A three-dimensional identification detection method and system with adaptive precision and distance, medium and computer device

Abstract

The disclosure provides a three-dimensional recognition detection method and system with adaptive precision and distance, a medium and a computer device, comprising: acquiring a first target image, a first speckle pattern and a target distance of a recognition target; acquiring a first precision of the first target image and a first speckle density of the first speckle pattern; presetting an image standard precision; detecting whether the first precision is higher than the standard precision; when the first precision is higher than the standard precision, recognizing the first target image and the first speckle pattern; when the first precision is lower than the standard precision, obtaining a second target image and a second speckle pattern of the recognition target by adjusting the corresponding laser partition through an adjustable algorithm; acquiring a second precision of the second target image and a second speckle density of the second speckle pattern; and recognizing the second target image and the second speckle pattern. The disclosure can realize multi-distance, multi-precision, and especially high-precision three-dimensional detection and recognition.

Description

Technical Field

[0001] This disclosure relates to the field of computer vision technology, and in particular to a three-dimensional recognition and detection method, system, medium, and computer device with adaptive accuracy and distance. Background Technology

[0002] With the booming development of machine vision, autonomous driving, and robotics, it is becoming increasingly common to use depth cameras to collect depth information of the environment and then perform object recognition, environmental modeling, and other tasks. A depth camera is a camera that can measure the distance (depth) from an object to the camera and has many application scenarios and recognition and detection fields.

[0003] Currently, the three main depth camera solutions on the market are structured light, binocular stereo vision, and time-of-flight optical methods. The basic principle of structured light is to project light with specific structural features onto the object being photographed using an infrared laser, which is then captured by a specialized infrared camera. A drawback of structured light is that its accuracy decreases as the detection distance increases.

[0004] Binocular stereo vision is an important form of machine vision. It is based on the principle of parallax and uses imaging equipment to acquire two images of a test object from different positions. By calculating the positional deviation between corresponding points in the images, it obtains the object's three-dimensional geometric information. The computation is very resource-intensive and highly sensitive to ambient lighting conditions. Lighting can cause large image deviations, leading to matching failures or low accuracy.

[0005] Time-of-flight (TOF) optical methods measure distance by the time it takes for light to travel. Specifically, a laser pulse is emitted to a target, and a sensor receives the reflected light. The exact distance to the target is determined by measuring the round-trip time of the light pulse. However, TOF is resource-intensive and has low edge accuracy. Summary of the Invention

[0006] This disclosure addresses the shortcomings of existing technologies by providing a method, system, medium, and computer device for adaptive three-dimensional recognition and detection with varying accuracy and distance. The technical solution of this disclosure solves the technical problem that existing technologies cannot provide multi-precision and multi-distance recognition and detection by using an algorithm to control the combination of the focal length of the VCSEL and the liquid crystal lens to adaptively achieve recognition and detection with different accuracy and distance.

[0007] A three-dimensional recognition and detection method with adaptive accuracy and distance includes the following steps:

[0008] Acquire the first target image, the first speckle pattern, and the target distance for the identified target;

[0009] Obtain the first precision of the first target image and the first speckle density of the first speckle pattern;

[0010] Preset image standard precision;

[0011] Check whether the initial accuracy is higher than the standard accuracy;

[0012] When the first precision is higher than the standard precision, the first target image and the first speckle pattern are identified;

[0013] When the first precision is lower than the standard precision, the corresponding laser partition is adaptively illuminated through an adjustable algorithm to obtain the second target image and the second speckle pattern of the target to be identified.

[0014] Obtain the second precision of the second target image and the second speckle density of the second speckle pattern;

[0015] The second target image and the second speckle pattern are identified.

[0016] Furthermore, the target pattern includes image precision, and the speckle pattern includes speckle density;

[0017] Image precision corresponds one-to-one with speckle density.

[0018] Furthermore, target distance is divided into short distance and long distance, and speckle density is divided into medium density and dense density;

[0019] The speckle density corresponding to close distance is dense density;

[0020] The speckle density at long distances is medium.

[0021] Furthermore,

[0022] The target distance corresponds one-to-one with the speckle density;

[0023] The distance to the target is proportional to the density of the speckle density.

[0024] Furthermore, the standard accuracy is directly proportional to the laser partitioning.

[0025] Furthermore, the adjustable algorithm includes adaptively reducing the number of laser zones to be illuminated corresponding to the standard accuracy when the standard accuracy is lower than the first accuracy.

