Data processing method and system, vehicle, storage medium and program product
By dividing the occupied grid array into grid groups and utilizing run-length encoding, the problem of low compression efficiency of the occupied grid is solved, achieving efficient data compression and improved rendering effects.
Patent Information
- Application Number
- CN202511215863.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-28
- Publication Date
- 2025-10-28
AI Technical Summary
In existing technologies, the compression efficiency of the grid is low and the compression effect is poor, resulting in high resource consumption and affecting the rendering efficiency of vehicle intelligent assisted driving systems.
The occupied grid array is divided into multiple grid groups. The state value is determined based on the occupancy information of the grid group and encoded using travel coding before being sent to the cockpit system for rendering.
By formatting the state values of the grid group, the amount of data is reduced, compression efficiency and rendering real-time performance are improved, resource consumption is reduced, and rendering effects are enhanced.
Smart Images
Figure CN120852707A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of battery technology, specifically to a battery charging and discharging control method and device, a battery management system, and electronic equipment. Background Technology
[0002] Occupancy grids (OG) are a method of representing environmental information using multiple small grids, each recording whether it is occupied and what kind of object occupies it. Occupancy grids are widely used in path planning, obstacle avoidance, and road surface rendering.
[0003] In related technologies, within the electronic and electrical architecture of a vehicle, the occupancy grid is typically generated by the vehicle's intelligent driver assistance system and then sent to the cockpit system for rendering. The original occupancy grid data is generally quite large, and direct transmission would consume significant resources. Currently, it is usually encoded row-wise or column-wise, which suffers from low compression efficiency and poor compression results. Summary of the Invention
[0004] One objective of this application is to provide a data processing method to solve the problems of low compression efficiency and poor compression effect in related technologies; another objective is to provide a data processing system; a third objective is to provide a vehicle; a fourth objective is to provide a computer-readable storage medium; and a fifth objective is to provide a computer program product.
[0005] To achieve the above objectives, this application provides a data processing method applied to an intelligent assisted driving system for vehicles, and the technical solution adopted is as follows:
[0006] Based on the road information surrounding the vehicle, an occupation grid array is generated;
[0007] The occupied grid array is divided into multiple grid groups, and each grid group includes multiple grids;
[0008] For each grid group, the state value of the grid group is determined based on the occupancy information of each grid in the grid group;
[0009] Using run-length encoding, the state value of each grid group is encoded to obtain encoded information;
[0010] The rendering information is sent to the vehicle's cockpit system for rendering. The rendering information includes the encoding information and the mesh information. The mesh information includes the resolution of the occupied mesh array, the resolution of the mesh group, and the traversal method of the travel encoding. The traversal method of the travel encoding includes row traversal or column traversal.
[0011] Based on the aforementioned technical methods, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grids can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Secondly, replacing the occupancy information of multiple grids with the state value of the grid group greatly reduces the data volume, thus achieving a high compression ratio and improving compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value through run-length encoding can further improve the compression ratio and efficiency.
[0012] Furthermore, dividing the occupied grid array into multiple grid groups includes: determining the division size based on the resolution of the occupied grid array; and dividing the occupied grid array into the multiple grid groups according to the division size.
[0013] Based on the aforementioned technical means, the partition size is determined according to the resolution of the occupied grid array, which improves the rationality and accuracy of the partition size compared to a fixed size.
[0014] Furthermore, determining the state value of the grid group based on the occupancy information of each grid in the grid group includes: for each grid in the grid group, determining the type of the grid based on the occupancy information of the grid; determining a first quantity based on the type of each grid; wherein the first quantity is the number of first type grids in the grid group; and determining the state value of the grid group based on the first quantity.
[0015] Based on the aforementioned technical methods, on the one hand, determining the grid type based on grid occupancy information improves the accuracy of grid type identification; on the other hand, determining the grid group's state value by statistically analyzing the number of first-type grids not only formats the grid group's occupancy state but also simplifies the method of determining the state value. Compared to determining the state value through complex algorithms and models, this reduces data redundancy and computational overhead, thus improving processing speed. Furthermore, since this state value stably reflects the overall trend of the grid group, it enhances noise resistance.
[0016] Furthermore, the grid occupancy information includes occupancy state and occupancy type. The occupancy state indicates whether the grid is occupied, and the occupancy type indicates the type of the occupying object corresponding to the grid. Determining the grid type based on the grid occupancy information includes: when the grid's occupancy state is a first occupancy state and the grid's occupancy type is not a preset type, using a first type of grid as the grid type; wherein, the first occupancy state indicates that the grid is occupied; when the grid's occupancy state is a second occupancy state and / or the grid's occupancy type is a preset type, using a second type of grid as the grid type; wherein, the second occupancy state indicates that the grid is not occupied.
[0017] Based on the aforementioned technical means, determining the grid type according to the grid's occupancy status and occupancy type can mitigate the impact of local misjudgments, avoid noise interference, and improve the reliability and accuracy of the grid type.
[0018] Further, determining the state value of the grid group based on the first quantity includes: when the first quantity is less than a preset first threshold, using a first state value as the state value of the grid group; when the first quantity is not less than a preset second threshold, using a second state value as the state value of the grid group; wherein the second threshold is greater than the first threshold; when the first quantity is not less than the first threshold and the first quantity is less than the second threshold, obtaining the state values of at least two target grid groups adjacent to the grid group, and determining the state value of the grid group based on the state value of each target grid group.
[0019] Based on the aforementioned technical methods, the state values of the grid group are divided by comparing a first quantity with two thresholds. On the one hand, this achieves the formatting of multiple state values for the grid group, which, compared to binarization, can more accurately reflect the occupancy information of each grid, improving the granularity and adaptability of state division. On the other hand, the dual-threshold design can buffer the impact of data fluctuations, avoid frequent jumps near the critical point, significantly reduce the misjudgment rate, and thus improve robustness and stability. Furthermore, by integrating the state values of neighboring grid groups to determine the state value of the current grid group, the state value of this grid group can more accurately reflect the local environmental characteristics, avoid biases caused by isolated judgments, and improve the accuracy of state representation and context awareness.
