputs it into a gesture recognition algorithm, and then the gesture recognition algorithm recognizes possible human actions from the input image. In human body gesture recognition, the accuracy of the recognition result is restricted by the input image to a large extent. If the input image has high clarity and few interference factors, the accuracy of the recognized human actions is high; on the contrary, if there are many interference factors in the input image, the accuracy of the recognition result decreases. Therefore, in a gesture recognition scenario, when there are interference factors in the acquired image and the interference factors may affect the gesture recognition result, how to determine and prompt the user about the interference factors has become an urgent technical problem to be solved. Summary of the Invention

[0003] This application provides an interference prompt method and device to determine the interference of background factors on the gesture recognition result and prompt the user with interference information in a gesture recognition scenario.

[0004] In a first aspect, the technical solution of this application provides an interference prompt method, including:

[0005] Determine a human body region and a background region from the detected user image;

[0006] Determine the interference degree of the background region on recognizing the user's action from the human body region;

[0007] Generate interference prompt information according to the interference degree.

[0008] The method of the embodiment of this application can be applied to a human body gesture recognition scenario. When recognizing the gesture of a user, first determine the interference degree of background factors on recognizing the user's action, and send interference prompt information to the user according to the determined interference degree. The interference prompt information can be used to prompt the user that the background influence of the current scenario affects the accurate recognition of the action, and it is recommended to change clothes or change the scene background, etc.

[0009] In combination with the first aspect, in some implementation manners of the first aspect, determining a human body region from the detected user image includes:

[0010] Recognize target joint points from the user image;

[0011] Determine the target joint point or the area formed by the target joint points as the human body area.

[0012] In the embodiments of the present application, all or some of the limb joint points in the user image can be used as target joint points. When determining the human body area, the area formed by the target joint points can be determined as the human body area. For example, determine the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point as target joint points; and determine the area formed by the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point as the human body area. Another optional way is to also determine the target joint point as the human body area. It can be understood that each limb joint point corresponds to a sub-area on the human body contour, and only one limb joint point is included in a sub-area, and the size of the sub-area can be set according to actual needs.

[0013] Combined with the first aspect, in some implementation manners of the first aspect, determining the background area from the user image includes:

[0014] Determine the extended area of the human body area in the user image;

[0015] Determine the extended area as the background area.

[0016] Combined with the first aspect, in some implementation manners of the first aspect, determining the extended area of the human body area in the user image includes:

[0017] Determine the action range area in the user image according to the user's current action and subsequent actions;

[0018] Determine the first area including the action range area in the user image, and determine the extended area of the human body area from the first area.

[0019] Combined with the first aspect, in some implementation manners of the first aspect, determining the extended area of the human body area in the user image includes:

[0020] Determine the sub-extended areas of the respective limb joint points included in the human body area in the user image;

[0021] Determine the sub-extended areas of the respective limb joint points as the extended area of the human body area.

[0022] Combined with the first aspect, in some implementation manners of the first aspect, determining the interference degree of the background area on identifying the user's action from the human body area includes:

[0023] Determine the color difference value between the background area and the human body area;

[0024] Determine the degree of interference of the background region on identifying the user action from the human body region according to the color difference value.

[0025] In combination with the first aspect, in some implementation manners of the first aspect, determining the degree of interference of the background region on identifying the user action from the human body region includes:

[0026] Determine the complexity of the background region;

[0027] Determine the degree of interference of the background region on identifying the user action from the human body region according to the complexity.

[0028] In combination with the first aspect, in some implementation manners of the first aspect, determining the degree of interference of the background region on identifying the user action from the human body region includes:

[0029] According to the information of the background region, determine the accuracy of each limb joint point included in the human body region;

[0030] Determine the degree of interference of the background region on identifying the user action from the human body region according to the accuracy of each limb joint point.

[0031] In combination with the first aspect, in some implementation manners of the first aspect, according to the information of the background region, determining the accuracy of each limb joint point included in the human body region includes:

[0032] Determine the background complexity of each limb joint point included in the human body region and the color difference value between each limb joint point and the background region;

[0033] Determine the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background region.

[0034] In a second aspect, the present technical solution provides an interference prompt device, including: a processing unit, configured to determine a human body region and a background region from a detected user image; determine the degree of interference of the background region on identifying the user action from the human body region; a prompt unit, configured to generate interference prompt information according to the degree of interference.

[0035] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to identify target joint points from the user image; determine the human body region as the target joint points or the region formed by connecting the target joint points.

[0036] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine an extended region of the human body region in the user image; determine the extended region as the background region.

[0037] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine an action range area in the user image according to the user's current action and subsequent actions; determine a first area including the action range area in the user image, and determine an extended area of the human body area from the first area.

[0038] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine a sub-extended area of each limb joint point included in the human body area in the user image; and determine the sub-extended areas of the respective limb joint points as the extended area of the human body area.

[0039] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine a color difference value between the background area and the human body area; and determine the interference degree of the background area on identifying the user action from the human body area according to the color difference value.

[0040] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine the complexity of the background area; and determine the interference degree of the background area on identifying the user action from the human body area according to the complexity.

