Game picture generation method and device, equipment, medium and computer program product

Abstract

The invention discloses a game picture generation method and device, equipment, a medium and a computer program product. The method comprises the steps of obtaining a game picture of a first player and a game picture of at least one second player in a game; and according to the game picture of the first player and the game picture of the second player, generating a target picture of the first player in each target view angle in the game. According to the method, the game picture is expanded from a single-view-angle picture to a multi-view-angle picture, a wider view field and richer scene content are provided, the immersive experience of a user is greatly enhanced, the accuracy and responsiveness of game interaction are improved, and players can interact with the game content more visually and naturally.

Description

Technical Field

[0001] The present invention relates to the field of game technology, and in particular to a method, device, equipment, medium and computer program product for generating a game screen. Background Art

[0002] The current game screen cannot provide gamers with a broader field of view and richer scene content because the game itself only has a single perspective. This limitation affects the immersion of the game. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a game screen generation method, device, equipment, medium and computer program product, which expands the game screen from a single perspective to multiple perspectives, provides a wider field of view and richer scene content, greatly enhances the user's immersive experience, improves the accuracy and responsiveness of game interaction, and enables players to interact with game content more intuitively and naturally.

[0004] In order to achieve the above object, an embodiment of the present invention provides a method for generating a game screen, comprising:

[0005] Acquire a game screen of a first player and a game screen of at least one second player in the game;

[0006] According to the game screen of the first player and the game screen of the second player, a target screen of the first player at each target perspective in the game is generated.

[0007] As an improvement of the above solution, the game screen includes a single-view screen, and then generating a target screen of each target view of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0008] Feature extraction and feature matching are performed on the single-view picture of the first player and the single-view picture of the second player to generate the target picture of each target viewpoint of the first player in the game.

[0009] As an improvement of the above solution, the game screen includes a multi-perspective screen, and the generating of the target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0010] The multi-perspective images of the first player and the multi-perspective images of the second player are identified and segmented to generate the target images of the first player at each target perspective in the game.

[0011] As an improvement of the above solution, the game screen includes a single-perspective screen and a multi-perspective screen, and the generating of the target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0012] Performing feature extraction and feature matching on the single-view picture of the first player and the single-view picture of the second player to generate a first target picture of each target view;

[0013] Identifying and segmenting the multi-perspective images of the first player and the multi-perspective images of the second player to generate second target images of the target perspectives;

[0014] The first target screen and the second target screen of each corresponding target perspective are integrated to obtain the target screen of each target perspective of the first player in the game.

[0015] As an improvement of the above solution, the step of extracting and matching features of the first player's single-view picture and the second player's single-view picture to generate the first target picture of each target view includes:

[0016] Calculating the position of the second player relative to the first player according to the single-view picture of the first player and the single-view picture of the second player, so as to determine the target view corresponding to the single-view picture of the second player;

[0017] Feature extraction and feature matching are performed on the single-perspective picture of the first player and the single-perspective picture of the second player, and a transformation matrix is ​​calculated, and the single-perspective picture of the second player is converted into the first target picture of the target perspective according to the transformation matrix.

[0018] As an improvement of the above solution, the step of extracting and matching features of the single-view picture of the first player and the single-view picture of the second player, and calculating a transformation matrix, and converting the single-view picture of the second player into the first target picture of the target perspective according to the transformation matrix includes:

[0019] Extracting features from the single-view picture of the first player and the single-view picture of the second player respectively to obtain a plurality of first feature points and a plurality of second feature points;

[0020] Perform feature matching on the first feature point and the second feature point to obtain a plurality of matching feature point pairs;

[0021] For each of the matching feature point pairs, calculating a transformation matrix;

[0022] The pixels in the single-view picture of the second player are mapped to the picture corresponding to the target view of the first player according to the transformation matrix to obtain the first target picture of the target view.