[0020] Further, determining the state value of a grid group based on the state value of each target grid group includes: determining a second number of target grid groups for each state value based on the state value of each target grid group; if the maximum second number is greater than a third threshold, using the state value of the maximum second number as the state value of the grid group; wherein the third threshold is determined based on the number of target grid groups; if the maximum second number is not greater than the third threshold, determining the state value of the grid group based on the type and position information of each grid in the grid group.
[0021] Based on the above technical means, on the one hand, the state value of the grid group is determined by comparing the maximum number of the same state value in adjacent grid groups with the third threshold, which can effectively buffer the influence of local noise or misjudgment and improve the accuracy of the state value; on the other hand, when the maximum second number is not greater than the third threshold, the state value of the grid group is further determined based on the type and location information of each grid to ensure the reliability and accuracy of the state value of the grid group.
[0022] Furthermore, determining the state value of the grid group based on the first quantity includes: when the first quantity is less than a preset fourth threshold, using the first state value as the state value of the grid group; and when the first quantity is not less than the fourth threshold, using the second state value as the state value of the grid group.
[0023] Based on the above technical means, by comparing the first quantity with the fourth threshold to determine the state value of the grid group, on the one hand, the state value of the grid group is binarized, providing clear boundary conditions, making the state value recognition more interpretable and reducing ambiguity interference; on the other hand, the calculation process of the state value is simplified, and the algorithm complexity is significantly reduced.
[0024] A data processing method, applied to a vehicle's cockpit system, includes:
[0025] The system receives rendering information sent by the vehicle's intelligent assisted driving system. The rendering information includes encoding information and grid information. The encoding information is obtained by encoding the state values of multiple grid groups using travel coding. The multiple grid groups are obtained by dividing an occupied grid array generated based on road information surrounding the vehicle. The state value of each grid group is determined based on the occupancy information of each grid in the grid group. The grid information includes the resolution of the occupied grid array, the resolution of the grid group, and the travel coding traversal method. The travel coding traversal method includes row traversal or column traversal.
[0026] Render the road information around the vehicle according to the rendering information.
[0027] Based on the aforementioned technical methods, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grids can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Secondly, replacing the occupancy information of multiple grids with the state value of the grid group greatly reduces the data volume, thus achieving a high compression ratio and improving compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value through run-length encoding can further improve the compression ratio and efficiency.
[0028] A data processing system, applied in a vehicle, includes an intelligent driver assistance system and a cockpit system, wherein:
[0029] The intelligent assisted driving system is used to generate an occupancy grid array based on road information around the vehicle; divide the occupancy grid array into multiple grid groups, each grid group including multiple grids; for each grid group, determine the state value of the grid group based on the occupancy information of each grid in the grid group; encode the state value of each grid group using trip coding to obtain coded information; and send rendering information to the cockpit system, the rendering information including the coded information and grid information, the grid information including the resolution of the occupancy grid array, the resolution of the grid group, and the traversal method of the trip coding, the traversal method of the trip coding including row traversal or column traversal.
[0030] The cockpit system is used to receive the rendering information and render road information around the vehicle according to the rendering information.
[0031] Based on the aforementioned technical methods, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grids can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Secondly, replacing the occupancy information of multiple grids with the state value of the grid group greatly reduces the data volume, thus achieving a high compression ratio and improving compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value through run-length encoding can further improve the compression ratio and efficiency.
[0032] A vehicle includes a processor and a memory, the memory storing a computer program executable on the processor, the processor executing the computer program to implement any of the methods described above.
[0033] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in any of the preceding claims.
[0034] A computer program product includes a computer program or instructions that, when executed by a processor, implement the method described in any of the preceding claims.
[0035] The beneficial effects of this application are:
[0036] (1) The partition size is determined based on the resolution of the grid array, which improves the rationality and accuracy of the partition size compared to a fixed size.
[0037] (2) Determining the grid type based on the grid's occupancy status and grid occupancy type can alleviate the impact of local misjudgment and avoid noise interference, thereby improving the reliability and accuracy of the grid type.
[0038] (3) The state values of the grid group are divided by comparing the first quantity with two thresholds. First, the formatting of multiple state values of the grid group is realized. Compared with binarization, it can more accurately reflect the occupancy information of each grid, improving the precision and adaptability of state division. Second, the dual threshold design can buffer the impact of data fluctuations, avoid frequent jumps near the critical point, significantly reduce the misjudgment rate, and thus improve robustness and stability. Third, the method of determining state values is simplified. Compared with determining state values through complex algorithms and models, it reduces data redundancy and computational overhead, and improves processing speed. Finally, since the state value can stably reflect the overall trend of the grid group, the noise resistance is improved.
[0039] (4) When the first quantity is between two thresholds, the state value of the current grid group is determined by integrating the state values of neighboring grid groups, so that the state value of the grid group can more accurately reflect the local environmental characteristics, avoid the deviation caused by isolated judgment, effectively buffer the influence of local noise or misjudgment, and improve the accuracy of state representation and context awareness.
[0040] (5) When the maximum second quantity is not greater than the third threshold, the state value of the grid group is further determined according to the type and location information of each grid to ensure the reliability and accuracy of the state value of the grid group.
[0041] (6) By comparing the first quantity with the fourth threshold to determine the state value of the grid group, on the one hand, the state value of the grid group is binarized, providing clear boundary conditions, making the state value recognition more interpretable and reducing ambiguity interference; on the other hand, the calculation process of the state value is simplified, and the algorithm complexity is significantly reduced.
[0042] (7) By formatting each grid group into a state value, on the one hand, the noise or burrs of the original grid can be eliminated. Compared with the additional noise reduction of the grid data, this greatly reduces resource consumption and improves the real-time performance of rendering. On the other hand, it can also improve the continuity of each grid, thereby improving the subsequent rendering effect.