[0041] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine the accuracy of each limb joint point included in the human body area according to the information of the background area; and determine the interference degree of the background area on identifying the user action from the human body area according to the accuracy of each limb joint point.

[0042] In combination with the second aspect, in some implementation manners of the second aspect, the processing unit is specifically configured to determine the background complexity of each limb joint point included in the human body area and the color difference value between each limb joint point and the background area; and determine the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background area.

[0043] In a third aspect, the present technical solution provides an electronic device, including: a display screen; a camera; one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the following steps: determine a human body area and a background area from a detected user image; determine the interference degree of the background area on identifying the user action from the human body area; and generate interference prompt information according to the interference degree.

[0044] Fourth aspect, the present technical solution provides an electronic device, which includes a storage medium and a central processing unit. The storage medium can be a non-volatile storage medium. A computer-executable program is stored in the storage medium. The central processing unit is connected to the non-volatile storage medium and executes the computer-executable program to implement the method in the first aspect or any possible implementation manner of the first aspect.

[0045] Fifth aspect, the present technical solution provides a chip, which includes a processor and a data interface. The processor reads instructions stored on a memory through the data interface and executes the method in the first aspect or any possible implementation manner of the first aspect.

[0046] Optionally, as an implementation manner, the chip may further include a memory. Instructions are stored in the memory. The processor is configured to execute the instructions stored on the memory. When the instructions are executed, the processor is configured to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0047] Sixth aspect, the present technical solution provides a computer-readable storage medium. The computer-readable medium stores program code for a device to execute. The program code includes instructions for executing the method in the first aspect or any possible implementation manner of the first aspect. Description of the Drawings

[0048] Figure 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

[0049] Figure 2 is a schematic flowchart of an interference prompt method provided by an embodiment of the present application;

[0050] Figure 3 is another schematic flowchart of an interference prompt method provided by an embodiment of the present application;

[0051] FIG. 4 is a schematic diagram of determining a human body area and a background area according to a user image provided by an embodiment of the present application;

[0052] Figure 5 is another schematic flowchart of an interference prompt method provided by an embodiment of the present application;

[0053] Figure 6 is yet another schematic flowchart of an interference prompt method provided by an embodiment of the present application;

[0054] Figure 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0055] The technical solution in the present application will be described below in conjunction with the accompanying drawings.

[0056] As introduced in the background art section, in the gesture recognition scenario, interference factors in the input image will affect the accuracy of the gesture recognition result. Among various interference factors, the image background, that is, the scene background where the user is located when capturing the user's action, is an important interference factor affecting the accuracy of the gesture recognition result. For example, the color, shape, texture, etc. of the image background will all affect the accurate recognition of the user's action. Therefore, in gesture recognition, a solution for recognizing background interference and sending an interference prompt to the user is required.

[0057] The embodiment of the present application provides an interference prompt method, which is applied to the human body gesture recognition scenario. When performing gesture recognition on the user, first determine the interference degree of the background factor on the recognition of the user's action, and send an interference prompt message to the user according to the determined interference degree. The interference prompt message can be used to prompt the user that the background of the current scene affects the accurate recognition of the action, and it is recommended to change the scene background or change clothes, etc.

[0058] The interference prompt method of the embodiment of the present application can be applied to electronic devices such as mobile phones, tablet computers, computers, smart screens, wearable devices, in-vehicle devices, smart home devices, augmented reality (AR) / virtual reality (VR) devices, etc. with a display screen. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device.

[0059] Exemplarily, Figure 1 shows a schematic structural diagram of the electronic device 100 provided by the embodiment of the present application. As Figure 1As shown, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0060] It can be understood that the structure schematically shown in the embodiments of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than those shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0061] The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0062] Among them, the controller may be the nerve center and command center of the electronic device 100. The controller may generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching instructions and executing instructions.

[0063] A memory can also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can be directly retrieved from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0064] The electronic device 100 realizes the display function through the GPU, the display screen 194, and the application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or change display information.

[0065] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0066] The electronic device 100 can realize the shooting function through the ISP, the camera 193, the video codec, the GPU, the display screen 194, and the application processor, etc.

[0067] The ISP is used to process the data fed back by the camera 193. For example, when taking a photo, the shutter is opened, and light passes through the lens and is transmitted to the camera sensor. The light signal is converted into an electrical signal, and the camera sensor transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can also perform algorithm optimization on the noise, brightness, and skin color of the image. The ISP can also optimize parameters such as the exposure and color temperature of the shooting scene. In some embodiments, the ISP can be provided in the camera 193.

[0068] The camera 193 is used to capture static images or videos. An object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transfers the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in standard formats such as RGB and YUV. In some embodiments, the electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0069] The NPU is a neural-network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission pattern between human brain neurons, it can quickly process the input information and can also continuously learn by itself. Through the NPU, applications such as intelligent recognition of the electronic device 100 can be realized, such as: image recognition, face recognition, speech recognition, text understanding, etc.

[0070] For example, in this application, the user image in the current pose recognition scenario can be captured by the camera 193. The ISP converts the electrical signal about the user image fed back by the camera 193 into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP can convert the digital image signal into an image signal in standard formats such as RGB and YUV.