[0023] As an improvement of the above solution, the identifying and segmenting of the multi-perspective picture of the first player and the multi-perspective picture of the second player to generate the second target picture of each target perspective includes:

[0024] Performing multi-dimensional feature extraction and feature similarity calculation on the multi-perspective images of the first player and the multi-perspective images of the second player;

[0025] Dividing pixels in the multi-perspective picture of the first player and the multi-perspective picture of the second player into clusters corresponding to the pictures of each target perspective according to the feature similarity;

[0026] A segmentation plane is determined based on the clustering result, and the multi-perspective picture of the first player and the multi-perspective picture of the second player are divided into pictures of each target perspective according to the segmentation plane to generate a second target picture of each target perspective.

[0027] As an improvement of the above solution, the first target screen and the second target screen of each corresponding target perspective are integrated to obtain the target screen of each target perspective of the first player in the game, including:

[0028] Extracting and matching feature points of the first target picture and the second target picture, and aligning images in the first target picture and the second target picture according to the matching result;

[0029] The aligned first target picture and the second target picture are merged to obtain the target pictures of each target perspective of the first player in the game.

[0030] As an improvement of the above solution, the game screen generation method is applied to an in-vehicle game, and the method further includes:

[0031] The target images of each target perspective are rendered respectively onto the vehicle-mounted screen of the corresponding perspective for display.

[0032] The embodiment of the present invention further provides a game screen generating device, comprising:

[0033] A screen acquisition module, used to acquire a game screen of a first player and a game screen of at least one second player in the game;

[0034] The screen generation module is used to generate a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player.

[0035] An embodiment of the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any of the above-mentioned game screen generation methods when executing the computer program.

[0036] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any of the above-mentioned game screen generation methods.

[0037] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, any of the above-mentioned game screen generation methods is implemented.

[0038] Compared with the prior art, the beneficial effects of a game screen generation method, device, equipment, medium and computer program product provided by the embodiments of the present invention are: by acquiring the game screen of the first player and the game screen of at least one second player in the game; generating the target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player. The embodiments of the present invention provide a wider field of view and richer scene content by expanding the game screen from a single perspective screen to multiple perspective screens, greatly enhancing the user's immersive experience, improving the accuracy and responsiveness of game interaction, and allowing players to interact with game content more intuitively and naturally. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of a preferred embodiment of a method for generating a game screen provided by the present invention;

[0040] Figure 2 It is a structural schematic diagram of a preferred embodiment of a game screen generating device provided by the present invention;

[0041] Figure 3 It is a structural schematic diagram of a preferred embodiment of a terminal device provided by the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] See also Figure 1 , Figure 1 The figure is a flow chart of a preferred embodiment of a method for generating a game screen provided by the present invention. The method for generating a game screen comprises:

[0044] S1, obtaining a game screen of a first player and a game screen of at least one second player in the game;

[0045] S2, generating a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player.

[0046] Specifically, the game screen generation method provided by the embodiment of the present invention obtains the game screen of the first player and the game screen of at least one second player in the game after entering the game. According to the game screen of the first player and the game screen of the second player, the target screen of each target perspective of the first player in the game is generated. Among them, the target perspective includes the left perspective, the right perspective and the rear perspective. For example, there are four players A, B, C, and D in the game, among which player A is the first player, and player B, player C and player D are all second players. Here, the game screen of each player is the game screen from the first-person perspective, and the game screen of player A is the screen from the front perspective. According to the game screens of players A, B, C, and D, the target screen of the left perspective, the target screen of the right perspective, and the target screen of the rear perspective of player A in the game can be generated.

[0047] In another preferred embodiment, the game screen includes a single-view screen, and generating a target screen of each target view of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0048] Feature extraction and feature matching are performed on the single-view picture of the first player and the single-view picture of the second player to generate the target picture of each target viewpoint of the first player in the game.

[0049] Specifically, in the embodiment of the present invention, the game screen includes a single-view screen, that is, the game screen of each player only includes the game screen under the first-person perspective of the player. Feature extraction is performed on the single-view screen of each player, and feature matching is performed on the single-view screen of the first player and the single-view screen of at least one second player, so as to expand and generate various target perspectives, for example, target screens on the left, right, and back.