[0043] (8) The state values of the grid group are used to replace the occupancy information of multiple grids, which greatly reduces the amount of data, thereby achieving a high compression ratio and improving compression efficiency.
[0044] (9) Since run-length encoding can compress a large amount of data with consecutive repetitive elements, encoding each state value through run-length encoding can further improve the compression ratio and compression efficiency. Attached Figure Description
[0045] Figure 1 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 1 ;
[0046] Figure 2 A schematic diagram of the state values of a grid group provided in an embodiment of this application. Figure 1 ;
[0047] Figure 3 A schematic diagram of the state values of a grid group provided in an embodiment of this application. Figure 2 ;
[0048] Figure 4 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 2 ;
[0049] Figure 5 A schematic diagram of the composition structure of a data processing system provided in this application embodiment. Figure 1 ;
[0050] Figure 6 A schematic diagram of the composition structure of a data processing system provided in this application embodiment. Figure 2 . Detailed Implementation
[0051] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.
[0052] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0053] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.
[0054] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.
[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.
[0056] The method provided in this application can be executed by an electronic device, which can be a laptop, tablet, desktop computer, vehicle, set-top box, mobile device (e.g., mobile phone, portable music player, personal digital assistant, dedicated messaging device, portable gaming device), or a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.
[0057] The technical solutions in the embodiments of this application will now be clearly and completely described with reference to the accompanying drawings.
[0058] Figure 1 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 1 It is applied to intelligent driver assistance systems in vehicles, such as Figure 1 As shown, the method includes steps S11 to S15, wherein:
[0059] Step S11: Generate an occupied grid array based on the road information around the vehicle.
[0060] Here, the vehicle includes at least an Advanced Driving Assistance System (ADAS) and a cockpit system. ADAS uses sensors, cameras, radar, and other equipment onboard to perceive the surrounding environment in real time and uses algorithms to control the vehicle's driving status, assisting the driver in completing some driving tasks. The cockpit system is a core component of the vehicle, integrating various technologies to achieve human-machine interaction, environmental perception, and proactive service functions, providing an intelligent experience for the driver and passengers.
[0061] Road information can include road attribute information and road dynamic information. Road attribute information may include, but is not limited to, road type, width, and lane markings. Road dynamic information may include, but is not limited to, lane number changes and construction status. The method of acquiring this road information can be any suitable method. In some implementations, road information sent by other systems or devices can be received. In some implementations, the road information is acquired through an ADAS perception module. This perception module can be any suitable module capable of performing this function, and it may include multiple sensors to acquire road information.
[0062] An occupied grid array consists of multiple rows and columns; it can also be called a grid map or raster map. For example, if the resolution of the occupied grid array is 1200*400, then the occupied grid array includes 1200 rows * 400 columns of OGs. The number of rows and columns in the occupied grid array can be the same or different.
[0063] The occupancy grid array can be generated in any suitable manner. In some implementations, spatial discretization followed by attribute mapping can yield the occupancy grid array. Spatial discretization involves dividing the road space surrounding the vehicle into multiple regular grids according to the resolution of the occupancy grid array. Attribute mapping refers to mapping road information onto the corresponding grids. In some implementations, road information can also be input into a preset neural network model to obtain the occupancy grid array; this neural network model can be a model capable of performing this function.
[0064] Step S12: Divide the occupied grid array into multiple grid groups, each grid group including multiple grids.
[0065] Here, the resolution of the grid group can be any suitable resolution, such as 400*400, 600*300, etc. The number of rows and columns of the grid group can be the same or different.
[0066] The partition size of the grid array can be any suitable size. This partition size characterizes the resolution of the grid group. This partition size can be preset or dynamically set.
[0067] In some embodiments, step S12 includes steps S121 and S122, wherein:
[0068] Step S121: Determine the partition size based on the resolution of the occupied grid array;
[0069] Step S122: Divide the occupied grid array into multiple grid groups according to the division size.
[0070] Here, the resolution of the occupies the grid array can be M*N, where M and N are both positive integers, and M and N can be the same or different. In some implementations, if the partition size is K*K, then K can be a common divisor of M and N, and the number of grid groups is (M*N) / (K*K). For example, if M is 1600 and N is 400, then K can be 400, that is, the partition size is 400*400, and the number of grid groups is 4. In implementation, the occupies the grid array evenly divided according to this partition size to obtain multiple grid groups.
[0071] In this embodiment, the partition size is determined based on the resolution of the occupied grid array, which improves the rationality and accuracy of the partition size compared to a fixed size.
[0072] Step S13: For each grid group, determine the state value of the grid group based on the occupancy information of each grid in the grid group.
[0073] Here, the grid occupancy information may include, but is not limited to, occupancy status and occupancy type. Occupancy status indicates whether the grid is occupied. Occupancy status may include, but is not limited to, a first occupancy status and a second occupancy status. The first occupancy status indicates that the grid is occupied, and the second occupancy status indicates that the grid is not occupied. Occupancy type indicates the type of the object occupying the grid. Occupancy type may include, but is not limited to, a first occupancy type and a second occupancy type. The first occupancy type indicates that the object occupying the grid is an object in a preset whitelist, which records information about objects that can be included in the same row area. The second occupancy type indicates that the object occupying the grid is not an object in the whitelist.
[0074] The state values of a grid group can include, but are not limited to, a first state value and a second state value. The first state value can be any suitable value that indicates the grid group is a passable area, for example, 0. The second state value can be any suitable value that indicates the grid group is an impassable area, for example, 1.
