Scene feature extraction method and device, medium and electronic equipment

Abstract

The present disclosure relates to a scene feature extraction method, device, medium and electronic equipment, the method comprising: acquiring each environment object in a target environment, the environment object including a virtual character and an object in the target environment; for each environment object, determining the object type corresponding to the environment object; according to the object type of the environment object, collecting point cloud information of a target feature point of the environment object; and generating a feature representation corresponding to the environment object according to the point cloud information of the target feature point. In this way, when extracting features in a scene, different object types of environment objects can be based on their corresponding features for feature extraction, thereby improving the accuracy of feature extraction and the matching degree between environment objects. The point cloud information-based method can effectively reduce the data amount of the feature representation and accurately describe the environment.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method, apparatus, medium, and electronic device for scene feature extraction. Background Technology

[0002] Currently, interactive applications in terminals are increasingly designed to closely align with user experience, enhancing user immersion and engagement. For example, users can control corresponding virtual objects (AI, Artificial Intelligence) to operate and observe in a virtual environment. When controlling the movement of virtual objects in a virtual environment, it is usually necessary to encode the surrounding environment to understand the surrounding situation in order to control the virtual object to act.

[0003] In related technologies, it is common to use a Cartesian coordinate system and nearby map encoding to identify nearby enemies and objects, or to use fixed-width images to represent surrounding terrain and other features. However, in the above technical solutions, using images to describe the surrounding environment is very inefficient and requires high-quality data transmission. Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Firstly, this disclosure provides a scene feature extraction method, the method comprising:

[0006] Obtain various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment;

[0007] For each of the aforementioned environment objects, determine the object type corresponding to that environment object;

[0008] Based on the object type of the environmental object, collect the point cloud information of the target feature points of the environmental object;

[0009] Based on the point cloud information of the target feature points, a feature representation corresponding to the environmental object is generated.

[0010] Secondly, this disclosure provides a scene feature extraction device, the device comprising:

[0011] The acquisition module is used to acquire various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment;

[0012] The determination module is used to determine the object type corresponding to each of the environment objects.

[0013] The acquisition module is used to acquire point cloud information of target feature points of the environmental object according to the object type of the environmental object;

[0014] The generation module is used to generate a feature representation corresponding to the environment object based on the point cloud information of the target feature points.

[0015] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the method described in the first aspect.

[0016] Fourthly, this disclosure provides an electronic device, comprising:

[0017] A storage device on which computer programs are stored;

[0018] A processing device for executing the computer program in the storage device to implement the steps of the method described in the first aspect.

[0019] Therefore, in the above technical solution, for each environmental object in the target environment, point cloud information of the target feature points of the environmental object is collected according to the object type of the environmental object, so as to generate the feature representation corresponding to the environmental object based on the point cloud information of the target feature points. Thus, through the above technical solution, when extracting features in a scene, feature extraction can be performed on environmental objects of different object types according to their corresponding methods, thereby improving the accuracy of feature extraction and the matching degree between environmental objects. Furthermore, in this disclosure, representing the features describing the surrounding environment based on point cloud information can effectively reduce the amount of data corresponding to the feature representation, so that the extracted features can be applied to subsequent reinforcement learning training, reducing the high requirements of feature processing and transmission for reinforcement learning training, enabling accurate description of the surrounding environment based on the extracted feature representation, and improving the accuracy and effectiveness of scene feature extraction.

[0020] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0021] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0022] Figure 1This is a flowchart illustrating a scene feature extraction method according to one embodiment of the present disclosure;

[0023] Figure 2 This is a schematic diagram of an environment object in a virtual scene provided according to one embodiment of the present disclosure;

[0024] Figure 3 This is a schematic diagram representing the characteristics of an environmental object according to one embodiment of the present disclosure;

[0025] Figure 4 This is a block diagram of a scene feature extraction apparatus provided according to one embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of an electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0027] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0028] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0029] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0030] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0031] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0032] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0033] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0034] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0035] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0037] Meanwhile, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0038] The applicant's research revealed that in related technologies, when using images to describe scenes, such as in virtual scenes, if the scene is very empty, most of the surrounding map will be filled with empty pixels. Furthermore, due to the data transmission requirements in reinforcement learning training, images are usually small in size, resulting in extremely coarse information within the images, making it almost impossible for AI to make detailed observations of the surrounding environment. Based on this, the present disclosure provides the following embodiments.