[0050] In another preferred embodiment, the game screen includes a multi-perspective screen, and generating a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0051] The multi-perspective images of the first player and the multi-perspective images of the second player are identified and segmented to generate the target images of the first player at each target perspective in the game.

[0052] Specifically, in the embodiment of the present invention, the game screen includes a multi-perspective screen, that is, each player's game screen includes multiple perspective screens. The multi-perspective screen of each player is identified and segmented to generate different target perspectives, such as left, right, and back target screens.

[0053] In another preferred embodiment, the game screen includes a single-perspective screen and a multi-perspective screen, and S2, based on the game screen of the first player and the game screen of the second player, generates a target screen of each target perspective of the first player in the game, including:

[0054] S21, performing feature extraction and feature matching on the single-view picture of the first player and the single-view picture of the second player to generate a first target picture of each target view;

[0055] S22, identifying and segmenting the multi-perspective picture of the first player and the multi-perspective picture of the second player to generate a second target picture of each target perspective;

[0056] S23, integrating the first target screen and the second target screen of each corresponding target perspective to obtain the target screen of each target perspective of the first player in the game.

[0057] Specifically, in the embodiment of the present invention, the game screen includes a single-perspective screen and a multi-perspective screen. For the single-perspective screen of the first player and the single-perspective screen of the second player, feature extraction and feature matching are performed to expand and generate various different target perspectives, for example, first target screens on the left, right, and back. For the multi-perspective screen containing multiple perspectives in the game screens of the first player and the second player, identification and segmentation are performed to generate various different target perspectives, for example, second target screens on the left, right, and back. Then, the first target screen and the second target screen of each corresponding target perspective are integrated to obtain the target screens of each target perspective of the first player in the game, for example, the first target screen and the second target screen on the left are integrated, the first target screen and the second target screen on the right are integrated, and the first target screen and the second target screen on the back are integrated to finally obtain the target screens on the left, right, and back.

[0058] Exemplarily, the game screen generation method provided by the embodiment of the present invention can be applied to in-vehicle games, and the in-vehicle game can be switched under parking conditions. For single-perspective racing games, the mobile phone is connected to various display screens in the car, and the mobile phone and the in-vehicle system are connected to a network. The mobile client processes the received multi-perspective images according to the specifications of the in-vehicle screen, and sets mapping rules in the client to specify the in-vehicle screens to which the images of different perspectives are projected, for example: the left perspective is projected to the left rearview mirror screen. The mobile client transmits the image data to the in-vehicle system through the network, and the in-vehicle system receives the image data and displays the image on the corresponding screen according to the preset mapping rules, for example: the left perspective image is displayed on the left rearview mirror, the right perspective image is displayed on the right rearview mirror, the rear side perspective image is displayed on the rearview mirror or the in-vehicle screen, and the first perspective (front side perspective) image is displayed on the front windshield or the in-vehicle central control screen. In this way, when the player is playing in the car, multiple corresponding perspective images can be rendered and projected onto the corresponding in-vehicle screen.

[0059] The embodiments of the present invention provide a wider field of view and richer scene content by expanding the game screen from a single perspective to multiple perspectives, greatly enhancing the user's immersive experience, improving the accuracy and responsiveness of game interaction, and enabling players to interact with game content more intuitively and naturally.

[0060] In another preferred embodiment, the step S21, extracting and matching features of the first player's single-view picture and the second player's single-view picture to generate a first target picture of each target view, includes:

[0061] S211, calculating the position of the second player relative to the first player according to the single-view picture of the first player and the single-view picture of the second player, so as to determine the target view corresponding to the single-view picture of the second player;

[0062] S212, performing feature extraction and feature matching on the single-perspective picture of the first player and the single-perspective picture of the second player, and calculating a transformation matrix, and converting the single-perspective picture of the second player into the first target picture of the target perspective according to the transformation matrix.