[0071] The above-mentioned image signal about the user image generated based on the DSP processing can be sent to the NPU for human pose recognition, such as recognizing the user's joint points and user actions based on the user image. Further, the human pose recognized by the DSP can be displayed on the display screen 194. In addition, reference actions can also be displayed on the display screen 194. For example, in a fitness scenario, fitness guidance actions can be displayed on the display screen 194. When the user's action is recognized, the user's action is displayed on the display screen 194. Optionally, the user's action and the fitness guidance action can be displayed on the display screen 194 at the same time.

[0072] In addition, the NPU or the controller can execute the interference prompt method of the embodiments of this application based on the user image, that is, the NPU or the controller can determine the interference degree of the background factor on the recognition of the user's action from the user image, and then send an interference prompt to the user according to the determined interference degree. Optionally, the interference prompt can be displayed on the display screen 194, or the interference prompt information can be played through the audio module 170 and the speaker 170A, etc.

[0073] The internal memory 121 can be used to store computer-executable program codes, and the executable program codes include instructions. The internal memory 121 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.). The data storage area can store data created during the use of the electronic device 100 (such as image data, phone book, etc.). In addition, the internal memory 121 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121 and / or the instructions stored in the memory provided in the processor.

[0074] For ease of understanding, in the following embodiments of the present application, an electronic device having Figure 1 the structure shown will be taken as an example, and in combination with the accompanying drawings and application scenarios, the interference prompt method provided by the embodiments of the present application will be specifically described.

[0075] Figure 2 FIG. is a schematic flowchart of the interference prompt method provided by the embodiments of the present application. The present application will take a mobile phone or a display device as an electronic device and introduce in detail the interference prompt method provided by the present application. Among them, the display device can be, for example, a television, a smart screen, and other devices. A smart screen is a new type of large-screen device. On the basis of having a display function, it also has functions of interconnecting with mobile phones, tablets, vehicle-mounted devices, home devices, etc., and is the connection entrance of the home Internet of Things. Based on the smart screen, the interference prompt method of the embodiments of the present application can be realized. Similarly, the interference prompt method of the embodiments of the present application can also be realized on a mobile phone.

[0076] 101, collect user images.

[0077] In the human body pose recognition scenario, a user image is captured by a camera on the electronic device. For example, a user image is captured by a camera on a mobile phone. Another example is that a user image is captured by a camera on a display device. In the captured user image, in addition to including the user's body part, it also includes the background part of the user's location scene.

[0078] 102, determine the human body area and the background area from the user image.

[0079] After obtaining a user image based on a camera on an electronic device, a human body region and a background region are determined from the user image. Among them, the method for identifying the human body region and the background region from the user image can be: first, identify the human body region from the user image; after identifying the human body region, determine the background region according to the human body region in the user image.

[0080] Among them, identifying the human body region from the user image includes: using a human body pose recognition algorithm to determine the human body position and human body contour from the user image. Part or all of the human body contour can be used as the human body region in the embodiments of the present application. The human body pose recognition algorithm can be algorithms such as open-pose, poseNet, etc. When using a human body pose recognition algorithm to identify the human body contour from the user image, the limb joint nodes of the user can be identified first, and the human body contour can be determined according to the identified limb joint points.

[0081] When determining the human body region from the human body contour, the target joint points can be determined first, and then the human body region can be determined according to the target joint points. Specifically, the region formed by connecting the target joint points on the human body contour can be determined as the human body region. Optionally, in addition to determining the region formed by the target joint points as the human body region, the target joint points can also be determined as the human body region in the embodiments of the present application. Further, in the embodiments of the present application, when determining the target joint points, all the identified limb joint points can be used as the target joint points. In addition, some joint points can also be selected from all the identified limb joint points as the target joint points. In one example, the limb joint points corresponding to the human body trunk can be used as the target joint points. For example, the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point can be determined as the target joint points, and the rectangular region surrounded by the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point can be determined as the human body region. Or, directly determine the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point as the human body region in the embodiments of the present application. When determining the target joint points as described above, it can be set in advance, or determined according to the user's current action and / or subsequent action. For example, if the user is doing a squat exercise, the limb joint points related to the user's lower limbs can be used as the target joint points.

[0082] After identifying the human body region from the user image, the background region can be further determined in the user image based on the human body region. Among them, the region related to the human body region in the user image can be determined as the background region. In a possible design, the extended region of the human body region can be determined from the user image, and the extended region can be determined as the background region in the embodiments of the present application. For example, when the region enclosed by the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point is determined as the human body region, the human body region can be extended in any one or more directions of up, down, left, and right, and the extended region can be determined as the background region. In addition, the action range region can be determined in the user image according to the user's current action and subsequent actions; the first region including the action range region is determined in the user image, and the extended region of the human body region is determined from the first region. For example, when the user is doing a squatting motion and the current detected user image shows a squatting posture, it can be determined that the user's subsequent action is a posture of gradually getting up from the squatting posture. At this time, the action range region from the squatting posture to the standing posture of the user can be determined as the first region; the region other than the current body range of the user in the first region can be determined as the extended region, that is, the background region.