[0039] Figure 1 The diagram shown is a flowchart illustrating a scene feature extraction method according to one embodiment of this disclosure. Figure 1 As shown, the method may include:

[0040] In step 11, various environmental objects in the target environment are obtained, wherein the environmental objects include virtual characters and objects in the target environment.

[0041] For example, the target environment can be a game scene, which may contain multiple virtual characters in combat. Each virtual character can be controlled by a user or by a machine control model. The game scene may also contain various bounding boxes, such as attack boxes, damage-bearing boxes, and battlefield edge boxes. As an example, image recognition can be performed on the scene image to identify various environmental objects in the target environment, such as the virtual characters controlled by the two combatants and objects in the environment, such as attack boxes and battlefield edge boxes. The types of objects to be identified can be set according to the specific application scenario, thereby identifying various objects in the target environment.

[0042] In step 12, for each environment object, the object type corresponding to the environment object is determined.

[0043] This allows for the setting of multiple object types based on actual application scenarios, and the establishment of a correspondence between each object type and environmental objects. When identifying various environmental objects, their corresponding object types can be further determined based on this correspondence. For example, object types can include character types, skill box types, and venue types. For instance, the character type could include the current virtual character (e.g.,...). Figure 2 As shown in A1) and the other party's virtual character (e.g. Figure 2 As shown in A2), environmental objects, such as skill boxes, can include attack boxes (e.g., ...). Figure 2 As shown in A3), environmental objects such as the hitbox can be included. The field type can include battlefield edge types, etc. The opposing virtual character is a character with hostile attributes to the current virtual character.

[0044] As an example, if the identified environment object is a virtual character, then the corresponding object type can be determined to be a character type based on this correspondence.

[0045] In step 13, point cloud information of target feature points of the environmental object is collected according to the object type of the environmental object.

[0046] The determination of target feature points differs for different object types, allowing for different processing of environmental objects under different object types to improve the accuracy of feature extraction. The extraction method for point cloud information can be based on methods existing in this field, and will not be elaborated further here. Compared to image extraction methods in related technologies, the point cloud information extraction method in this disclosure effectively reduces the amount of data processing required for feature extraction.

[0047] In step 14, feature representations corresponding to environmental objects are generated based on the point cloud information of target feature points.

[0048] In this embodiment of the disclosure, the corresponding feature representation of the target feature points of the environmental object can be determined based on the point cloud information of the environmental object, so as to characterize the surrounding environment of the environmental object.

[0049] Therefore, in the above technical solution, for each environmental object in the target environment, point cloud information of the target feature points of the environmental object is collected according to the object type of the environmental object, so as to generate the feature representation corresponding to the environmental object based on the point cloud information of the target feature points. Thus, through the above technical solution, when extracting features in a scene, feature extraction can be performed on environmental objects of different object types according to their corresponding methods, thereby improving the accuracy of feature extraction and the matching degree between environmental objects. Furthermore, in this disclosure, representing the features describing the surrounding environment based on point cloud information can effectively reduce the amount of data corresponding to the feature representation, so that the extracted features can be applied to subsequent reinforcement learning training, reducing the high requirements of feature processing and transmission for reinforcement learning training, enabling accurate description of the surrounding environment based on the extracted feature representation, and improving the accuracy and effectiveness of scene feature extraction.

[0050] In one possible embodiment, the object type of the environment object is a skill box type or a venue type;

[0051] Accordingly, the step of collecting point cloud information of target feature points of the environmental object according to the object type of the environmental object may include:

[0052] Determine the number of feature points for each object type. The number of feature points for each object type can be preset according to the actual application scenario. For example, since the range of a skill frame is typically smaller than that of a field type, the number of feature points for the skill frame type can be set to be less than that for the field type. For instance, the number of feature points for the skill frame type can be set to 16, while the number of feature points for the field type can be set to 80.

[0053] The feature points in the edge of the environmental object are determined based on the number of feature points, and point cloud acquisition is performed based on the feature points to obtain the point cloud information of the target feature points under the number of feature points.