[0063] Specifically, the embodiment of the present invention obtains the state data of each player from the single-view game screen of each player, and the state data includes the position and orientation. For example, the video streams of each player are transmitted to the server that processes the multi-view screen, and the three-dimensional coordinates (x, y, z) and the θ angle position of each player's car in the game world are analyzed. According to the position and orientation of each player, the relative position arrangement between the players is determined. According to the relative position arrangement between the players in the game, the screens of the remaining target perspectives other than the first perspective of the first player are obtained from the state data of other second players. For example, by using the position and orientation data of the players, by comparing the position coordinates of the players, a geometric calculation method is used to determine the relative ranking and position (front, back, left, right) between the players. According to the results of the relative ranking analysis, it is determined which player's screen needs to be converted into a new perspective image, and the target perspective corresponding to the single-view game screen of the second player is determined. If player B is located at the back, and players C and D are located on the left and right sides, the screens of these players will be selected as conversion targets. Then, feature extraction and feature matching are performed on the single-perspective picture of the first player's first perspective and the single-perspective picture of the second player, and a transformation matrix is ​​calculated. According to the transformation matrix, the single-perspective picture of the second player is converted into the first picture of the first target picture of the target perspective.

[0064] For example, suppose player A is on a curve on the track, player A has a first-person perspective, player B is following closely behind, player C is behind on the left, and player D is behind on the right. Suppose player A's coordinates are (x A ,y A ,z A ), the direction is θ A . The coordinates of players B, C, and D are (x B ,y B ,z B ), (x C ,y C ,z C ),((x D ,y D ,z D )), the directions are θ B ,θC ,θ D . Calculate the position vectors of players B, C, and D relative to player A, and use the vector dot product to calculate the angle between players B, C, D and player A to determine their relative positions. Extract feature points from all players' screens, and find matching feature point pairs between player A's screen and those of players B, C, and D. For each matching feature point pair, calculate the transformation matrix. For example, if player C is located to the left rear of player A, calculate a transformation matrix that maps the pixels in player C's screen to the left rear of player A's perspective. Use the transformation matrix to transform the screens of players B, C, and D into the corresponding perspective screens from player A's perspective. Encode the converted perspective image and transmit it to the player client, which decodes it to obtain images of different perspectives (front, left rear, right rear, and front rear).

[0065] In another preferred embodiment, the step of extracting and matching features of the first player's single-view picture and the second player's single-view picture, and calculating a transformation matrix, and converting the second player's single-view picture into the first target picture of the target perspective according to the transformation matrix comprises:

[0066] Extracting features from the single-view picture of the first player and the single-view picture of the second player respectively to obtain a plurality of first feature points and a plurality of second feature points;

[0067] Perform feature matching on the first feature point and the second feature point to obtain a plurality of matching feature point pairs;

[0068] For each of the matching feature point pairs, calculating a transformation matrix;

[0069] The pixels in the single-view picture of the second player are mapped to the picture corresponding to the target view of the first player according to the transformation matrix to obtain the first target picture of the target view.

[0070] Specifically, the embodiment of the present invention uses an image feature detection algorithm to extract feature points from the first perspective of the first player and the single perspective of the second player, and generates a descriptor for each feature point, and then uses a feature matching algorithm to find the matching feature point pairs between the first perspective of the first player and the single perspective of the second player. The transformation matrix is ​​calculated using these matching feature point pairs, and the transformation matrix can map the pixels in the single perspective of the other second players to the transformation parameters required by the first player, and the transformation parameters are the parameters in the feature matching algorithm; then, the transformation matrix is ​​applied to transform the single perspective of the other second players to generate the first target images of each target perspective.

[0071] In another preferred embodiment, the method further comprises:

[0072] An image interpolation method is used to fill in discontinuous or missing pixels in the first target picture of each target viewing angle.