[0075] In some implementations, the state values of the grid group may include, but are not limited to, a third state value, a fourth state value, a fifth state value, and a sixth state value. The third state value can be any suitable value that indicates the upper right corner of the grid group is an impassable area. For example, 2, where the upper right corner being an impassable area means that all grids in the first row of the grid group are of type 1, and the number of type 2 grids increases by one in each subsequent row. Type 1 grids are occupied grids, and type 2 grids are unoccupied grids. The fourth state value can be any suitable value that indicates the upper left corner of the grid group is an impassable area. For example, 3, where the upper left corner being an impassable area means that all grids in the first row of the grid group are of type 1, and the number of type 2 grids increases by one in each subsequent row. The fifth state value can be any suitable value that indicates the lower left corner of the grid group is an impassable area. For example, 4, where the lower left corner being an impassable area means that all grids in the last row of the grid group are of type 1, and the number of type 2 grids increases by one in each subsequent row. The sixth state value can be any suitable value that indicates that the bottom right corner of the grid group is an impassable area. For example, 5 means that all grids in the last row of the grid group are of type 1, and the number of type 2 grids in each row above increases by 1 from front to back.
[0076] The state value of the grid group can be determined in any suitable way. In some embodiments, a correspondence between the occupancy information of each grid and the state value of each grid group can be established in advance. Based on this correspondence, a state value that matches the occupancy information of each grid can be obtained. In some embodiments, the state value of the grid group can be determined based on the number of first-type grids in the grid group. For example, if the number of first-type grids is not less than a set threshold, then the second state value is used as the state value of the grid group; otherwise, the first state value is used as the state value of the grid group. In some embodiments, the state value of the grid group can be determined based on the state values of each adjacent grid group in the grid group.
[0077] like Figure 2 As shown, since the resolution of the original occupied grid array 21 is 6*6, the partition size can be 3*3. The original occupied grid array 21 is divided into 4 grid groups according to 3*3, namely: grid group 221 to 224. The state value of grid group 221 and the state value of grid group 224 are both the second state value 1, the state value of grid group 222 is the first state value 0, and the state value of grid group 223 is the third state value 2.
[0078] Step S14: Use run-length encoding to encode the state value of each grid group to obtain encoded information.
[0079] Here, Run-Length Encoding (RLE) is a simple data compression technique primarily used to compress data containing a large number of consecutive repeating elements. Its basic idea is to traverse the data row by row or column by column, replacing consecutive identical data elements with a combination of a starting value and a count value of the same consecutive type. RLE traversal methods can include row traversal, column traversal, etc. In some implementations, based on the characteristics of the road conditions, passable areas are usually parallel to the vehicle, and there are impassable areas such as medians, pedestrian crossings, and green belts in the driving environment. These areas are also generally parallel to the vehicle and are column-continuous. Therefore, column traversal usually achieves a higher compression ratio. Thus, this application defaults to using column traversal for compression encoding. It is understood that this application also supports row traversal compression.
[0080] In implementation, this application performs RLE encoding on the occupancy status values of each grid group. Each occupied grid group is traversed sequentially using either row or column traversal. The starting grid group number and the number of consecutive grid groups with the same status value are recorded as a grid group occupancy status pair. All grid group occupancy status pairs are recorded and used as the encoded information.
[0081] Step S15: Send the rendering information to the vehicle's cockpit system for rendering. The rendering information includes encoding information and mesh information. The mesh information includes the resolution of the occupied mesh array, the resolution of the mesh group, and the traversal method of the travel encoding. The traversal method of the travel encoding includes row traversal or column traversal.
[0082] Here, mesh information can be sent to the cockpit system as header information, and encoded information can be sent as data (or main body). It is understandable that the intelligent driver assistance system can send rendering information to the cockpit system, and the cockpit system can also read this rendering information from the intelligent driver assistance system.
[0083] After receiving the rendering data, the cockpit system first decompresses the data portion based on the header information, then reconstructs the original occupancy grid array according to the grid group resolution and the occupancy grid array resolution before rendering. In some implementations, high-static map data, occupancy grid arrays, and perception information can be fused to achieve accurate rendering of lane lines across the entire scene. In some implementations, a suitable rendering engine can be invoked to perform real-time rendering based on the occupancy grid array, weather, water accumulation, etc.
[0084] In this embodiment, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grid can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Thirdly, using the state value of the grid group to replace the occupancy information of multiple grids greatly reduces the data volume, achieving a high compression ratio and improved compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value using run-length encoding can further improve the compression ratio and efficiency.
[0085] In some implementations, step S13, "determining the state value of the grid group based on the occupancy information of each grid in the grid group," includes steps S131 to S133, wherein:
[0086] Step S131: For each grid in the grid group, determine the grid type based on the grid's occupancy information.
[0087] Here, the type of grid can include, but is not limited to, type I grid, type II grid, etc. Type I grid refers to occupied grids, and type II grid refers to unoccupied grids.
[0088] The type of the grid can be determined in any suitable way. In some implementations, a correspondence between each occupancy information and each type can be established in advance, and the type that matches the occupancy information can be obtained based on this correspondence.
[0089] In some implementations, the grid occupancy information includes occupancy state and occupancy type. The occupancy state indicates whether the grid is occupied, and the occupancy type indicates the type of the occupying object corresponding to the grid. Step S131, "determining the grid type based on the grid occupancy information," includes steps S1311 and S1312, wherein:
[0090] Step S1311: When the grid's occupation state is the first occupation state and the grid's occupation type is not a preset type, the first type of grid is taken as the grid type; wherein, the first occupation state indicates that the grid is occupied;
[0091] Step S1312: When the grid occupancy state is the second occupancy state and / or the grid occupancy type is a preset type, the second type of grid is taken as the grid type; wherein, the second occupancy state indicates that the grid is not occupied.
[0092] Here, the default type refers to the first occupancy type. In implementation, if a grid is occupied and the object occupying the grid is not in the whitelist, the grid is considered to be of type first. If a grid is occupied and the object occupying the grid is in the whitelist, or if the grid is not occupied, the grid is considered to be of type second.