[0054] The number of feature points collected can be constrained based on the number of feature points. For example, in the skill attack box type, if the number of feature points is 16, then 16 points on the edge of the skill attack box can be identified as feature points. Feature point extraction can be performed using methods known in the art. The method disclosed herein can be applied to feature collection in circular areas, such as where the edges of environment objects of the field type and skill box type are represented by circles. When extracting feature points, random sampling, uniform sampling, or random-uniform sampling can be used; this disclosure does not limit this. Figure 3 The feature representation of the field edge box under the field type is shown at C2, and the feature representation of each skill box under the skill box type is shown at C1.

[0055] As an example, point cloud information may include the x-coordinate, y-coordinate, and feature point attributes of feature points, wherein the feature point attributes may be determined based on the attributes of the environment object.

[0056] Therefore, the above technical solution allows for the description of relatively abstract objects in a scene based on point cloud information. For example, the edges of attack boxes can be described; a circular attack box can be described based on 16 target feature points. The point cloud information of each feature point can include XY coordinates and feature point attributes. For instance, if the attack box is an enemy attack box, then the feature point attributes extracted from each feature point based on that attack box are all related to the enemy attack box. Thus, this feature extraction method effectively reduces the amount of data corresponding to point cloud information. Compared with image-based representation, it significantly reduces the amount of data and processing required for feature representation, improving both the efficiency and accuracy of feature extraction.

[0057] In one possible embodiment, the step of generating a feature representation corresponding to the environment object based on the point cloud information of the target feature points may include:

[0058] The coordinates of the target feature points are corrected based on the coordinates of the current virtual character in the target environment to obtain the feature representation.

[0059] To further enhance the user experience, this disclosure defines the feature representations of various feature points in a first-person perspective. This means that when the AI ​​controls this virtual character, its input is ultimately converted into a first-person input, essentially simulating the interaction between a real user and the AI. This makes the AI's observations and input / output more closely resemble those of a real user, allowing the AI ​​to approximate the performance of a real user after reinforcement learning training. The current virtual character refers to the character controlled on the current device.

[0060] Based on this, in this embodiment of the disclosure, the extracted point cloud information can be transformed based on the coordinates of the current virtual character to the coordinate representation in the first-person perspective corresponding to the current virtual character.

[0061] As an example, correcting the coordinates of the target feature points based on the coordinates of the current virtual character in the target environment to obtain the feature representation may include:

[0062] The coordinates obtained by subtracting the coordinates of the current virtual character from the coordinates of the target feature point are used as the movement coordinates.

[0063] For example, the translation coordinates (x, y) can be determined as follows:

[0064] x = x ′ -x p ;y = y ′ -y p

[0065] Among them, (x ′ ,y ′ (x) is used to represent the coordinates of the target feature point. p ,y p () is used to represent the coordinates of the current virtual character.

[0066] Then, the coordinates obtained by rotating the moving coordinates by the target azimuth angle are determined as the feature representation, wherein the target azimuth angle is formed based on the current virtual character and its corresponding target virtual character.

[0067] The target azimuth angle is formed based on the current virtual character and its corresponding target virtual character. That is, during rotation, the target virtual character is matched in the first-person view after rotation, which meets the usage requirements in the virtual scene. The target virtual character can be quickly locked through coordinate correction, so as to improve the comprehensiveness and effectiveness of feature learning when reinforcement learning training is performed based on the extracted feature representation.

[0068] In one possible embodiment, the coordinates obtained by rotating the moving coordinates by the target azimuth angle can be determined as the feature representation using the following formula:

[0069] new_x = x*cosin(Θ) - y*sin(Θ)

[0070] new_y = x*sin(Θ) + y*cosin(Θ)

[0071] Wherein, new_x represents the horizontal coordinate in the feature representation, new_y represents the vertical coordinate in the feature representation, x represents the horizontal coordinate in the movement coordinate, y represents the vertical coordinate in the movement coordinate, and Θ represents the target azimuth angle.

[0072] In one possible embodiment, the target azimuth angle is determined in the following manner:

[0073] Determine the distance between each other virtual character in the target environment and the current virtual character.