[0073] Specifically, after generating the first target images of each target perspective, the embodiment of the present invention uses image interpolation to fill in any discontinuous or missing pixels in the new image caused by the transformation, thereby ensuring that the generated image is visually smooth and natural.

[0074] In another preferred embodiment, the S22, identifying and segmenting the multi-perspective picture of the first player and the multi-perspective picture of the second player to generate the second target picture of each target perspective, comprises:

[0075] S221, performing multi-dimensional feature extraction and feature similarity calculation on the multi-perspective images of the first player and the multi-perspective images of the second player;

[0076] S222, dividing pixels in the multi-perspective picture of the first player and the multi-perspective picture of the second player into clusters corresponding to the pictures of each target perspective according to the feature similarity;

[0077] S223, determining a segmentation plane based on the clustering result, dividing the multi-perspective picture of the first player and the multi-perspective picture of the second player into pictures of each target perspective according to the segmentation plane, and generating a second target picture of each target perspective.

[0078] Specifically, the embodiment of the present invention targets a multi-perspective screen containing multiple perspectives. First, the multi-dimensional features of each player's multi-perspective screen are extracted and the feature similarity is calculated. Then, a cluster analysis method is used to divide the elements in the multi-perspective screen into different clusters according to the feature similarity. These clusters represent different target perspectives. Then, a segmentation plane is determined based on the clustering result, and the multi-perspective screen is divided into target perspective areas according to the segmentation plane, thereby generating a second target screen for each target perspective. Finally, image restoration technology is used to fill in the missing screen that may be caused by segmentation to ensure the integrity and coherence of the screen for each target perspective.

[0079] It should be noted that when extracting and splicing multidimensional features, the color histogram is used to describe the color distribution and characteristics of the image; the gray level co-occurrence matrix (GLCM) is used to analyze the roughness, contrast and directionality of the image texture; the edge detection algorithm is used to determine the outline of the object in the image; and the optical flow algorithm is used to calculate the motion vector of each point in the image sequence. All extracted features are standardized so that they are at the same order of magnitude. The standardization method is as follows:

[0080]

[0081] Among them, x represents the eigenvalue, μ represents the mean value of the feature, and σ represents the standard deviation.

[0082] The feature pooling method is used to process the four feature vectors extracted above, reduce the spatial dimension of each feature, and retain the most important information of each feature. The pooled feature vectors are concatenated to form a comprehensive feature vector.

[0083] Using the cluster analysis method, the similarity distance between data points is calculated based on the comprehensive feature vector. The specific calculation method is as follows:

[0084]

[0085] Among them, A and B represent two eigenvectors, A i and B i Respectively represent the value of the vector in the i-th dimension.

[0086] Using the above method, calculate the similarity distance for each pair of samples in the data set. Fill the calculation results into the adjacency matrix, where the rows and columns of the matrix represent the samples in the data set, and the values ​​in the matrix represent the similarity or distance between the samples. For each data point to be classified, use the nearest neighbor search algorithm to find the k nearest neighbors. Here k takes the value of 4, replacing the four perspectives of front, back, left, and right. Based on the k best neighbors found, determine their labels. Based on the labels of the nearest neighbors, make classification decisions for all data points to be classified, and finally obtain 4 clusters. Analyze the characteristics of each cluster to obtain their spatial location information. For example, one cluster may represent images from the "left perspective" and another cluster represents images from the "right perspective".

[0087] Calculate the center point of each cluster and identify the point in each cluster that is farthest from the center. These points can be used as candidate points for the boundary. For each pair of points in the cluster, calculate the distance between them to determine the farthest point pair as the boundary point, and use the boundary points to build the boundary.