[0083] Optionally, the way to determine the extended region can also be: determining the sub-extended regions of each limb joint point included in the human body region in the user image; determining the sub-extended regions of each limb joint point as the extended region of the human body region. In this way, each target joint point can be extended separately, and each sub-extended region associated with the target joint point can be determined as the background region.

[0084] 103. Determine the interference degree of the background region on identifying the user's action from the human body region.

[0085] In the embodiments of the present application, the interference degree of the background region on identifying the user's action can be determined according to the color difference between the background region and the human body region, the complexity of the background region, and the joint point accuracy derived from the color difference and complexity. Among them, determining the interference degree of the background region on identifying the user's action according to the color difference between the background region and the human body region includes: determining the color difference value between the background region and the human body region; determining the interference degree of the background region on identifying the user's action from the human body region according to the color difference value. Among them, when the color difference value between the background region and the human body region is less than the first threshold, it can be considered that the color difference between the background region and the human body region is small, and the interference degree of the background region on identifying the user's action is high.

[0086] In possible scenarios, although there is a large color difference between the background area and the human body area, since the pattern of the background area is relatively complex, the background area will also affect the recognition of the user at this time. Therefore, the interference degree of the background area on the recognition of the user's action can be determined according to the complexity of the background area; when the complexity of the background area is greater than the second threshold, it can be considered that the complexity of the background area is large and the interference degree of the background area on the recognition of the user's action is high.

[0087] It can be understood that in addition to using the color difference value between the background area and the human body area and the complexity of the background area as separate independent bases to determine the interference degree of the background area on the recognition of the user's action, the interference degree of the background area on the recognition of the user's action from the human body area can also be determined according to the color difference value and the complexity at the same time. In a possible design, when the color difference value between the background area and the human body area is greater than the first threshold, it can be further determined whether the complexity of the background area is greater than the second threshold. If the complexity of the background area is greater than the second threshold, it is determined that the interference degree of the background area on the recognition of the user's action is high. In another possible design, the accuracy of each limb joint point included in the human body area can also be determined according to the background area information; the interference degree of the background area on the recognition of the user's action from the human body area can be determined according to the accuracy of each limb joint point.

[0088] Among them, determining the accuracy of each limb joint point included in the human body area according to the information of the background area includes: determining the background complexity of each limb joint point included in the human body area and the color difference value between each limb joint point and the background area; determining the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background area.

[0089] Among them, when calculating the accuracy of each limb joint point, each limb joint point can be used as the target joint point. At this time, the method for determining the background area can be: connecting the target joint points into a second area; determining a third area in the user image that contains the second area, and determining the part of the third area except the second area as the background area. When calculating the color difference between each target joint point and the background area, the background area can be divided into multiple non-overlapping sub-areas, and each sub-area contains at least one target joint point, and calculate the color difference between each target joint point and the sub-area where it is located. Calculating the background complexity of each target joint point includes: calculating the complexity of the sub-area where the target joint point is located. Optionally, another possible method for determining the background area of the target joint point can be: respectively determining the sub-expansion areas of each target joint point; determining the sub-expansion areas of the respective limb joint points as the background area of the human body area. Correspondingly, calculating the color difference between each target joint point and the background area includes: calculating the color difference between the target joint point and its corresponding sub-expansion area. Further, calculating the background complexity of each target joint point includes: calculating the complexity of the sub-expansion area where the target joint point is located.

[0090] In the embodiments of the present application, after calculating the accuracy of each limb joint point, the interference degree of the background area on the recognition of the user's action can be determined according to the accuracy of each limb joint point. For example, when the accuracy of one or more limb joint points is less than the third threshold, it is considered that the interference degree of the background area on the one or more joint points is relatively high, and a prompt can be sent to the user. In addition, the total accuracy of the joint points can also be calculated according to the accuracy of each limb joint point, and the interference degree of the background area can be determined according to the total accuracy of the joint points.

[0091] In the embodiments of the present application, the above interference degree is used to characterize the interference degree of the background area on the recognition of the user's action. In one example, the above interference degree can be a specific parameter. For example, when the complexity of the background area is in the range of a 1 -a 2 range, the interference degree takes the value of b 1 ; when the complexity of the background area is in the range of a 2 -a 3 range, the interference degree takes the value of b 2 etc.; Optionally, the above interference degree can also be characterized by other parameters. For example, when using the complexity of the background area to determine the interference of the background area on the recognition of the user's action, when the complexity of the background area exceeds the second threshold, it is considered that the interference degree of the background area has reached the level that needs to be prompted to the user. At this time, the interference degree can be characterized by the complexity of the background area, and no specific value needs to be assigned to the interference degree.

[0092] 104, generating interference prompt information according to the interference degree.

[0093] In the embodiments of the present application, when it is determined according to the calculated interference degree that the background area interferes with the recognition of the user's action, interference prompt information can be generated and provided to the user. For example, when the color difference between the background area and the human body area is small, affecting the recognition of the user's action, the user can be prompted that the current clothing color is close to the background area, affecting the action recognition, and it is recommended to change the clothing. Another example is that when the pattern of the background area is too complex, the user can be prompted to change the scene background. Through the method of the embodiments of the present application, the user can be prompted about the interference of the current background scene on the recognition of the user's action, improving the accuracy of the recognition of the user's action. The following will further elaborate on the solution of the present application in combination with specific embodiments.