[0074] In this context, the opposing virtual character can be a character controlled by a player belonging to a different side within the virtual environment than the current virtual character. Whether a player's controlled virtual character is the opposing virtual character can be determined through the player's attributes. For example, in a game scenario where it's a single-player game, all virtual characters except the current one are the opposing virtual characters; if it's a two-player game, all virtual characters except the current one and the other player in the same group are the opposing virtual characters.

[0075] After identifying the other party's virtual character, the distance between them can be determined by using the first coordinates of each other party's virtual character in the target environment and the coordinates of the current virtual character. This distance can be calculated using Euclidean distance, which will not be elaborated here.

[0076] The virtual character closest to the current virtual character is identified as the target virtual character, and the angle between the line connecting the current virtual character and the target virtual character and the Y-axis is defined as the target azimuth angle. In a virtual scene, the positive Y-axis is typically chosen as true north. Therefore, the angle between the line connecting the current virtual character and the target virtual character and the axis corresponding to true north in the environment's coordinate system is used as the azimuth angle. This determines the azimuth angle of the closest enemy virtual character to the current virtual character, ensuring that the closest enemy virtual character is always positioned due north in its first-person perspective in the feature representation. This allows for adjustments to the characteristics of other environmental objects based on the target virtual character when moving within the virtual environment, providing data support for rapid decision-making in subsequent gameplay.

[0077] In one possible embodiment, the step of collecting point cloud information of target feature points of the environmental object according to the object type of the environmental object includes:

[0078] The point cloud information of the target feature points is determined based on the coordinates and attributes of the environmental object.

[0079] In this embodiment of the disclosure, a player's virtual character can be represented by a feature point. In this disclosure, the point corresponding to the environment object can be directly determined as the target feature point, the coordinates of the environment object can be determined as the coordinates of the target feature point, and the attributes of the environment object can be determined as the attributes of the target feature point. For example, the attribute can be the attribute of an enemy virtual character, so that point cloud information can be formed based on the coordinates and attributes of the target feature point.

[0080] Therefore, through the above technical solution, objects under the role type can be simplified to a single point in the scene. For environmental objects under the role type, they can be directly simplified to a single target feature point for representation. This reduces the amount of data processing required for scene feature extraction while ensuring the effectiveness of feature processing.

[0081] This can be achieved by initializing values ​​when extracting point cloud information of feature points. Initially, an empty array can be initialized, and then the point cloud information of each extracted feature point can be added to this array. The array after the last update is used as the feature representation of the environment object.

[0082] Based on the same inventive concept, this disclosure also provides a scene feature extraction device, such as... Figure 4 As shown, the device 10 includes:

[0083] The acquisition module 100 is used to acquire various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment;

[0084] The determining module 200 is used to determine the object type corresponding to each of the environment objects;

[0085] The acquisition module 300 is used to acquire point cloud information of target feature points of the environmental object according to the object type of the environmental object;

[0086] The generation module 400 is used to generate a feature representation corresponding to the environment object based on the point cloud information of the target feature points.

[0087] Optionally, the object type of the environment object is a skill box type or a venue type;

[0088] The acquisition module includes:

[0089] The first determining submodule is used to determine the number of feature points under the object type;

[0090] The acquisition submodule is used to determine the feature points in the edge of the environmental object according to the number of feature points, and to perform point cloud acquisition based on the feature points to obtain the point cloud information of the target feature points under the number of feature points.

[0091] Optionally, the generation module includes:

[0092] The correction submodule is used to correct the coordinates of the target feature points based on the coordinates of the current virtual character in the target environment, so as to obtain the feature representation.

[0093] Optionally, the correction submodule includes:

[0094] The first processing submodule is used to subtract the coordinates of the current virtual character from the coordinates of the target feature point and use the resulting coordinates as the movement coordinates;

[0095] The second processing submodule is used to determine the coordinates obtained by rotating the moving coordinates by the target azimuth angle as the feature representation, wherein the target azimuth angle is formed based on the current virtual character and its corresponding target virtual character.

[0096] Optionally, the second processing submodule is used to determine the coordinates obtained by rotating the moving coordinates by the target azimuth angle as the feature representation using the following formula:

[0097] new_x = x*cosin(Θ) - y*sin(Θ)

[0098] new_y = x*sin(Θ) + y*cosin(Θ)

[0099] Wherein, new_x represents the horizontal coordinate in the feature representation, new_y represents the vertical coordinate in the feature representation, x represents the horizontal coordinate in the movement coordinate, y represents the vertical coordinate in the movement coordinate, and Θ represents the target azimuth angle.