[0026] Furthermore, the adjustable algorithm also includes pre-recognition detection, which adaptively adjusts the precision of the target image and the speckle density of the speckle image before recognizing the target image and the speckle image to ensure that the precision and speckle density are higher than or equal to the standard precision.

[0027] Furthermore, the adjustable algorithm can adjust the speckle density from medium density to dense density to improve the accuracy of the identification and detection method.

[0028] Furthermore, including:

[0029] The variable pattern projection module is used to transform the speckle pattern for projection;

[0030] The variable image projection module includes:

[0031] The diffraction optics module is used to precisely control the laser to form a speckle pattern of illumination distribution;

[0032] The zoom module is used to adjust image accuracy by adjusting the lens focal length;

[0033] Laser module, used to project speckle patterns;

[0034] The identification and detection system also includes:

[0035] The detection module is used to detect and identify the distance to the target and the accuracy of the target image;

[0036] The feedback control module is used to control the hardware and provide feedback on the hardware status to the control system.

[0037] A 3D recognition module is used for identity verification;

[0038] The control module is used to control the normal operation of each module in the system.

[0039] Furthermore, the variable image projection module also includes a ceramic substrate and an FPC.

[0040] Furthermore, the laser module includes at least one VCSEL laser.

[0041] Furthermore, the VCSEL laser includes at least one laser zone.

[0042] Furthermore, the laser zones can be controlled independently.

[0043] Furthermore, the zoom module includes at least one liquid crystal lens.

[0044] Furthermore, the zoom module and the laser module can work together to adaptively adjust the target image accuracy and speckle pattern density for target identification.

[0045] A computer-readable storage medium having computer instructions stored thereon, characterized in that the instructions are executed by a processor of the steps of the system and the method described above.

[0046] A computer device, comprising:

[0047] A communicator used for communicating with the outside world;

[0048] Memory, used to store computer programs;

[0049] A processor is configured to run the computer program to use the aforementioned adaptive accuracy and distance 3D recognition and detection method or to execute the aforementioned adaptive accuracy and distance 3D recognition and detection system, or to run the computer program.

[0050] The processor implements the above method by running executable instructions.

[0051] Compared with the prior art, this disclosure has the following beneficial effects:

[0052] This disclosure provides a method, system, medium, and computer device for adaptive accuracy and distance-based 3D recognition and detection. By using a variable-focus projector with different VCSEL illumination areas, various diffraction patterns can be projected, and the accuracy can be adaptively adjusted based on feedback from the system hardware to meet testing objectives. The VCSEL's laser illumination area can be a single area or several areas, and through algorithmic control, when high accuracy requirements are not necessary, the illuminated area of ​​the VCSEL can be adaptively reduced to decrease the power consumption of the 3D recognition and detection system. This disclosure enables 3D detection and recognition at multiple distances and with varying levels of accuracy, particularly high-precision 3D. The hardware structure is simple, the manufacturing process is low, and it is suitable for use in various scenarios. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of 3D structured light in one embodiment of the present disclosure;

[0054] Figure 2 This is a schematic diagram of the variable focus projection element structure in one embodiment of the present disclosure;

[0055] Figure 3 This is a schematic diagram of VCSEL partitioning in one embodiment of the present disclosure;

[0056] Figure 4 This describes the positional relationship between the user and the 3D system in one embodiment of this disclosure.

[0057] Figure 5 This is a speckle pattern in one embodiment of the present disclosure;

[0058] Figure 6 This is a flowchart illustrating adaptive precision in one embodiment of the present disclosure;

[0059] Figure 7 This is a schematic diagram of the structure of a computer device in one embodiment of the present disclosure.

[0060] Figure label:

[0061] 1-Main control chip; 2-Variable projector; 3-IR camera; 4-RGB camera; 5-Diffractive optical element; 6-Holder; 7-Liquid crystal zoom lens; 8-VCSEL and its components; 9-Ceramic substrate and FPC; 10-First laser zone; 11-Second laser zone; 12-Third laser zone; 13-Fourth laser zone; 14-3D recognition system; 15-First position of the target; 16-Second position of the target; 17-Medium density speckle pattern; 18-Dense density speckle pattern. Detailed Implementation

[0062] The present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Through these descriptions, the features and advantages of the present disclosure will become clearer and more apparent.

[0063] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments. Although various aspects of embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated otherwise.

[0064] Furthermore, the technical features involved in the different embodiments of this disclosure described below can be combined with each other as long as they do not conflict with each other.

