Ramp layer generation method and apparatus, high-precision map, and electronic device
By filtering and segmenting the digital terrain model data, high-precision ramp layers are generated, which solves the problem of excessive data volume in driverless vehicles and improves computing efficiency and safety.
Patent Information
- Application Number
- PCT/CN2023/125035
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-01
- Filing Date
- 2023-10-17
- Publication Date
- 2024-12-05
AI Technical Summary
In the prior art, the amount of digital terrain model data is too large, and the calculation time is time-consuming to meet the real-time requirements of unmanned vehicles, affecting driving safety.
By obtaining the digital terrain model data of the work area, filtering and segmenting the data based on the terrain factor at the target resolution, multiple target boundary polygons are extracted as ramp layers, reducing the amount of data and improving calculation accuracy.
It achieves the real-time requirements of unmanned vehicles, ensures driving safety, and optimizes path planning and decision-making control by generating high-precision ramp layers.
Smart Images

Figure CN2023125035_05122024_PF_FP_ABST
Abstract
Description
Ramp layer generation method and device, high-precision map and electronic equipment
[0001] This application claims priority to Chinese patent application No. 2023106356165 filed with the China Patent Office on June 1, 2023, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present disclosure relates to the field of autonomous driving and / or electronic map technology, and in particular to a ramp layer generation method, device, high-precision map, electronic device, and computer-readable storage medium. Background Art
[0003] Open-pit mining involves removing the covering from an ore body to obtain the desired minerals. The production process includes drilling, blasting, mining and loading, transportation, and dumping. With the continuous development of autonomous driving technology, the application of autonomous driving in mining vehicles has emerged. Currently, operations such as loading, transportation, and dumping are mainly performed by autonomous mining vehicles. With the in-depth research of autonomous driving technology in open-pit mines, the demand for high-precision maps in mining areas is increasing. Not only does this require vector maps to achieve centimeter-level accuracy, but they also need to be rapidly updated to accommodate the high-frequency terrain changes caused by mining and loading operations.
[0004] Currently, vehicle-mounted LiDAR collects high-precision, high-density point cloud data of areas with varying terrain. Based on this data, high-resolution Digital Elevation Model (DEM) data is generated for high-precision, high-frequency production and updating of vector maps. Furthermore, based on high-resolution DEM data and the varying needs of autonomous vehicles (e.g., autonomous mining vehicles) with different vehicle parameters, Digital Terrain Model (DTM) data of varying resolutions can be generated to derive terrain factors such as road slope, aspect, and bumpiness.
[0005] In related technologies, to ensure the safety of autonomous vehicles during global or local path planning, in addition to considering obstacle avoidance and path efficiency, factors such as road slope and slope aspect change rate must be considered in conjunction with vehicle dynamics to appropriately limit the speed of the autonomous vehicle. Therefore, it is necessary to reference the slope and aspect terrain factors in the digital terrain model data. However, directly using digital terrain model data cannot meet the real-time requirements of autonomous driving due to excessive data volume and time-consuming calculations, and thus cannot guarantee the safety of autonomous vehicles.
[0006] Summary of the Invention
[0007] In view of this, the embodiments of the present disclosure provide a ramp layer generation method, device, high-precision map, electronic device and computer-readable storage medium to solve the problem in related technologies that the real-time requirements of unmanned driving cannot be met due to the large amount of digital terrain model data and time-consuming calculations.
[0008] In a first aspect of an embodiment of the present disclosure, a ramp layer generation method is provided, comprising: obtaining digital terrain model data of an operating area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; filtering the digital terrain model data based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data; segmenting the target digital terrain model data to obtain multiple target digital terrain model data clusters; and extracting boundaries of the multiple target digital terrain model data clusters to obtain multiple target boundary polygons as a ramp layer.
[0009] In a second aspect of an embodiment of the present disclosure, a ramp layer generation apparatus is provided, comprising: an acquisition module configured to acquire digital terrain model data of an operating area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; a filtering module configured to filter the digital terrain model data based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data; a segmentation module configured to segment the target digital terrain model data to obtain multiple target digital terrain model data clusters; and an extraction module configured to extract boundaries of the multiple target digital terrain model data clusters to obtain multiple target boundary polygons as the ramp layer.