[0094] Embodiment 1

[0095] In this embodiment, the interference degree of the background area on the recognition of the user's action is determined according to the color difference between the background area and the human body area, as Figure 3 shown. The processing steps of the method of this embodiment include:

[0096] 201. Identify the position and human body contour of the user from the user image. Among them, a human body pose recognition algorithm can be used to determine the user's position from the user image, and the recognized user position is shown as the rectangular frame in Figure 4(a). On the basis of recognizing the user's position, as shown in Figure 4(a), further identify the respective limb joint points of the user, and the recognized respective limb joint points are connected to form a human body contour.

[0097] 202. Determine the human body area for subsequent calculation from the human body contour. Among them, the recognized human body contour can be determined as the human body area for subsequent calculation. In addition, a partial area can also be selected from the human body contour as the human body area for subsequent calculation. When a partial area in the human body contour is used as the human body area for subsequent calculation, the target joint points can be determined first, and the area formed by the target joint points can be determined as the human body area. As shown in Figure 4(b), the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point can be determined as the target joint points. As shown in Figure 4(b), the rectangular area A surrounded by the left shoulder joint point, the right shoulder joint point, the left hip joint point, and the right hip joint point can be determined as the human body area.

[0098] 203. Determine the background area from the user image. As shown in Figure 4(c), after determining the human body area A, an enlarged area B can be determined on the basis of the human body area A, and the part of the enlarged area B excluding the human body area A is the background area. The size of the enlarged area can be set according to actual needs, such as magnifying the size of the human body area according to a certain size ratio, etc.

[0099] 204. Calculate the color difference value C between the human body region and the background region. In the embodiments of the present application, the human body region and the background region determined from the user image can be color images. Correspondingly, the pixel points of the human body region and the background region can be assigned values based on the three color channels of RGB, and the value range of each color channel is [0, 255]. The color difference value C between the human body region and the background region = ||C 1 - C 2 ||. Wherein, C 1 is the color value of the human body region, and the color value of the human body region can represent the color of the user's clothes or skin. Specifically, C 1 can take the average value or the median value of the color values of the pixel points in the human body region. C 2 is the color value of the background region. Similarly, C 2 can take the average value or the median value of the color values of the pixel points in the background region. When calculating the color difference value C based on C 1 and C 2 , the difference value C can take the average value, the modulus value or the maximum value of the three-channel color differences of C 1 and C 2 .

[0100] In another possible way, the above-mentioned human body region and background region can be grayscale images. For example, after obtaining the color user image, convert the user image into a grayscale image, and then identify the human body region and the background region from the grayscale image. Another example is that after obtaining the color user image and determining the human body region and the background region from the user image, convert the human body region and the background region into grayscale images respectively, and then calculate the color difference value C between the human body region and the background region using the grayscale images. When the human body region and the background region are grayscale images, the grayscale values of the pixel points in the human body region and the background region are determined based on their original RGB three-channel color values. For example, if the original color pixel point has a value of RGB(R1, G1, B1), then the converted grayscale value Gray of this pixel point can be determined based on the formula Gray = 0.2989 * R + 0.5870 * G + 0.1140 * B. Of course, the formula for converting the color pixel value into a grayscale value is only an example, and can be adjusted according to actual needs in specific implementations. The color difference value C between the human body region and the background region = ||C 1 - C 2 ||. Wherein, C 1 is the grayscale value of the human body region. Specifically, C 1 can take the average value or the median value of the grayscale values of the pixel points in the human body region. C 2 is the grayscale value of the background region. Similarly, C 2It can take the mean value of the gray values of the pixels in the background area or the median value of the gray values of the pixels in the background area. The color difference value C can take C 1 and C 2 the modulus value of the difference.

[0101] 205, determine whether the color difference value C is lower than the threshold value c. If it is lower than the threshold value c, execute step 206; otherwise, execute step 207.

[0102] 206, generate an interference prompt message and send an interference prompt to the user. When the color difference value C between the human body area and the background area is lower than the threshold value c, it can be considered that the colors of the background area and the human body area are relatively close, and the background area will affect the accurate recognition of the user's actions by the human body pose recognition algorithm. For example, in a scenario of exercising through a display device, fitness guidance actions can be played on the display device. The camera on the display device captures the user's image, and the display device recognizes the user's actions based on the user's image captured by the camera. Among them, it can be judged whether the actions made by the user are standard according to the actions recognized from the user's image. In this fitness scenario, if the user's clothes are white and the background of the user's exercise is also white, then because the background color and the clothes color are close, it will interfere with the recognition of the user's actions by the human body pose recognition algorithm. At this time, a prompt message can be generated, for example, prompting the user that the clothes color is close to the background color, and suggesting changing the clothes color or changing the venue, etc. Among them, the prompt message can be displayed through the display device or can be given a voice prompt through the audio module.

[0103] 207, perform normal user pose recognition. If the color difference between the human body area and the background area is greater than or equal to the threshold value c, it is considered that the current background does not affect the recognition of the user's actions by the human body pose recognition algorithm, and the pose recognition of the user can be carried out normally.