[0065] By combining liquid crystal lenses with depth camera technology, multi-distance projection with variable zoom can be achieved. Liquid crystal lenses have electronically controlled zoom capabilities. Under the influence of an electric field, liquid crystal molecules are redirected, generating different refractive indices. This causes polarized light passing through the lens to refract, achieving a zoom effect. The zoom range can be adjusted and controlled by the voltage and the properties of the liquid crystal material itself.

[0066] 3D structured light and active binocular stereo vision are both technologies used in depth cameras. In existing solutions, the projector can only project one pattern. To achieve different arrangements / densities of projected patterns, multiple projectors are needed, and adaptive adjustments are not possible. Furthermore, the depth effect of 3D systems is limited, operating only over a short range.

[0067] Prior to addressing the above issues, this disclosure introduces 3D structured light, such as... Figure 1 As shown. The hardware system consists of a projector and one or more receivers. Figure 1This invention relates to a 3D structured light recognition scheme using two receivers. The left side comprises a main control chip 1, and the right side comprises a variable projector 2, an IR camera 3, and an RGB camera 4. The variable projector 2 can project patterns with different arrangements and densities. The main control chip 1 controls the variable projector 2 to perform variable projection on the object to be recognized, and also controls the IR camera 3 and the RGB camera 4 to capture images. This disclosure relates to a 3D recognition and detection method with adaptive accuracy and distance, comprising the following steps: acquiring a first target image, a first speckle pattern, and the target distance.

[0068] Obtain the first precision of the first target image and the first speckle density of the first speckle pattern;

[0069] Preset image standard precision;

[0070] Check whether the initial accuracy is higher than the standard accuracy;

[0071] When the first precision is higher than the standard precision, the first target image and the first speckle pattern are identified;

[0072] When the initial precision is lower than the standard precision, an adjustable algorithm adaptively illuminates the corresponding laser partitions to obtain a second target image and a second speckle pattern for the target to be identified. The adjustable algorithm includes adaptively reducing the number of laser partitions to be illuminated corresponding to the standard precision when the standard precision is lower than the initial precision. The adjustable algorithm also includes pre-identification detection; before identifying the target image and speckle image, it adaptively adjusts the precision of the target image and the speckle density of the speckle image to ensure that the precision and speckle density are higher than or equal to the standard precision. The adjustable algorithm can adjust the speckle density from medium density to dense density to improve the accuracy of the identification and detection method.

[0073] Obtain the second precision of the second target image and the second speckle density of the second speckle pattern;

[0074] The second target image and the second speckle pattern are identified.

[0075] The target pattern includes image precision, and the speckle pattern includes speckle density; image precision and speckle density are in one-to-one correspondence. Target distance is divided into short and long distance, and speckle density is divided into medium and dense density; short distance corresponds to dense speckle density, and long distance corresponds to medium density speckle density. Target distance and speckle density are in one-to-one correspondence, and the length of the target distance is directly proportional to the speckle density. Standard precision is directly proportional to laser zoning.

[0076] An adaptive precision and distance 3D recognition and detection system includes a variable pattern projection module for projecting a speckle pattern. The variable pattern projection module further includes a diffraction optics module, a zoom module, and a laser module, as well as a ceramic substrate and an FPC. The diffraction optics module is used to finely control the laser to form a speckle pattern of illumination distribution. The zoom module is used to adjust the image precision by adjusting the lens focal length and includes at least one liquid crystal lens. The laser module is used to project the speckle pattern and includes at least one VCSEL laser (in this embodiment, one VCSEL laser). The laser includes at least one partition (in this embodiment, four laser partitions), and these laser partitions can be independently controlled. The recognition and detection system also includes a detection module for controlling the hardware and feeding back the hardware status to the control system; a 3D recognition module for identity recognition; and a control module for controlling the normal operation of each module. The zoom module and the laser module can work together to adaptively adjust the target image precision and speckle pattern density of the target to be recognized.

[0077] Variable pattern projectors, such as Figure 2 As shown, the collimating lens consists of a liquid crystal zoom lens and / or lens group, including diffractive optical elements, a holder, a liquid crystal zoom lens or liquid crystal zoom lens group, a laser (VCSEL) and its components, a ceramic substrate, and a flexible printed circuit board (FPC). Figure 3 The diagram shown is a schematic of a single-piece lens. In this embodiment, the laser (VCSEL) is divided into four sections: the first laser section 10, the second laser section 11, the third laser section 12, and the fourth laser section 13. Each section supports individual control, and the illuminated laser section is controlled individually by recognizing the distance of the target from the recognition system. The first laser section 10 can be illuminated individually while controlling the zoom lens, or the second laser section 11 and the third laser section 12 can be illuminated simultaneously while controlling the zoom lens.