[0010] A third aspect of the embodiments of the present disclosure provides a high-precision map, including a ramp layer generated by the steps of the above method.
[0011] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising at least one processor; and a memory for storing instructions executable by at least one processor; wherein the at least one processor is configured to execute instructions to implement the steps of the above method.
[0012] According to a fifth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the steps of the above method.
[0013] At least one of the above-mentioned technical solutions adopted in the embodiments of the present disclosure can achieve the following beneficial effects: by acquiring digital terrain model data of an operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; filtering the digital terrain model data based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data; segmenting the target digital terrain model data to obtain multiple target digital terrain model data clusters; and performing boundary extraction on the multiple target digital terrain model data clusters to obtain multiple target boundary polygons as ramp layers. The ramp layers can be generated based on the terrain factors in the digital terrain model data. Thus, the data volume of the ramp layers is reduced, the accuracy of the calculation results of the ramp layers is improved, the real-time requirements of unmanned driving are met, and the driving safety of unmanned vehicles is ensured. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0015] FIG1 is a flow chart of a ramp layer generation method provided by an exemplary embodiment of the present disclosure.
[0016] 2a to 2c are schematic diagrams of a filtering process of digital terrain model data provided by an exemplary embodiment of the present disclosure.
[0017] FIG3 is a schematic diagram of boundary extraction of a target digital terrain model data cluster provided by an exemplary embodiment of the present disclosure.
[0018] FIG4 is a schematic diagram of segmenting a target boundary polygon based on slope aspect according to an exemplary embodiment of the present disclosure.
[0019] FIG5 is a flowchart of another ramp layer generation method provided by an exemplary embodiment of the present disclosure.
[0020] FIG6 is a schematic structural diagram of a ramp layer generating device provided by an exemplary embodiment of the present disclosure.
[0021] FIG7 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure.
[0022] FIG8 is a schematic diagram of the structure of a computer system provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0023] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.
[0024] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0025] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0026] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".
[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0028] A method and apparatus for generating a ramp layer according to an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.
[0029] FIG1 is a flow chart of a ramp layer generation method provided by an exemplary embodiment of the present disclosure. The ramp layer generation method of FIG1 can be executed by a server or electronic device in an autonomous driving system or a remote driving system. As shown in FIG1 , the ramp layer generation method includes:
[0030] S101, obtaining digital terrain model data of an operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions;
[0031] S102, filtering the digital terrain model data based on the terrain factors of the digital terrain model data at the target resolution to obtain target digital terrain model data;
[0032] S103, segmenting the target digital terrain model data to obtain multiple target digital terrain model data clusters;
[0033] S104 , performing boundary extraction on multiple target digital terrain model data clusters to obtain multiple target boundary polygons as ramp layers.
[0034] Specifically, taking the server in the autonomous driving system as an example, the server collects point cloud data of the operating area in real time through a data acquisition device installed on the unmanned vehicle, and generates high-resolution digital elevation model data based on the collected point cloud data. This data is used to provide basic terrain data support for high-precision maps, terrain analysis, decision-making and planning in autonomous driving scenarios. During the mining process of open-pit mines, since different types of unmanned vehicles have different vehicle parameters (for example, wheel size, body size, etc.), in order to ensure the safety of unmanned driving, unmanned vehicles can be divided based on type, and the high-resolution digital elevation model data can be divided into equal intervals for different types of unmanned vehicles to obtain digital elevation model data of different resolutions.
[0035] Furthermore, the server generates digital terrain model data of varying resolutions based on the digital elevation model data of varying resolutions. This allows for the use of digital terrain model data of varying resolutions when performing global or local path planning for different types of unmanned vehicles. For example, for unmanned vehicles with relatively small wheels or bodies, relatively high-resolution digital terrain model data can be used; for unmanned vehicles with relatively large wheels or bodies, relatively low-resolution digital terrain model data can be used. This improves the operational efficiency of the unmanned vehicles during driving.