[0093] In this way, determining the grid type based on the grid's occupancy status and occupancy type can mitigate the impact of local misjudgments, avoid noise interference, and improve the reliability and accuracy of the grid type.
[0094] Step S132: Determine the first quantity based on the type of each grid.
[0095] Here, the first count refers to the number of first-type grids in the grid group. During implementation, when traversing the grid group, the count is incremented by 1 when a grid is a first-type grid. After the traversal is complete, this count is used as the first count. It's understandable that before the traversal, this count is 0.
[0096] Step S133: Determine the state value of the grid group based on the first quantity.
[0097] Here, the state value can be determined in any suitable way.
[0098] In some embodiments, step S133 includes steps S1331 and S1332, wherein:
[0099] Step S1331: If the first quantity is less than the preset fourth threshold, the first state value is used as the state value of the grid group.
[0100] Step S1332: If the first quantity is not less than the fourth threshold, the second state value is used as the state value of the grid group.
[0101] Here, the fourth threshold can be any suitable value. For example, the fourth threshold can be greater than half the total number of grids contained in the grid group. In implementation, when the number of first-type grids in the grid group exceeds half, the grid group is considered an impassable area, and the second state value can be used as the state value of the grid group; when the number of first-type grids in the grid group is less than half, the grid group is considered a passable area, and the first state value can be used as the state value of the grid group.
[0102] In this way, by comparing the first quantity with the fourth threshold to determine the state value of the grid group, on the one hand, the state value of the grid group is binarized, providing clear boundary conditions, making the state value recognition more interpretable and reducing ambiguity interference; on the other hand, the calculation process of the state value is simplified, significantly reducing the algorithm complexity.
[0103] In some implementations, a correspondence between each first quantity and each state value can be established in advance. Based on this correspondence, a state value that matches the first quantity can be obtained.
[0104] In this embodiment, on the one hand, the grid type is determined based on the grid occupancy information, improving the accuracy of the grid type; on the other hand, the state value of the grid group is determined by counting the number of first-type grids in the grid group. This not only achieves the formatting of the grid group's occupancy state but also simplifies the method of determining the state value. Compared to determining the state value through complex algorithms and models, this reduces data redundancy and computational overhead, and improves processing speed. Furthermore, since this state value can stably reflect the overall trend of the grid group, it enhances noise resistance.
[0105] In some embodiments, step S133 includes steps S1331 to S1333, wherein:
[0106] Step S1331: If the first quantity is less than a preset first threshold, the first state value is used as the state value of the grid group.
[0107] Step S1332: If the first quantity is not less than the preset second threshold, the second state value is used as the state value of the grid group.
[0108] Step S1333: When the first quantity is not less than the first threshold and the first quantity is less than the second threshold, obtain the state values of at least two target grid groups adjacent to the grid group, and determine the state value of the grid group based on the state value of each target grid group.
[0109] Here, the second threshold is greater than the first threshold. The second threshold and the first threshold can be any suitable value. The first threshold refers to the communicable area threshold, and the second threshold is the impassable threshold.
[0110] The state values of the grid group may include, but are not limited to, the first state value, the second state value, and other state values.
[0111] When the number of first-class grids in a grid group is not less than the second threshold, the grid group is considered to be an impassable area. In this case, the second state value can be used as the state value of the grid group.
[0112] When the number of first-type grids in a grid group is less than the first threshold, the grid group is considered a passable area, and the first state value can be used as the state value of the grid group.
[0113] When the number of first-type grids in a grid group is not less than a first threshold and less than a second threshold, it cannot be determined whether the grid group is a passable area. In this case, the grid group can be added to the pending state list. After traversing all grid groups, if the pending list is not empty, each grid group in the pending list is processed sequentially. In implementation, the state value of a grid group can be determined based on the state values of each adjacent grid group. In some implementations, the number of state values of each adjacent grid group is counted, and the state value of the grid group is determined based on the number of each state value. For example, if the number of a certain state value exceeds half the number of adjacent grid groups, then that state value is taken as the state value of the grid group; if the number of each state is less than half the number of adjacent grid groups, then the state value of the grid group can be further determined based on the type and position information of each grid in the grid group.
[0114] In this embodiment, the state values of the grid group are divided by comparing a first quantity with two thresholds. On the one hand, this achieves the formatting of multiple state values for the grid group, which, compared to binarization, can more accurately reflect the occupancy information of each grid, improving the fineness and adaptability of state division. On the other hand, the dual-threshold design can buffer the impact of data fluctuations, avoid frequent jumps near the critical point, significantly reduce the misjudgment rate, and thus improve robustness and stability. Furthermore, by integrating the state values of neighboring grid groups to determine the state value of the current grid group, the state value of this grid group can more accurately reflect the local environmental characteristics, avoid bias caused by isolated judgments, and improve the accuracy of state representation and context awareness.
[0115] In some implementations, the step S1333, "determining the state value of a grid group based on the state value of each target grid group," includes steps S161 to S163, wherein:
[0116] Step S161: Based on the state value of each target grid group, determine the second number of target grid groups for each state value;
[0117] Step S162: If the maximum second quantity is not less than the third threshold, take the state value of the maximum second quantity as the state value of the grid group; wherein, the third threshold is determined based on the number of the target grid group.
[0118] Step S163: If the maximum second quantity is less than the third threshold, determine the state value of the grid group based on the type and position information of each grid in the grid group.
[0119] Here, the second quantity matches the number of state values. For example, if the target mesh group has 4 members, and 3 of them have the same state value, then the second quantity is two. It can be understood that the target mesh group has no more than 4 members, and the target mesh group can be located above, below, to the left, or to the right of other mesh groups.
[0120] The third threshold can be no less than half the number of target grid groups. For example, if there are 4 target grid groups, the third threshold can be 3, 4, etc.; if there are 3 target grid groups, the third threshold can be 2, 3, etc.