[0100] Optionally, the target azimuth angle is determined in the following manner:

[0101] Determine the distance between each other virtual character in the target environment and the current virtual character;

[0102] The virtual character with the smallest distance is identified as the target virtual character, and the angle between the line connecting the current virtual character and the target virtual character and the Y-axis is identified as the target azimuth angle.

[0103] Optionally, the role type of the environment object, the acquisition module includes:

[0104] The second determining submodule is used to determine the point cloud information of the target feature points based on the coordinates of the environmental object and the attributes of the environmental object.

[0105] The following is for reference. Figure 5The diagram illustrates a structural schematic of an electronic device (e.g., a terminal device or a server) 600 suitable for implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0106] like Figure 5 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0107] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0108] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0109] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0110] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0111] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0112] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire various environmental objects in a target environment, wherein the environmental objects include virtual characters and objects in the target environment; determine the object type corresponding to each environmental object; collect point cloud information of target feature points of the environmental object according to the object type of the environmental object; and generate a feature representation corresponding to the environmental object according to the point cloud information of the target feature points.

[0113] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. 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 drawings. 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 using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0115] The modules described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a module does not necessarily limit the module itself; for example, an acquisition module can also be described as "a module for acquiring various environmental objects in a target environment".

[0116] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0117] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0118] According to one or more embodiments of this disclosure, Example 1 provides a scene feature extraction method, wherein the method includes:

[0119] Obtain various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment;

[0120] For each of the aforementioned environment objects, determine the object type corresponding to that environment object;

[0121] Based on the object type of the environmental object, collect the point cloud information of the target feature points of the environmental object;

[0122] Based on the point cloud information of the target feature points, a feature representation corresponding to the environment object is generated. According to one or more embodiments of this disclosure, Example 2 provides the method of Example 1, wherein the object type of the environment object is a skill box type or a venue type;

[0123] The step of collecting point cloud information of target feature points of the environmental object according to the object type of the environmental object includes:

[0124] Determine the number of feature points under the object type;

[0125] The feature points in the edge of the environmental object are determined based on the number of feature points, and point cloud acquisition is performed based on the feature points to obtain the point cloud information of the target feature points under the number of feature points.

[0126] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 1, wherein generating a feature representation corresponding to the environment object based on the point cloud information of the target feature points includes:

[0127] The coordinates of the target feature points are corrected based on the coordinates of the current virtual character in the target environment to obtain the feature representation.

[0128] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 3, wherein correcting the coordinates of the target feature points based on the coordinates of the current virtual character in the target environment to obtain the feature representation includes:

[0129] The coordinates obtained by subtracting the coordinates of the current virtual character from the coordinates of the target feature point are used as the movement coordinates;

[0130] The coordinates obtained by rotating the moving coordinates by the target azimuth angle are determined as the feature representation, wherein the target azimuth angle is formed based on the current virtual character and its corresponding target virtual character.

[0131] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 4, wherein the coordinates obtained by rotating the moving coordinates by the target azimuth angle are determined as the feature representation by the following formula:

[0132] new_x = x*cosin(Θ) - y*sin(Θ)

[0133] new_y = x*sin(Θ) + y*cosin(Θ)

[0134] Wherein, new_x represents the horizontal coordinate in the feature representation, new_y represents the vertical coordinate in the feature representation, x represents the horizontal coordinate in the movement coordinate, y represents the vertical coordinate in the movement coordinate, and Θ represents the target azimuth angle.

[0135] According to one or more embodiments of this disclosure, Example 6 provides the method of Example 4, wherein the target azimuth angle is determined in the following manner:

[0136] Determine the distance between each other virtual character in the target environment and the current virtual character;

[0137] The virtual character with the smallest distance is identified as the target virtual character, and the angle between the line connecting the current virtual character and the target virtual character and the Y-axis is identified as the target azimuth angle.

[0138] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 1, wherein the role type of the object type of the environment object, and the step of collecting point cloud information of target feature points of the environment object according to the object type of the environment object, includes:

[0139] The point cloud information of the target feature points is determined based on the coordinates and attributes of the environmental object.