[0036] Here, an autonomous driving system refers to a system composed of hardware and software that can continuously perform some or all dynamic driving tasks. Dynamic driving tasks refer to the perception, decision-making, and execution required to complete vehicle driving. That is, they include all real-time operational and tactical functions when driving a road vehicle, but do not include planning functions such as trip planning, destination and route selection, etc. For example, dynamic driving tasks may include, but are not limited to, controlling the lateral movement of the vehicle, controlling the longitudinal movement of the vehicle, monitoring the driving environment and preparing responses by detecting, identifying, and classifying targets and events, executing responses, driving decisions, and controlling vehicle lighting and signaling devices.
[0037] The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The embodiments of the present disclosure do not limit this.
[0038] An unmanned vehicle refers to a vehicle that senses the vehicle's surroundings through an on-board sensor system, and controls the vehicle's steering and speed based on the road, vehicle position, and obstacle information obtained through the sensing, so that the vehicle can travel safely and reliably on the road. An unmanned vehicle can be a vehicle with data acquisition capabilities and autonomous driving capabilities, or it can be an autonomous driving fleet composed of vehicles with autonomous driving capabilities, and the embodiments of the present disclosure are not limited to this. In the embodiments of the present disclosure, unmanned vehicles can include but are not limited to wide-body vehicles, large mining trucks, collection vehicles, and forklifts equipped with data acquisition devices, and the collection devices can include but are not limited to lidar, millimeter-wave radar, ultrasonic radar, camera, etc.
[0039] Operations can be any social activity that causes changes in the terrain, including but not limited to road construction (affecting the flatness of the ground, etc.), placing objects in a specific area (increasing the height of a certain area), removing objects from a specific area (decreasing the height of a certain area), and activities that cause changes in the road surface topography (concaving or convexing a certain area). For example, earthwork refers to the unloading of excavated materials such as earth and stone into a spoil dump.
[0040] The operating area refers to the area within a mining area where an unmanned vehicle is located during operations such as loading, transporting, and dumping. Specifically, it encompasses the area within which the unmanned vehicle can be located along its travel direction. The operating area can be located in an enclosed space, an open space, or even an unpaved space. For example, an enclosed space can be an open-pit mine. In the disclosed embodiments, the operating area refers to the area within an open-pit mine where an unmanned vehicle is located during operations such as loading, transporting, and dumping.
[0041] A Digital Elevation Model (DEM) is a digital simulation of a terrain surface, or a digital representation of its surface morphology, achieved through a limited set of terrain elevations. This DEM represents terrain features by rasterizing the terrain surface and recording the elevation of each grid point. It serves as fundamental data for various terrain analyses. In this disclosed embodiment, the high-precision DEM data has a resolution of 0.1m, meaning each pixel represents a ground area of 0.1m x 0.1m.
[0042] A Digital Terrain Model (DTM), also known as a digital ground model, describes the spatial distribution of linear and nonlinear combinations of various terrain factors, including elevation, slope, aspect, and slope change rate, and serves as fundamental data for analyzing current land use. The resolution of digital terrain model data can include, but is not limited to, 0.4m, 2.5m, and 5.0m. In the disclosed embodiment, considering that wide-body vehicles commonly used in mining areas generally weigh between 40 and 90 tons, and the length and width of a single wheel are approximately 1.5m and 0.4m, respectively, digital terrain model data with a resolution of 2.5m was selected.
[0043] Next, the server obtains digital terrain model data of the operating area at different resolutions. This data includes terrain factors at different resolutions. Because open-pit mines have complex terrain, typically dominated by unstructured roads, and terrain factors like road slope, aspect, and bumpiness vary significantly across different areas, terrain factors must be considered during early global and local path planning, as well as real-time perception decisions, to ensure safe operation of autonomous vehicles.
[0044] Here, terrain factors are used to describe parameters of terrain, including but not limited to longitude, latitude, altitude, slope, aspect, position, surface roughness, terrain relief, slope shape, etc. Preferably, in the embodiment of the present disclosure, terrain factors include slope and aspect.