[0088] Image segmentation is performed using the region growing algorithm. Each boundary point is used as a seed point. Based on the similarity measurement of features such as color, texture, and direction, the neighboring pixels are evaluated to check whether they meet the preset similarity criteria. If the similarity between the neighboring pixels and the seed point in the feature space exceeds the set threshold, these pixels are included in the current region and become new seed points for further growth and expansion. This process continues until all pixels have been checked and no new pixels meet the similarity criteria, thus completing the image segmentation and forming regions with consistent features. The boundaries of each region are analyzed to check whether there are missing parts. For the missing parts, the pixels in the surrounding similar regions are used to fill in and generate a complete image.

[0089] The filled perspective image is encoded and transmitted to the player client, and the player client decodes and obtains images of different target perspectives (left side, right side, back side).

[0090] In another preferred embodiment, the step S23, integrating the first target screen and the second target screen of each corresponding target perspective to obtain the target screen of each target perspective of the first player in the game, includes:

[0091] S231, extracting and matching feature points of the first target picture and the second target picture, and aligning images in the first target picture and the second target picture according to the matching result;

[0092] S232: Merge the aligned first target screen and the second target screen to obtain the target screens of the first player at each target perspective in the game.

[0093] Specifically, the embodiment of the present invention pre-processes the first target picture and the second target picture of each target perspective to unify the resolution. Then, through the feature point matching technology, the key feature points of the pre-processed first target picture and the second target picture are extracted and matched, and according to the corresponding relationship of the feature points, a geometric transformation method is used, such as rotation, scaling and translation, to align the images in the first target picture and the second target picture. Then, the corresponding transformation matrix is ​​constructed and applied to align the pictures in space. On the basis of the alignment, the aligned first target picture and the second target picture are merged by the image fusion method to ensure the continuity of the picture, and the target pictures of each target perspective are obtained.

[0094] Correspondingly, the present invention also provides a game screen generating device, which can implement all the processes of the game screen generating method in the above embodiment.

[0095] See also Figure 2 , Figure 2 1 is a schematic diagram of a preferred embodiment of a game screen generating device provided by the present invention. The game screen generating device comprises:

[0096] A screen acquisition module 201, used to acquire a game screen of a first player and a game screen of at least one second player in the game;

[0097] The screen generation module 202 is used to generate a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player.

[0098] Preferably, the game screen includes a single-view screen, and the step of generating a target screen of each target viewpoint of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0099] Feature extraction and feature matching are performed on the single-view picture of the first player and the single-view picture of the second player to generate the target picture of each target viewpoint of the first player in the game.

[0100] Preferably, the game screen includes a multi-perspective screen, and the generating of a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0101] The multi-perspective images of the first player and the multi-perspective images of the second player are identified and segmented to generate the target images of the first player at each target perspective in the game.

[0102] Preferably, the game screen includes a single-perspective screen and a multi-perspective screen, and the generating of a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes:

[0103] Performing feature extraction and feature matching on the single-view picture of the first player and the single-view picture of the second player to generate a first target picture of each target view;

[0104] Identifying and segmenting the multi-perspective images of the first player and the multi-perspective images of the second player to generate second target images of the target perspectives;

[0105] The first target screen and the second target screen of each corresponding target perspective are integrated to obtain the target screen of each target perspective of the first player in the game.

[0106] Preferably, the extracting and matching features of the first player's single-view picture and the second player's single-view picture to generate the first target picture of each target viewpoint includes:

[0107] Calculating the position of the second player relative to the first player according to the single-view picture of the first player and the single-view picture of the second player, so as to determine the target view corresponding to the single-view picture of the second player;

[0108] Feature extraction and feature matching are performed on the single-perspective picture of the first player and the single-perspective picture of the second player, and a transformation matrix is ​​calculated, and the single-perspective picture of the second player is converted into the first target picture of the target perspective according to the transformation matrix.

[0109] Preferably, the extracting and matching features of the first player's single-view picture and the second player's single-view picture, and calculating a transformation matrix, and converting the second player's single-view picture into the first target picture of the target perspective according to the transformation matrix, comprises:

[0110] Extracting features from the single-view picture of the first player and the single-view picture of the second player respectively to obtain a plurality of first feature points and a plurality of second feature points;

[0111] Perform feature matching on the first feature point and the second feature point to obtain a plurality of matching feature point pairs;

[0112] For each of the matching feature point pairs, calculating a transformation matrix;

[0113] The pixels in the single-view picture of the second player are mapped to the picture corresponding to the target view of the first player according to the transformation matrix to obtain the first target picture of the target view.