[0104] Embodiment 2

[0105] In this embodiment, the interference degree of the background area on the recognition of the user's actions is determined according to the complexity of the background area. As Figure 5 shown, the processing steps of the method of this embodiment include:

[0106] 301, recognize the position and human body contour of the user from the user's image.

[0107] 302, determine the human body area and the background area from the human body contour. The method for determining the human body area and the background area in this embodiment can refer to Embodiment 1 and will not be elaborated here.

[0108] 303, calculate the complexity of the background area.

[0109] Specifically, the complexity of the background area can be calculated according to the following formula.

[0110]

[0111] In the formula for the above-mentioned computational complexity C, n i is the number of pixels with gray level i in the background region, and N is the total number of pixels in the background region.

[0112] In addition, the complexity of the background region can also be measured by information entropy. The calculation formula for the information entropy H is as follows:

[0113]

[0114] In the formula for calculating the above-mentioned information entropy H, n i is the number of pixels with gray level i in the background region, and N is the total number of pixels in the background region.

[0115] 304. Determine whether the complexity of the background region is greater than the threshold h. If it is greater than the threshold h, then execute step 305; otherwise, execute step 306.

[0116] 305. Generate interference prompt information and send an interference prompt to the user. In this embodiment, if the complexity of the background region is higher than the threshold h, it is considered that the background in the current scenario is relatively complex and affects the recognition of the user's actions. For example, when the complexity of the background region is represented by information entropy, if the information entropy is greater than 4, it is considered that the background region is relatively complex and will affect the recognition of the user's actions by the human body pose recognition algorithm. At this time, interference prompt information can be generated, such as prompting the user to change the venue or change the background layout, etc.

[0117] 306. Perform normal user pose recognition.

[0118] In this embodiment, based on the background complexity to judge the interference of the background region on the recognition of the user's actions, it can be in a scenario where the background color difference is not sufficient to affect the current action recognition, but the shape and texture of the background still have an impact.

[0119] Embodiment III

[0120] In this embodiment, by calculating the accuracy of the user's limb joint points, the interference degree of the background region on the recognition of the user's actions is judged. In this embodiment, first, a joint point accuracy calculation model is constructed, and the accuracy of the limb joint points in the currently captured user image is calculated through the joint point accuracy calculation model. As Figure 6 shown, the specific processing steps include:

[0121] 401. Determine the image training set and execute the human body pose recognition algorithm based on the image training set.

[0122] The above image training set contains a large number of images with the positions of limb joint points already annotated. By performing a human pose recognition algorithm on each image in the image training set, the recognition ability of the joint point accuracy calculation model for limb joint points can be trained.

[0123] 402. Based on the image training set, calculate the color difference value of the limb joint points.

[0124] In this embodiment, for each image in the image training set, after identifying the limb joint points in the image, calculate the color difference value of each limb joint point. Among them, when calculating the color difference value of each limb joint point, it can be calculated according to the method of the first embodiment above. Specifically, the human body area where each limb joint point is located can be determined first. For example, the human body is divided into a torso area, a left upper limb area, a right upper limb area, a left lower limb area, a right lower limb area, etc. When the joint point to be calculated is the left elbow joint point, determine the human body area where it is located as the left upper limb area. Determine the background area according to the human body area, and calculate the color difference value between the human body area and the background area. The method for determining the background area and calculating the color difference value in this embodiment can refer to the first embodiment. In another possible design, the limb joint point is used as the human body area for calculation. It can be understood that the limb joint point corresponds to a sub-area on the human body contour, and only one limb joint point is included in a sub-area, and the size of the sub-area can be set according to actual needs. When determining the background area of each joint point, the extended area of the limb joint point can be determined. Then, calculate the color difference value between the joint point and its corresponding extended area.

[0125] 403. Based on the image training set, calculate the complexity of the limb joint points.

[0126] In this embodiment, for each image in the image training set, after identifying the limb joint points in the image, calculate the background complexity of each limb joint point. Among them, the method for determining the background area of each limb joint point can refer to the description in step 402. The calculation method of the background complexity can refer to the second embodiment and will not be elaborated here.

[0127] 404. Based on the color difference value and complexity of the limb joint points calculated above, calculate the accuracy of each limb joint point.

[0128] In this embodiment, after calculating the color difference value and background complexity of each limb joint point in each image, calculate the accuracy P of each limb joint point in each image i . In one example, P i = a i *C i + b i *H i + c i ; where i is the limb joint point number, C iis the color difference value of the i-th limb joint point, H i is the background complexity of the i-th limb joint point.

[0129] Optionally, the accuracy P of each image can be determined according to the accuracies of the limb joint points in the image. In a possible design, P takes the mean value of the accuracies P i of the limb joint points or the minimum value among the accuracies P i of the limb joint points.

[0130] In another possible design, after calculating the accuracies of the limb joint points in each image, the target joint points can be determined according to the user's current action or subsequent action; the overall accuracy is determined according to the accuracies of the target joint points. For example, in the squatting action, the action to be recognized is squatting, and the target joint points can be determined as the left knee joint point, the right knee joint point, and the hip joint point; the overall accuracy of the image is determined according to the accuracies of the left knee joint point, the right knee joint point, and the hip joint point.