[0045] Furthermore, due to abnormal or uneven local terrain, the terrain factors of the area may be abnormal, forming noise points and affecting the subsequent calculation of the ramp layer. Therefore, after obtaining the digital terrain model data, in order to improve the accuracy of the digital terrain model data, the server filters the digital terrain model data based on the terrain factors of the digital terrain model data at the target resolution (i.e., filters out noise points in the digital terrain model data) to obtain target digital terrain model data, and then segments the obtained target digital terrain model data to obtain multiple target digital terrain model data clusters. Here, the target digital terrain model data cluster is a digital terrain model data set composed of multiple target digital terrain model data. The server then extracts the boundaries of the multiple target digital terrain model data clusters to obtain multiple target boundary polygons as the ramp layer.
[0046] According to the technical solution provided by the embodiments of the present disclosure, digital terrain model data of an operating area is obtained, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; the digital terrain model data is filtered based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data; the target digital terrain model data is segmented to obtain multiple target digital terrain model data clusters; and the boundaries of the multiple target digital terrain model data clusters are extracted to obtain multiple target boundary polygons as ramp layers. Thus, the ramp layer can be generated based on the terrain factors in the digital terrain model data. Thus, the data volume of the ramp layer is reduced, the accuracy of the calculation results of the ramp layer is improved, the real-time requirements of unmanned driving are met, and the driving safety of the unmanned vehicle is ensured.
[0047] In some embodiments, the terrain factor includes slope, and the digital terrain model data is filtered based on the terrain factor of the digital terrain model data at a target resolution to obtain target digital terrain model data, including: determining a target working area in the working area based on slope classification, and obtaining digital terrain model data of the target working area, wherein the slope classification is obtained by dividing the ramp based on the slope; and using an erosion algorithm and an expansion algorithm to perform an opening operation on the digital terrain model data of the target working area to obtain the target digital terrain model data.
[0048] Specifically, terrain factors include slope. Considering the requirements of vehicle dynamics, the ramp can be divided based on the slope to obtain slope classification. The server determines the target working area in the working area based on the slope classification and obtains the digital terrain model data of the target working area. Furthermore, the server uses the corrosion algorithm and the expansion algorithm to perform an opening operation on the digital terrain model data of the target working area to obtain the target digital terrain model data.
[0049] Here, slope is used to characterize the steepness of a surface unit. The ratio of a slope's vertical height (h) to its horizontal distance (l) is typically called the "slope" or "slope ratio," denoted by the letter "i." The slope formula is i = h / l × 100%. For example, an 8% slope (i.e., an 8-degree slope) means that for every 100 meters of horizontal distance, there is an 8-meter vertical rise (descent) in vertical direction.
[0050] The slope classification can be: a slope with a slope of 0° to 3° is level 0, that is, a flat slope; a slope with a slope of 3° to 6° is level 1, that is, a gentle slope; a slope with a slope of 6° to 10° is level 2, that is, a medium slope; a slope with a slope of 10° to 35° is level 3, that is, a steep slope; a slope with a slope of more than 35° is level 4, that is, a dangerous slope.
[0051] It should be noted that because steep slopes can affect the safety of unmanned vehicles and increase the risk of mining operations, steep slopes are considered dangerous areas and not included in drivable areas. Furthermore, it should be noted that different colors can be used to represent different slope levels, for example, blue represents level 0, green represents level 1, yellow represents level 2, and red represents level 3.
[0052] The target operation area refers to the area in the operation area excluding the dangerous area. The digital terrain model data of the target operation area includes digital terrain model data corresponding to four slope grades: flat slope, gentle slope, medium slope and steep slope.
[0053] The erosion algorithm filters out boundary points, shrinking the boundary inward; in other words, the erosion algorithm can be used to filter out small and meaningless objects. The dilation algorithm merges all background points that touch an object into the object, expanding the boundary outward; in other words, the dilation algorithm can be used to fill holes in the object. An opening operation is an erosion-then-dilation operation.
[0054] It should be noted that the embodiments of the present disclosure are not limited to the above-mentioned opening operation, and a closing operation may also be performed on the digital terrain model data of the target operation area, that is, an operation of first dilation and then erosion.