[0114] Preferably, the identifying and segmenting the multi-perspective picture of the first player and the multi-perspective picture of the second player to generate the second target picture of each target perspective includes:

[0115] Performing multi-dimensional feature extraction and feature similarity calculation on the multi-perspective images of the first player and the multi-perspective images of the second player;

[0116] Dividing pixels in the multi-perspective picture of the first player and the multi-perspective picture of the second player into clusters corresponding to the pictures of each target perspective according to the feature similarity;

[0117] A segmentation plane is determined based on the clustering result, and the multi-perspective picture of the first player and the multi-perspective picture of the second player are divided into pictures of each target perspective according to the segmentation plane to generate a second target picture of each target perspective.

[0118] Preferably, the step of integrating the first target screen and the second target screen of each corresponding target perspective to obtain the target screen of each target perspective of the first player in the game includes:

[0119] Extracting and matching feature points of the first target picture and the second target picture, and aligning images in the first target picture and the second target picture according to the matching result;

[0120] The aligned first target picture and the second target picture are merged to obtain the target pictures of each target perspective of the first player in the game.

[0121] Preferably, the game screen generating device is applied to an in-vehicle game, and the device further comprises a display module, and the display module is used to:

[0122] The target images of each target perspective are rendered respectively onto the vehicle-mounted screen of the corresponding perspective for display.

[0123] In the specific implementation, the working principle, control process and technical effect achieved by the game screen generation device provided in the embodiment of the present invention are the same as those of the game screen generation method in the above embodiment, and will not be repeated here.

[0124] See also Figure 3 , Figure 3 3 is a schematic diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 301, a memory 302, and a computer program stored in the memory 302 and configured to be executed by the processor 301. When the processor 301 executes the computer program, the game screen generation method described in any of the above embodiments is implemented.

[0125] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory 302 and executed by the processor 301 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0126] The processor 301 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or the processor 301 can be any conventional processor. The processor 301 is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.

[0127] The memory 302 mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory 302 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory 302 can also be other volatile solid-state storage devices.

[0128] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 3 The structural diagram is only an example of the above-mentioned terminal device and does not constitute a limitation of the above-mentioned terminal device. It may include more or less components than shown in the figure, or combine certain components, or different components.

[0129] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the game screen generation method described in any of the above embodiments.

[0130] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, the game screen generation method described in any of the above embodiments is implemented.

[0131] The embodiments of the present invention provide a method, device, equipment, medium and computer program product for generating a game screen, which obtains the game screen of a first player and the game screen of at least one second player in a game; and generates target screens of the first player at various target perspectives in the game according to the game screen of the first player and the game screen of the second player. The embodiments of the present invention provide a wider field of view and richer scene content by expanding the game screen from a single perspective screen to multiple perspective screens, greatly enhancing the user's immersive experience, improving the accuracy and responsiveness of game interaction, and enabling players to interact with game content more intuitively and naturally.

[0132] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0133] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a game screen, characterized in that: include: Acquire a game screen of a first player and a game screen of at least one second player in the game; According to the game screen of the first player and the game screen of the second player, a target screen of the first player at each target perspective in the game is generated.

2. The game screen generation method according to claim 1, characterized in that: The game screen includes a single-view screen, and generating target screens of the first player at each target viewpoint in the game according to the game screen of the first player and the game screen of the second player includes: Feature extraction and feature matching are performed on the single-perspective picture of the first player and the single-perspective picture of the second player to generate a first target picture of each target perspective of the first player in the game, wherein the target picture includes the first target picture.