[0131] When recognizing the accuracy of the limb joint points in the user image based on the joint point accuracy calculation model established above in 401-404, step 405 is executed.

[0132] 405. Input the user image into the joint point accuracy calculation model, and calculate the image accuracy based on the joint point accuracy calculation model.

[0133] Among them, calculating the image accuracy based on the joint point calculation model includes: recognizing each limb joint point in the user image and calculating the accuracy of each limb joint point. After determining the accuracy of each limb joint point, the image accuracy is determined according to the accuracy of each limb joint point.

[0134] 406. When the image accuracy is less than the threshold p, generate an interference prompt message.

[0135] In this embodiment, the minimum accuracy among the limb joint points can be used as the image accuracy, and an interference prompt is generated when the image accuracy is less than the threshold; in addition, according to the user's current action or subsequent action, a prompt can be given according to the accuracy of the target joint point. For example, when the user is doing a squatting action, if the overall accuracy determined according to the accuracies of the left knee joint point, the right knee joint point, and the hip joint point is less than the threshold, it is considered that in the current background, the human pose recognition algorithm may not accurately recognize the legs. At this time, an interference prompt can be generated, suggesting changing the background or changing the pants, etc.

[0136] Embodiment Five

[0137] In this embodiment, an action range area is determined in the user image according to the user's current action and / or subsequent action; in the user image, a background area is determined according to the action range area; after determining the background area, it is possible to determine whether the current background interferes with the recognition of the user's action based on any one of the methods in the above-mentioned Embodiments 1 to 4, and generate interference prompt information when it is determined that interference is caused.

[0138] In this embodiment, determining the background area according to the action range area in the user image includes: determining the area obtained by removing the current user contour from the action range area as the background area; or determining a first area larger than the action range area, and determining the area obtained by removing the current user contour from the first area as the background area.

[0139] The above-mentioned manner of determining the user's current action and / or subsequent action may include: determining the user's current action and / or subsequent action through application information. For example, in a fitness scenario, fitness guidance actions are played on an electronic device, and the current and subsequent fitness guidance actions to be played are preset in the application. Therefore, the user's current and / or subsequent actions can be determined according to the information in the application. Another example is that the user's current and / or subsequent actions can be determined according to the acquired user image.

[0140] In this embodiment, the activity range of the user is judged according to the user's current action and subsequent action, and the influence of the background related to the user's activity range on the recognition of the user's action is judged. On the one hand, the influence of the entire activity range on the recognition of the user can be estimated. For example, when the user does a squat, the influence of the background when standing on the recognition of the lower limb action can be predicted. On the other hand, it can also avoid the interference of the area that the user will not reach on the pose recognition algorithm.

[0141] It can be understood that in order for the electronic device to implement the above functions, it includes the corresponding hardware and / or software modules for executing each function. Combining the steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware 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 in combination with the embodiments.

[0142] This embodiment can divide the functional modules of the electronic device according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, and is only a logical function division. There may be other division methods in actual implementation.

[0143] In the case where each functional module is divided corresponding to each function, Figure 7 FIG. Figure 7 shows a possible schematic composition diagram of the electronic device involved in the above embodiment. As Figure 7 shown, a functional module for performing interference prompt in human body posture recognition can be integrated in the electronic device. The functional module specifically includes: a processing unit 701 and a prompt unit 702; wherein:

[0144] The processing unit 701 is configured to determine a human body region and a background region from the detected user image; determine the interference degree of the background region on identifying the user action from the human body region; the prompt unit 702 is configured to generate interference prompt information according to the interference degree.

[0145] In the embodiment of the present application, the processing unit 701 is specifically configured to identify target joint points from the user image; determine the human body region as the target joint points or the region formed by connecting the target joint points.

[0146] In the embodiment of the present application, the processing unit 701 is specifically configured to determine an extended region of the human body region in the user image; determine the extended region as the background region.

[0147] In the embodiment of the present application, the processing unit 701 is specifically configured to determine an action range region in the user image according to the current action and subsequent actions of the user; determine a first region including the action range region in the user image, and determine the extended region of the human body region from the first region.

[0148] In the embodiment of the present application, the processing unit 701 is specifically configured to determine sub-extended regions of each limb joint point included in the human body region in the user image; determine the sub-extended regions of each limb joint point as the extended region of the human body region.

[0149] In the embodiment of the present application, the processing unit 701 is specifically configured to determine the color difference value between the background region and the human body region; determine the interference degree of the background region on identifying the user action from the human body region according to the color difference value.

[0150] In the embodiment of the present application, the processing unit 701 is specifically configured to determine the complexity of the background region; determine the interference degree of the background region on identifying the user action from the human body region according to the complexity.

[0151] In an embodiment of the present application, the processing unit 701 is specifically configured to determine the accuracy of each limb joint point included in the human body region according to the information of the background region; and determine the interference degree of the background region on identifying the user action from the human body region according to the accuracy of each limb joint point.

[0152] In an embodiment of the present application, the processing unit 701 is specifically configured to determine the background complexity of each limb joint point included in the human body region and the color difference value between each limb joint point and the background region; and determine the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background region.