[0140] According to one or more embodiments of this disclosure, Example 8 provides a scene feature extraction apparatus, wherein the apparatus includes:

[0141] The acquisition module is used to acquire various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment;

[0142] The determination module is used to determine the object type corresponding to each of the environment objects.

[0143] The acquisition module is used to acquire point cloud information of target feature points of the environmental object according to the object type of the environmental object;

[0144] The generation module is used to generate a feature representation corresponding to the environment object based on the point cloud information of the target feature points.

[0145] According to one or more embodiments of the present disclosure, Example 9 provides a computer-readable medium having a computer program stored thereon that, when executed by a processing device, implements the steps of the method described in any one of Examples 1-7.

[0146] According to one or more embodiments of this disclosure, Example 10 provides an electronic device, including:

[0147] A storage device on which computer programs are stored;

[0148] A processing device for executing the computer program in the storage device to implement the steps of any one of the methods in Examples 1-7.

[0149] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0150] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0151] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A method for scene feature extraction, characterized in that, The method includes: Obtain various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment; For each of the aforementioned environment objects, determine the object type corresponding to that environment object; Based on the object type of the environmental object, collect the point cloud information of the target feature points of the environmental object; Based on the point cloud information of the target feature points, a feature representation corresponding to the environment object is generated, including: correcting the coordinates of the target feature points based on the coordinates of the current virtual character in the target environment to obtain the feature representation; The step of correcting the coordinates of the target feature point based on the coordinates of the current virtual character in the target environment to obtain the feature representation includes: subtracting the coordinates of the current virtual character from the coordinates of the target feature point to obtain the coordinates as the movement coordinates; and rotating the movement coordinates by the target azimuth angle to obtain the coordinates as the feature representation, wherein the target azimuth angle is formed based on the current virtual character and its corresponding target virtual character.

2. The method according to claim 1, characterized in that, The object type of the environment object is either a skill box type or a venue type; The step of collecting point cloud information of target feature points of the environmental object according to the object type of the environmental object includes: Determine the number of feature points under the object type; The feature points in the edge of the environmental object are determined based on the number of feature points, and point cloud acquisition is performed based on the feature points to obtain the point cloud information of the target feature points under the number of feature points.

3. The method according to claim 1, characterized in that, The coordinates obtained by rotating the moving coordinates by the target azimuth angle are determined as the feature representation using the following formula: in, Used to represent the horizontal coordinate in the feature representation. Used to represent the ordinate in the feature representation. Used to represent the x-coordinate in the movement coordinates Used to represent the ordinate in the movement coordinates. Used to indicate the target azimuth angle.

4. The method according to claim 1, characterized in that, The target azimuth angle is determined in the following way: Determine the distance between each other virtual character in the target environment and the current virtual character; The virtual character with the smallest distance is identified as the target virtual character, and the angle between the line connecting the current virtual character and the target virtual character and the Y-axis is identified as the target azimuth angle.

5. The method according to claim 1, characterized in that, The object type of the environment object is a role type. The step of collecting point cloud information of the target feature points of the environment object based on its object type includes: The point cloud information of the target feature points is determined based on the coordinates and attributes of the environmental object.

6. A scene feature extraction device, characterized in that, The device includes: The acquisition module is used to acquire various environmental objects in the target environment, wherein the environmental objects include virtual characters and objects in the target environment; The determination module is used to determine the object type corresponding to each of the environment objects. The acquisition module is used to acquire point cloud information of target feature points of the environmental object according to the object type of the environmental object; The generation module is used to generate a feature representation corresponding to the environment object based on the point cloud information of the target feature points, including: correcting the coordinates of the target feature points according to the coordinates of the current virtual character in the target environment to obtain the feature representation; The step of correcting the coordinates of the target feature point based on the coordinates of the current virtual character in the target environment to obtain the feature representation includes: subtracting the coordinates of the current virtual character from the coordinates of the target feature point to obtain the coordinates as the movement coordinates; and rotating the movement coordinates by the target azimuth angle to obtain the coordinates as the feature representation, wherein the target azimuth angle is formed based on the current virtual character and its corresponding target virtual character.

7. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processing device, it implements the steps of the method described in any one of claims 1-5.

8. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-5.

Images