3. The game screen generation method according to claim 1, characterized in that: The game screen includes a multi-perspective screen, and generating a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes: The multi-perspective screen of the first player and the multi-perspective screen of the second player are identified and segmented to generate a second target screen of the first player at each target perspective in the game, wherein the target screen includes the second target screen.

4. The game screen generation method according to claim 1, characterized in that: The game screen includes a single-perspective screen and a multi-perspective screen, and generating a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player includes: Performing feature extraction and feature matching on the single-view picture of the first player and the single-view picture of the second player to generate a first target picture of each target view; Identifying and segmenting the multi-perspective images of the first player and the multi-perspective images of the second player to generate second target images of the target perspectives; The first target screen and the second target screen of each corresponding target perspective are integrated to obtain the target screen of each target perspective of the first player in the game.

5. The game screen generation method according to claim 2 or 4, characterized in that: The extracting and matching features of the first player's single-view picture and the second player's single-view picture to generate first target pictures of the target viewpoints includes: Calculating the position of the second player relative to the first player according to the single-view picture of the first player and the single-view picture of the second player, so as to determine the target view corresponding to the single-view picture of the second player; Feature extraction and feature matching are performed on the single-perspective picture of the first player and the single-perspective picture of the second player, and a transformation matrix is ​​calculated, and the single-perspective picture of the second player is converted into the first target picture of the target perspective according to the transformation matrix.

6. The game screen generation method according to claim 5, characterized in that: The step of extracting and matching features of the first player's single-view picture and the second player's single-view picture, and calculating a transformation matrix, and converting the second player's single-view picture into the first target picture of the target perspective according to the transformation matrix, comprises: Extracting features from the single-view picture of the first player and the single-view picture of the second player respectively to obtain a plurality of first feature points and a plurality of second feature points; Perform feature matching on the first feature point and the second feature point to obtain a plurality of matching feature point pairs; For each of the matching feature point pairs, calculating a transformation matrix; The pixels in the single-view picture of the second player are mapped to the picture corresponding to the target view of the first player according to the transformation matrix to obtain the first target picture of the target view.

7. The game screen generation method according to claim 3 or 4, characterized in that: The identifying and segmenting the multi-perspective picture of the first player and the multi-perspective picture of the second player to generate the second target picture of each target perspective includes: Performing multi-dimensional feature extraction and feature similarity calculation on the multi-perspective images of the first player and the multi-perspective images of the second player; Dividing pixels in the multi-perspective picture of the first player and the multi-perspective picture of the second player into clusters corresponding to the pictures of each target perspective according to the feature similarity; A segmentation plane is determined based on the clustering result, and the multi-perspective picture of the first player and the multi-perspective picture of the second player are divided into pictures of each target perspective according to the segmentation plane to generate a second target picture of each target perspective.

8. The game screen generation method according to claim 4, characterized in that: The step of integrating the first target screen and the second target screen of each corresponding target perspective to obtain the target screen of each target perspective of the first player in the game comprises: Extracting and matching feature points of the first target picture and the second target picture, and aligning images in the first target picture and the second target picture according to the matching result; The aligned first target picture and the second target picture are merged to obtain the target pictures of each target perspective of the first player in the game.

9. The method for generating a game screen according to any one of claims 1 to 4 and 8, characterized in that: The game screen generation method is applied to in-vehicle games, and the method further includes: The target images of each target perspective are rendered respectively onto the vehicle-mounted screen of the corresponding perspective for display.

10. A game screen generating device, characterized in that: include: A screen acquisition module, used to acquire a game screen of a first player and a game screen of at least one second player in the game; The screen generation module is used to generate a target screen of each target perspective of the first player in the game according to the game screen of the first player and the game screen of the second player.

11. A terminal device, characterized in that: It includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is configured to be executed by the processor, and when the processor executes the computer program, the game screen generation method as described in any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the game screen generation method as described in any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The computer program product includes a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, the game screen generation method as described in any one of claims 1 to 9 is implemented.

Images