[0153] It should be understood that the electronic device herein is embodied in the form of functional units. The term "unit" herein can be implemented in software and / or hardware forms, and no specific limitation is made thereto. For example, the "unit" can be a software program, a hardware circuit, or a combination of the two to implement the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor, or a group of processors, etc.) for executing one or more software or firmware programs, a memory, a combined logic circuit, and / or other suitable components to support the described functions.

[0154] An embodiment of the present application further provides an electronic device, including: a display screen; a camera; one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the following steps: determine a human body region and a background region from the detected user image; determine the interference degree of the background region on identifying the user action from the human body region; and generate interference prompt information according to the interference degree.

[0155] The present application further provides an electronic device, the device includes a storage medium and a central processing unit, the storage medium may be a non-volatile storage medium, a computer executable program is stored in the storage medium, the central processing unit is connected to the non-volatile storage medium, and executes the computer executable program to implement the above Figures 2 to 6 interference prompt method shown.

[0156] The present application further provides a chip, the chip includes a processor and a data interface, the processor reads the instructions stored on the memory through the data interface, and executes the above Figures 2 to 6The interference prompting method shown in []. Optionally, as an implementation, the chip may further include a memory, and instructions are stored in the memory. The processor is configured to execute the instructions stored on the memory. When the instructions are executed, the processor is configured to execute the interference prompting method in the above embodiments.

[0157] In a sixth aspect, the present technical solution provides a computer-readable storage medium. The computer-readable medium stores program code for a device to execute. The program code includes instructions for executing the method in the possible implementation manners of the above display adjustment method.

[0158] The memory may be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0159] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, A and / or B may indicate the situation of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B may be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c may be single or multiple.

[0160] Those of ordinary skill in the art will realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0161] 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 foregoing method embodiments and will not be elaborated here.

[0162] In several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes. The above is only the specific implementation manner of this application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application and should be covered by the protection scope of this application. The protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A method for interference prompt, characterized in that, comprising: Determining a human body area and a background area from the detected user image; Determining the interference degree of the background area on identifying the user action from the human body area; Generating interference prompt information according to the interference degree; Determining the interference degree of the background area on identifying the user action from the human body area includes: Determining the accuracy of each limb joint point included in the human body area according to the information of the background area; Determining the interference degree of the background area on identifying the user action from the human body area according to the accuracy of each limb joint point; Determining the accuracy of each limb joint point included in the human body area according to the information of the background area includes: Determining the background complexity of each limb joint point included in the human body area and the color difference value between each limb joint point and the background area; Determining the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background area.

2. The method according to claim 1, characterized in that, Determining a human body area from the detected user image includes: Identifying target joint points from the user image; Determining the human body area as the target joint points or the area formed by connecting the target joint points.

3. The method according to claim 1, characterized in that, Determining the background area from the user image includes: Determining an extended area of the human body area in the user image; Determining the extended area as the background area.

4. The method according to claim 3, characterized in that, Determining the extended area of the human body area in the user image includes: Determining an action range area in the user image according to the user's current action and subsequent actions; Determining an extended area of the human body area from the first area that includes the action range area in the user image.

5. The method according to claim 3, characterized in that, Determining the extended area of the human body area in the user image includes: Determining a sub-extended area of each limb joint point included in the human body area in the user image; Determining the sub-extended areas of each limb joint point as the extended area of the human body area.

6. An electronic device, characterized in that, comprising: A display screen; A camera; One or more processors; A memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, when the instructions are executed by the device, the device is caused to perform the following steps: Determining a human body area and a background area from the detected user image; Determining the interference degree of the background area on identifying the user action from the human body area; Generating interference prompt information according to the interference degree; Determining the interference degree of the background area on identifying the user action from the human body area includes: Determining the accuracy of each limb joint point included in the human body area according to the information of the background area; Determine the interference degree of the background area on identifying the user's action from the human body area according to the accuracy of each limb joint point; According to the information of the background area, determine the accuracy of each limb joint point included in the human body area, including: Determine the background complexity of each limb joint point included in the human body area and the color difference value between each limb joint point and the background area; Determine the accuracy of each limb joint point according to the background complexity of each limb joint point and the color difference value between each limb joint point and the background area.

7. The device according to claim 6, wherein, when the instruction is executed by the device, the device is caused to execute the following steps: Identify the target joint points from the user image; Determine the target joint points or the area formed by connecting the target joint points as the human body area.

8. The device according to claim 6, wherein, when the instruction is executed by the device, the device is caused to execute the following steps: Determine the extended area of the human body area in the user image; Determine the extended area as the background area.

9. The device according to claim 8, wherein, when the instruction is executed by the device, the device is caused to execute the following steps: Determine the action range area in the user image according to the user's current action and subsequent actions; Determine the first area including the action range area in the user image, and determine the extended area of the human body area from the first area.

10. The device according to claim 8, wherein, when the instruction is executed by the device, the device is caused to execute the following steps: Determine the sub-extended areas of each limb joint point included in the human body area in the user image; Determine the sub-extended areas of each limb joint point as the extended area of the human body area.

11. A computer storage medium, wherein, it includes computer instructions, when the computer instructions run on an electronic device, the electronic device is caused to execute the interference prompt method according to any one of claims 1 to 5.

Images