[0121] During implementation, the number of state values for each target grid group is counted, and the largest number is compared with a third threshold. If the largest number is not less than the third threshold, the state value with the largest number is taken as the state value of that grid group; otherwise, the state value of the grid group is further determined based on the type and location information of each grid. In some implementations, the position of each first-type grid in the grid group is compared with other preset state values to determine the state value of the grid group. During implementation, if each grid in the grid group is completely identical to or has a similarity exceeding a preset similarity threshold with each grid corresponding to a certain state value, then that state value is taken as the state value of the grid group.
[0122] like Figure 3 As shown, for grid group 31, since the state value of 3 out of the 4 grid groups adjacent to grid group 31 is the second state value 1, the state value of grid group 31 can also be the second state value 1.
[0123] For grid group 32, since two of the four grid groups adjacent to grid group 32 have a state value of 0 (first state value) and two have a state value of 1 (second state value), the state value of grid group 32 needs to be further determined based on the type and position of each grid. Since grid group 32 is compatible with the preset third state value, the third state value 2 can be used as the state value of grid group 32.
[0124] For grid group 33, since two of the four grid groups adjacent to grid group 33 have a state value of the first state value 0 and two have a state value of the second state value 1, the state value of grid group 33 needs to be further determined based on the type and position of each grid. Since grid group 33 is compatible with the preset fourth state value, the fourth state value 3 can be used as the state value of grid group.
[0125] In this embodiment, on the one hand, the state value of the grid group is determined by comparing the maximum number of the same state value in adjacent grid groups with a third threshold, which can effectively buffer the influence of local noise or misjudgment and improve the accuracy of the state value; on the other hand, when the maximum second number is not greater than the third threshold, the state value of the grid group is further determined based on the type of each grid and the location information of each grid to ensure the reliability and accuracy of the state value of the grid group.
[0126] Based on the above embodiments, this application also provides a data processing method applied to a vehicle's cockpit system. Figure 4 A schematic diagram of the implementation flow of a data processing method provided in this application embodiment. Figure 2 ,like Figure 4 As shown, the method includes steps S41 and S42, wherein:
[0127] Step S41: Receive rendering information sent by the vehicle's intelligent assisted driving system; wherein, the rendering information includes encoding information and grid information, the encoding information is obtained by encoding the state values of multiple grid groups using travel coding, the multiple grid groups are obtained by dividing the occupied grid array generated based on the road information around the vehicle, the state value of the grid group is determined based on the occupied information of each grid in the grid group, the grid information includes the resolution of the occupied grid array, the resolution of the grid group and the travel coding traversal method, the travel coding traversal method includes row traversal method or column traversal method.
[0128] Here, the cockpit system and the intelligent driver assistance system are connected. The process by which the intelligent driver assistance system generates rendering information can be found in the specific implementation of steps S11 to S14 above.
[0129] Step S42: Render the road information around the vehicle according to the rendering information.
[0130] Here, the cockpit system decodes and restores the rendered information before rendering it. In practice, the process of rendering road information by the cockpit system can be found in the specific implementation of step S15 above.
[0131] In this embodiment, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grid can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Thirdly, using the state value of the grid group to replace the occupancy information of multiple grids greatly reduces the amount of data, thus achieving a high compression ratio and improving compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value through run-length encoding can further improve the compression ratio and compression efficiency.
[0132] Based on the above embodiments, this application also provides a data processing system applied in a vehicle. Figure 5 A schematic diagram of the composition structure of a data processing system provided in this application embodiment. Figure 1 ,like Figure 5 As shown, the data processing system 50 includes an intelligent driver assistance system 51 and a cockpit system 52, wherein:
[0133] The intelligent assisted driving system 51 is used to generate an occupancy grid array based on road information around the vehicle; divide the occupancy grid array into multiple grid groups, each grid group including multiple grids; for each grid group, determine the state value of the grid group based on the occupancy information of each grid in the grid group; use travel coding to encode the state value of each grid group to obtain coded information; and send the rendering information to the cockpit system for rendering. The rendering information includes coded information and grid information. The grid information includes the resolution of the occupancy grid array, the resolution of the grid group, and the traversal method of travel coding. The traversal method of travel coding includes row traversal or column traversal.
[0134] The cockpit system 52 is used to receive rendering information and render road information around the vehicle according to the rendering information.
[0135] Here, ADAS is a system that uses sensors, cameras, radar and other devices on the vehicle to perceive the surrounding environment in real time and use algorithms to control the vehicle's driving status, assisting the driver in completing some driving tasks.
[0136] Road information may include road attribute information, road dynamic information, etc. The occupancy grid array consists of multiple rows and columns. In implementation, the process of generating the occupancy grid array for ADAS can be found in the specific implementation of step S11 above.
[0137] The resolution of the grid group can be any suitable resolution, and the number of rows and columns of the grid group can be the same or different. In implementation, the process of dividing the ADAS grid array can be found in the specific implementation of step S12 above.
[0138] The occupancy information of the grid may include, but is not limited to, occupancy status and occupancy type. The state values of the grid group may include, but are not limited to, a first state value, a second state value, a third state value, a fourth state value, a fifth state value, and a sixth state value. In implementation, the process by which this ADAS determines the state values of the grid group can be found in the specific implementation of step S13 above.
[0139] The basic idea of RLE is to traverse the data row by row or column by column, replacing consecutive identical data elements with a combination of a starting value and a count value of consecutive identical types. In implementation, the process by which this ADAS obtains encoded information can be found in the specific implementation of step S14 above.
[0140] The cockpit system is a core component of the vehicle, integrating various technologies to achieve human-machine interaction, environmental perception, and proactive service functions, providing an intelligent experience for drivers and passengers. The process by which this cockpit system renders road information can be found in the specific implementation of step S15 mentioned above.