[0078] In one embodiment, since the image accuracy requirement for 3D recognition and detection is not very high, the image accuracy requirement can be met by using a medium-density speckle pattern 17, and a laser vcsel with only one laser zone can be used to realize 3D image recognition and detection.

[0079] By matching the VCSEL region with the focal length of the collimating lens, various diffraction patterns can be projected. Diffractive optical elements (DOEs) are a series of movable lenses in a lithography machine, primarily used to generate the light source required for lithography. A key characteristic of DOEs is their ability to precisely control the light intensity distribution while maintaining high diffraction efficiency. Therefore, this disclosure allows for precise control of image accuracy through the speckle density of the speckle pattern projected by the laser, and adaptive accuracy adjustment based on system feedback to meet different testing objectives. When higher accuracy is required, denser speckle patterns can be used.

[0080] like Figure 4 and 5 The diagram illustrates the positional relationship between the user and the 3D system. Position 1 is 50 cm from the 3D recognition system, and position 2 is 150 cm away. When the object is at position 1, due to the close distance, a medium-density speckle pattern is sufficient, resulting in a sparse speckle pattern 17. This medium-density speckle pattern 17 corresponds to the first laser zone 10 of the VCSEL and the focal length 1 of the liquid crystal lens. When the object is at a more distant position 2, the target distance increases. Projecting the medium-density speckle pattern 17 is insufficient for the algorithm's requirements. Therefore, the algorithm illuminates the second laser zone 11 of the VCSEL and adaptively changes the focal length of the liquid crystal lens. Through their combined action, the density of the projected pattern becomes denser, resulting in a dense speckle pattern 18. The accuracy of scene detection is directly proportional to the density of the pattern; the higher the accuracy requirement, the denser the speckle pattern.

[0081] Based on the above principles, various combinations of VCSEL regions and liquid crystal lens focal lengths can be used to achieve detection at different accuracies and distances. For improved accuracy, dense speckle patterns 18 can be used, suitable for high-precision detection scenarios. In detection scenarios where high precision is not required, the number of illuminated VCSEL zones can be reduced to decrease power consumption. Through the detection algorithm and hardware feedback control system, an adaptive variable-precision 3D detection hardware system can be realized. The final output of the system is a color camera image (RGB) and a depth camera image (DEPTH).

[0082] like Figure 6The diagram shown is an adaptive accuracy flowchart in one disclosed embodiment, primarily illustrating the adaptive accuracy flowchart of the VCSEL laser partition region and collimating lens combination. When the VCSEL laser partition region and collimating lens combination meet the accuracy requirements, the image is uploaded and the next algorithmic recognition calculation is performed. When the VCSEL laser partition region and collimating lens combination do not meet the accuracy requirements, the algorithm predicts the distance and the required speckle density at that distance, and feeds these parameters back to the hardware system. The VCSEL illuminated laser area and the focal length of the liquid crystal lens are adjusted to change the speckle pattern. The focal length and speckle pattern are adaptively adjusted according to the above method until the accuracy requirements are met. The image is then uploaded and the next algorithmic recognition calculation is performed.

[0083] In one embodiment, multiple projectors can be used to splice the projections, which can also achieve various patterns. However, the manufacturing process in this way is complex and the stability is relatively poor.

[0084] like Figure 7 As shown, the computer device 400 in this embodiment includes: a communicator 401 for communicating with external devices. Exemplarily, the communicator 401 includes wired or wireless communication circuitry; the wired communication circuitry includes a wired network card, etc.; the wireless communication circuitry includes, for example, WiFi, 2G / 3G / 4G / 5G communication modules, etc. A memory 402 is used to store at least one computer program. Exemplarily, the memory 402 may include high-speed random access memory and / or non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices.

[0085] In one embodiment, the memory may further include memory located in a different device but connected to one or more processors, such as network-attached memory accessed via RF circuitry or external ports and a communication network, wherein the communication network may be the Internet, one or more intranets, local area networks, wide area networks, storage area networks, etc., or suitable combinations thereof. The memory controller controls access to the memory by other components of the device, such as the CPU and peripheral interfaces. Processor 403 is used to run at least one computer program in the memory 402.

[0086] In implementing these steps, the processor 403 can control the communicator 401 to perform communication actions with the outside world as needed. The various functions implemented in the foregoing embodiments relate to computer software products; these computer software products are stored in a storage medium and, when run, cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application, for example... Figure 1 The program code corresponding to the steps performed in the embodiments can be stored in computer storage media.