[0055] 2a to 2c, the filtering process of the digital terrain model data will be described.
[0056] Specifically, Figure 2a is the digital terrain model data with a resolution of 2.5m, that is, the original ramp point set. As shown in Figure 2a, the original ramp point set contains many messy noise points. The original ramp point set is corroded to filter out most of the noise points, resulting in the corroded ramp point set, as shown in Figure 2b. Furthermore, the corroded ramp point set is expanded to restore the ramp point coverage while filtering out most of the noise points, as shown in Figure 2c. The expanded ramp point set is used as the target digital terrain model data.
[0057] According to the technical solution provided in the embodiments of the present disclosure, by performing erosion and dilation processing on the digital terrain model data based on slope grading, the target operation area can be better expanded and isolated noise points can be effectively filtered out, making the target operation area more obvious and the outline clearer, thereby facilitating the subsequent generation of target boundary polygons.
[0058] In some embodiments, segmenting the target digital terrain model data to obtain multiple target digital terrain model data clusters includes: clustering the target digital terrain model data based on a preset threshold of slope classification to obtain multiple first digital terrain model data clusters; dividing the multiple first digital terrain model data clusters using a region growing algorithm to obtain multiple second digital terrain model data clusters; and filtering the multiple second digital terrain model data clusters to obtain multiple target digital terrain model data clusters.
[0059] Specifically, considering that flat slopes do not affect the driving safety of unmanned vehicles, flat slopes are not used as target operating areas to ensure data accuracy and high availability. The server can cluster the target digital terrain model data based on a preset threshold for slope classification to obtain multiple first digital terrain model data clusters, and then use a region growing algorithm to divide the multiple first digital terrain model data clusters to obtain multiple second digital terrain model data clusters. Furthermore, the server filters the multiple second digital terrain model data clusters based on a preset number of points and / or a preset area to obtain multiple target digital terrain model data clusters.
[0060] Here, the preset threshold value can be a threshold value pre-set by the user based on empirical data, or a threshold value obtained by adjusting the preset threshold value according to actual needs. The present embodiment is not limited to this. Considering that the slope classification is generally 0 to 5, the preset threshold value can be any value in the range of 1 to 4. Preferably, in the present embodiment, the preset threshold value is 3.
[0061] For example, when the preset threshold is 2, slope points between 3° and 10° can be clustered, that is, the target digital terrain model data corresponding to gentle slopes and moderate slopes can be clustered; slope points between 6° and 35° can also be clustered, that is, the target digital terrain model data corresponding to moderate slopes and steep slopes can be clustered; or slope points between 3° and 6° and slope points between 10° and 35° can also be clustered, that is, the target digital terrain model data corresponding to gentle slopes and steep slopes can be clustered. When the preset threshold is 3, slope points between 3° and 35° can be clustered, that is, the target digital terrain model data corresponding to gentle slopes, moderate slopes, and steep slopes can be clustered.
[0062] Clustering involves dividing a dataset into distinct classes or clusters based on a specific criterion, such that data objects within the same cluster are as similar as possible, while data objects in different clusters are as different as possible. Clustering methods include, but are not limited to, hierarchical clustering, partition-based clustering, density-based clustering, grid-based clustering, and model-based clustering.
[0063] It should be noted that, in the embodiment of the present disclosure, each of the multiple first digital terrain model data clusters obtained through clustering processing may include target digital terrain model data corresponding to one or more slope classifications; that is, the multiple target digital terrain model data included in each first digital terrain model data cluster may belong to the same slope classification or to different slope classifications.
[0064] The region growing algorithm merges pixels with similar properties. For each region, a seed point is first designated as the starting point for growth. Pixels in the area surrounding the seed point are then compared with the seed point. Points with similar properties are merged and the algorithm continues to grow outward until no more pixels meet the criteria.