[0141] The data processing system is primarily used for processing the occupancy mesh data of road surfaces during scene reconstruction. The entire rendering process involves the intelligent driver assistance system and the cockpit system; the two systems operate independently but communicate via a network. For example... Figure 6 As shown, the data processing system 50 includes an intelligent driver assistance system 51 and a cockpit system 52. The intelligent driver assistance system 51 includes a perception module 511, a post-processing module 512, and an encoding module 513. The cockpit system 52 includes a decoding module 521 and a rendering module 522, wherein:
[0142] The sensing module 511 is responsible for generating the original occupied grid information (corresponding to the aforementioned occupied grid array);
[0143] Post-processing module 512 is responsible for formatting the original occupied grid information to facilitate compression by the encoding module;
[0144] The encoding module 513 is used to compress the data and then send the compressed grid data (corresponding to the aforementioned rendering information) to the cockpit system 52 via the network;
[0145] The decoding module 521 is used to decode and restore the mesh data, and then send the mesh data to the rendering module 522 for rendering.
[0146] In implementation, the main function of the post-processing module 512 is to format the original occupied mesh information, remove noise from the original occupied mesh information, and redetermine the occupancy state of the mesh for easier encoding by the encoding module. The formatting method is as follows: the original M*N mesh is transformed into multiple K*K mesh groups, where K is the common divisor of M and N, and the number of mesh groups is (M*N) / (K*K). After formatting, each mesh group is assigned a specific value (corresponding to the state value of the aforementioned mesh group), which represents the occupancy state of the mesh within the mesh group. Different state values represent specific occupancy states. State value 0 can represent that all meshes in the mesh group are passable, state value 1 represents that all meshes in the mesh group are impassable, and other state values are custom-defined specific occupancy states. Typically, the occupied mesh information output by the perception module 511 is quite rich, including not only whether the mesh is occupied but also information such as the type and height of the occupying object. However, when rendering the road surface, only whether the mesh is passable is of concern. Therefore, the purpose of formatting is to process the occupied mesh in units of mesh groups. The state value of each mesh group after formatting is a known, fixed state. The post-processing module 512 maintains a whitelist, which records information about occupants that can be included in the passable area. It also sets two sets of parameters: a passable area threshold (thres1) and an impassable threshold (thres2). When traversing each grid in a grid group, if a grid is an impassable area and the occupant is not in the whitelist, the accumulated count is incremented by 1. After traversing the entire grid group, the state value of the grid group is determined based on the accumulated count. The following three scenarios are possible:
[0147] 1) If the accumulated count value is less than the passable area threshold thres1, then the grid group is marked as a passable area grid group, that is, the value of all grids in the grid group is 0. The status value of the grid group is also set to 0.
[0148] 2) If the accumulated count value is greater than or equal to the impassable threshold thres2, then the grid group is marked as an impassable area grid group, that is, the value of all grids in the grid group is 1. The state value of the grid group is also set to 1.
[0149] 3) The accumulated count value is greater than or equal to thres1 and less than thres2. At this time, the grid group is added to the pending state list.
[0150] After traversing all grid groups, if the pending linked list is not empty, process the grid groups in the pending linked list sequentially. The processing method is to determine the state value of the grid group based on the state values of the grid groups adjacent to it. For example, if three of the four grid groups above, below, to the left, and to the right of the current grid group share the same state value, then the current grid group is also assigned that state value. The processing rules can be defined and adjusted as needed. The method for determining the state value of a pending grid group is not fixed and can be flexibly adjusted according to the situation in practical applications. Alternatively, the `thres1` and `thres2` parameters can be set so that the state value of the entire grid group can only be 0 or 1.
[0151] After post-processing of the grid, the encoding module 513 performs compression encoding on each grid group. Encoding is performed on the grid group information; this scheme uses run-length encoding (LLE). LLE is a simple data compression technique mainly used to compress data containing a large number of consecutive repetitive elements. Its basic idea is to traverse the data row by row, replacing consecutive identical data elements with a combination of a starting value and a count value of consecutive identical types. Based on the characteristics of the roads where vehicles travel, the traversable areas are usually parallel to the vehicle, and there are impassable areas such as medians, pedestrian crossings, and green belts in the driving environment. These areas are also basically parallel to the vehicle and are also column-continuous. Therefore, traversing in a column-wise manner usually achieves a higher compression ratio, and column-wise traversal is used by default for compression encoding. In addition to column-wise traversal, this application also supports row-wise traversal compression. This scheme chooses to perform RLE encoding on the state values of the grid groups. The grid groups are traversed in row or column order, and the starting grid group number and the number of grid groups with consecutive identical state values are recorded as a grid group occupied state pair. All grid group occupied state pairs are recorded. Sending only the mesh group occupancy status pair to the cockpit renderer is insufficient for accurate cockpit rendering; additional mesh information is needed, such as the resolution of the occupancy mesh array (number of horizontal and vertical grids), the resolution of the mesh group (number of horizontal and vertical grids in the mesh group), and the compression method. This mesh information is sent as header information, and the mesh group occupancy status pair is sent as the data portion, together to the cockpit system 52.
[0152] After receiving the data, the decoding module 521 decompresses the data part according to the header information, restores the original occupied grid size according to the resolution of the grid group and the resolution of the occupied grid array, and sends the data to the rendering module 522 for rendering.
[0153] In this embodiment, firstly, by formatting each grid group into a single state value, noise or glitches in the original occupying grid can be eliminated. Compared to further denoising the grid data, this significantly reduces resource consumption and improves the real-time performance of rendering. Secondly, it also enhances the continuity of each occupying grid, thereby improving subsequent rendering effects. Thirdly, using the state value of the grid group to replace the occupancy information of multiple grids greatly reduces the amount of data, thus achieving a high compression ratio and improving compression efficiency. Finally, since run-length encoding can compress a large amount of data with consecutive repeating elements, encoding each state value through run-length encoding can further improve the compression ratio and compression efficiency.
[0154] It should be noted that, in the embodiments of this application, if the above methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.