[0087] In the embodiments provided in this application, the computer storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer storage medium and data storage medium do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0088] In one or more exemplary aspects, the functionality described by the computer program involved in the method flow of this application can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored or transmitted as one or more instructions or code onto a computer-readable medium. The steps of the methods or algorithms disclosed in this application can be embodied in processor-executable software modules, wherein the processor-executable software modules can reside on tangible, non-transitory computer storage media. Tangible, non-transitory computer storage media can be any available medium accessible to a computer.

[0089] The flowcharts and block diagrams in the foregoing figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the figures. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or by a combination of dedicated hardware and computer instructions.

[0090] In the description of this application, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "left", "right", etc., indicate the orientation or positional relationship based on the orientation or positional relationship in the working state of this application. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0091] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0092] The present application has been described above with reference to preferred embodiments; however, these embodiments are merely exemplary and illustrative. Various substitutions and modifications can be made to the present application based on these embodiments, all of which fall within the protection scope of the present application.

Claims

1. A method for adaptive precision and distance three-dimensional recognition detection, characterized in that, The method comprises the following steps: acquiring a first target image of a recognition target, a first speckle pattern and a target distance; acquiring a first precision of the first target image and a first speckle density of the first speckle pattern; presetting an image standard precision; detecting whether the first precision is higher than the standard precision; when the first precision is higher than the standard precision, recognizing the first target image and the first speckle pattern; when the first precision is lower than the standard precision, adaptively lighting different laser partitions of the same laser through an adjustable algorithm to acquire a second target image and a second speckle pattern of the recognition target; acquiring a second precision of the second target image and a second speckle density of the second speckle pattern; and recognizing the second target image and the second speckle pattern. The target image comprises image precision, and the speckle pattern comprises speckle density. The image precision and the speckle density correspond to each other.

2. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, characterized in that, The target distance is divided into a near distance and a far distance, and the speckle density is divided into a medium density and a dense density. The near distance corresponds to the dense density.

3. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, characterized in that, The far distance corresponds to the medium density.

4. The adaptive precision and distance three-dimensional recognition detection method according to claim 3, wherein The target distance and the speckle density correspond to each other. The length of the target distance is proportional to the density of the speckle density. The standard precision is proportional to the laser partition. When the standard precision is lower than the first precision, the adjustable algorithm adaptively reduces the number of laser partitions to be lighted corresponding to the standard precision.

5. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, wherein, The adjustable algorithm further comprises a pre-recognition detection, which adaptively adjusts the precision of the target image and the speckle density of the speckle pattern before recognizing the target image and the speckle pattern to ensure that the precision and the speckle density are higher than or equal to the standard precision.

6. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, wherein, The adjustable algorithm can adjust the speckle density from the medium density to the dense density to improve the precision of the recognition detection method.

7. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, characterized in that, It comprises:

8. The adaptive precision and distance three-dimensional recognition detection method according to claim 1, wherein, a variable pattern projection module for transforming and projecting a speckle pattern; 9. A three-dimensional recognition detection system with adaptive precision and distance, using the recognition method of claims 1 to 8, characterized in that, The variable image projection module comprises: a diffractive optical module for fine control of laser to form a speckle pattern of light distribution; a zoom module for adjusting the focal length of a lens to realize image precision adjustment; a laser module for projecting a speckle pattern; wherein the laser module comprises a laser, and the laser comprises a plurality of laser partitions, and different speckle patterns are projected by lighting different laser partitions; The recognition detection system further comprises: a detection module for detecting the distance of a recognition target and the precision of a target image; a feedback control module for controlling hardware and feeding back the condition of the hardware to a control system; a three-dimensional recognition module for identity recognition; a control module for controlling the normal work of each module. The variable image projection module further comprises a ceramic substrate and an FPC. The laser partitions can be independently controlled.

10. The adaptive precision and distance three-dimensional recognition detection system according to claim 9, wherein, The zoom module comprises at least one liquid crystal lens.

11. The adaptive precision and distance three-dimensional recognition detection system according to claim 9, wherein, The zoom module and the laser module can jointly adaptively adjust the target image precision and the speckle pattern density of the recognition target.

12. The adaptive precision and distance three-dimensional recognition detection system of claim 9, wherein, ​ 13. The adaptive precision and distance three-dimensional recognition detection system of claim 9, wherein, ​ 14. A computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions, when executed by the processor, implement the method as claimed in any one of claims 1 to 8.

15. A computer device, comprising: comprising: a communicator for communicating with the outside; a memory for storing a computer program; a processor for executing the computer program to implement the method as claimed in any one of claims 1 to 8.

Images