[0155] This application also provides a vehicle including a memory and a processor, the memory storing a computer program that can run on the processor, and the processor executing the computer program to implement any of the methods described above.
[0156] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. The computer-readable storage medium can be transient or non-transient.
[0157] This application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement some or all of the steps in any of the above methods. The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.
[0158] It should be noted that, Figure 5 This is a schematic diagram of the hardware entity of an electronic device provided in the embodiments of this application, such as... Figure 5 As shown, the hardware entity of the electronic device 500 includes: a processor 501, a communication interface 502, and a memory 503, wherein:
[0159] Processor 501 typically controls the overall operation of electronic device 500.
[0160] Communication interface 502 enables electronic devices to communicate with other terminals or servers via a network.
[0161] The memory 503 is configured to store instructions and applications executable by the processor 501, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 501 and various modules in the electronic device 500. It can be implemented using flash memory or random access memory (RAM). Data transfer between the processor 501, the communication interface 502, and the memory 503 can be performed via bus 504.
[0162] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0163] The above embodiments are merely preferred embodiments provided to fully illustrate this application, and the scope of protection of this application is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on this application are all within the scope of protection of this application.
Claims
1. A data processing method, characterized in that, Intelligent driver assistance systems applied to vehicles include: Based on the road information surrounding the vehicle, an occupation grid array is generated; The occupied grid array is divided into multiple grid groups, and each grid group includes multiple grids; For each grid group, the state value of the grid group is determined based on the occupancy information of each grid in the grid group; Using run-length encoding, the state value of each grid group is encoded to obtain encoded information; The rendering information is sent to the vehicle's cockpit system for rendering. The rendering information includes the encoding information and the mesh information. The mesh information includes the resolution of the occupied mesh array, the resolution of the mesh group, and the traversal method of the travel encoding. The traversal method of the travel encoding includes row traversal or column traversal.
2. The method according to claim 1, characterized in that, The step of dividing the occupied grid array into multiple grid groups includes: The partition size is determined based on the resolution of the occupied grid array; The occupied grid array is divided into the plurality of grid groups according to the specified division size.
3. The method according to claim 1 or 2, characterized in that, Determining the state value of the grid group based on the occupancy information of each grid in the grid group includes: For each grid in the grid group, the type of the grid is determined based on the grid's occupancy information; Based on the type of each of the grids, a first quantity is determined; wherein, the first quantity is the number of grids of the first type in the grid group; Based on the first quantity, the state value of the grid group is determined.
4. The method according to claim 3, characterized in that, The grid occupancy information includes occupancy status and occupancy type. The occupancy status indicates whether the grid is occupied, and the occupancy type indicates the type of the object occupying the grid. Determining the type of the grid based on its occupancy information includes: When the grid's occupation state is a first occupation state and the grid's occupation type is not a preset type, the first type of grid is taken as the type of the grid; wherein, the first occupation state indicates that the grid is occupied; When the grid's occupancy state is the second occupancy state and / or the grid's occupancy type is a preset type, the second type of grid is taken as the type of the grid; wherein, the second occupancy state indicates that the grid is not occupied.
5. The method according to claim 3, characterized in that, Determining the state value of the grid group based on the first quantity includes: If the first quantity is less than a preset first threshold, the first state value is used as the state value of the grid group; If the first quantity is not less than a preset second threshold, the second state value is used as the state value of the grid group; wherein the second threshold is greater than the first threshold; When the first quantity is not less than the first threshold and the first quantity is less than the second threshold, the state values of at least two target grid groups adjacent to the grid group are obtained, and the state value of the grid group is determined based on the state value of each target grid group.
6. The method according to claim 5, characterized in that, Determining the state value of a grid group based on the state value of each target grid group includes: Based on the state value of each target grid group, determine the second number of target grid groups for each state value; If the maximum second quantity is not less than the third threshold, the state value of the maximum second quantity is taken as the state value of the grid group; wherein, the third threshold is determined based on the quantity of the target grid group; If the maximum second quantity is less than the third threshold, the state value of the grid group is determined based on the type and position information of each grid in the grid group.
7. The method according to claim 3, characterized in that, Determining the state value of the grid group based on the first quantity includes: If the first quantity is less than a preset fourth threshold, the first state value is used as the state value of the grid group; If the first quantity is not less than the fourth threshold, the second state value is used as the state value of the grid group.
8. A data processing method, characterized in that, Applications in vehicle cockpit systems include: The system receives rendering information sent by the vehicle's intelligent assisted driving system. The rendering information includes encoding information and grid information. The encoding information is obtained by encoding the state values of multiple grid groups using travel coding. The multiple grid groups are obtained by dividing an occupied grid array generated based on road information surrounding the vehicle. The state value of each grid group is determined based on the occupancy information of each grid in the grid group. The grid information includes the resolution of the occupied grid array, the resolution of the grid group, and the travel coding traversal method. The travel coding traversal method includes row traversal or column traversal. Render the road information around the vehicle according to the rendering information.
9. A data processing system, characterized in that, Applications in vehicles include intelligent driver assistance systems and cockpit systems, among which: The intelligent assisted driving system is used to generate an occupancy grid array based on road information around the vehicle; divide the occupancy grid array into multiple grid groups, each grid group including multiple grids; for each grid group, determine the state value of the grid group based on the occupancy information of each grid in the grid group; encode the state value of each grid group using trip coding to obtain coded information; and send rendering information to the cockpit system, the rendering information including the coded information and grid information, the grid information including the resolution of the occupancy grid array, the resolution of the grid group, and the traversal method of the trip coding, the traversal method of the trip coding including row traversal or column traversal. The cockpit system is used to receive the rendering information and render road information around the vehicle according to the rendering information.
10. A vehicle, characterized in that, It includes a processor and a memory, the memory storing a computer program that can run on the processor, the processor executing the computer program to implement the method of any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 8.
12. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the method of any one of claims 1 to 8.