[0065] The preset number of ramp points can be a number pre-set by the user based on empirical data, or can be a number of ramp points obtained by adjusting the preset number of ramp points based on actual needs. The present embodiment does not impose any restrictions on this. The preset number of points can be any value within the range of 30 to 50. Preferably, in the present embodiment, the preset number of points is 40, i.e., second digital terrain model data clusters having fewer than 40 ramp points are filtered out from the plurality of second digital terrain model data clusters.
[0066] The preset area can be the area of a digital terrain model data cluster pre-set by the user based on empirical data, or can be the area of a digital terrain model data cluster obtained by adjusting the area of the preset digital terrain model data cluster according to actual needs. This embodiment of the present disclosure is not limited thereto. In the embodiment of the present disclosure, the preset area is 0.5m×0.5m, that is, second digital terrain model data clusters with an area smaller than 0.5m×0.5m are filtered out from the plurality of second digital terrain model data clusters.
[0067] According to the technical solution provided by the embodiment of the present disclosure, by clustering and segmenting the target digital terrain model data based on slope classification, abnormal noise points can be filtered out according to actual needs, thereby improving the accuracy and reliability of the data.
[0068] In some embodiments, boundary extraction is performed on multiple target digital terrain model data clusters to obtain multiple target boundary polygons as ramp layers, including: using a scatter contour algorithm to obtain multiple boundary points of each target digital terrain model data cluster in the multiple target digital terrain model data clusters; and sequentially connecting the multiple boundary points to obtain an outer contour of the target digital terrain model data cluster as the ramp layer.
[0069] Specifically, after obtaining multiple target digital terrain model data clusters, the server can use the scatter contour algorithm to obtain multiple boundary points of each target digital terrain model data cluster in the multiple target digital terrain model data clusters, and connect the multiple boundary points in sequence to obtain the outer contour of the target digital terrain model data cluster, as shown in Figure 3.
[0070] The Alpha Shapes algorithm, also known as the rolling ball method, is an algorithm for extracting boundary points. In the disclosed embodiment, the Alpha Shapes algorithm can be used to extract the outer contour of a target digital terrain model data cluster by rolling a circle with an alpha radius (for 2.5m resolution digital terrain model data, the alpha radius can be set to 5.5m) along the edge of the target digital terrain model data cluster to form a complete, closed outer contour of the target digital terrain model data cluster.
[0071] It should be noted that the scattered point contour algorithm is usually used for point cloud contour extraction or three-dimensional reconstruction. Generally speaking, the smaller the alpha value, the more accurate the result.
[0072] According to the technical solution provided by the embodiment of the present disclosure, boundary points can be extracted quickly and accurately by utilizing the scattered point contour algorithm.
[0073] In some embodiments, the terrain factor includes a slope aspect, and the method further includes: obtaining slope aspect information of each target boundary polygon among a plurality of target boundary polygons; when it is determined based on the slope aspect information that a slope aspect change occurs in the target boundary polygon, determining a location where the slope aspect change occurs in the target boundary polygon; and segmenting the target boundary polygon based on the location where the slope aspect change occurs to obtain at least two sub-target boundary polygons as ramp layers.
[0074] Specifically, the terrain factors also include slope direction. Considering that there may be a continuous and long uphill or downhill section on the road surface in the mining area, accompanied by a relatively large slope direction change, therefore, in practical applications, in order to ensure the driving safety of unmanned vehicles, the server can obtain the slope direction information of each target boundary polygon among multiple target boundary polygons, and determine the position where the slope direction of the target boundary polygon changes based on the slope direction information; further, the server divides the target boundary polygon based on the position where the slope direction changes, and obtains two or more sub-target boundary polygons with roughly the same slope direction, as shown in Figure 4.
[0075] Here, aspect describes the direction of the slope normal projected onto the horizontal plane (from high to low). Aspect is measured in degrees clockwise, ranging from 0 degrees (due north) to 360 degrees (still due north). Each cell in the aspect grid represents the direction the slope of that cell faces. Flat slopes have no direction and are assigned a value of -1.
[0076] According to the technical solution provided in the embodiments of the present disclosure, by segmenting a complete boundary polygon with a large turn based on slope changes, at least two boundary polygons with roughly the same slope can be obtained, thereby providing terrain data support for path planning and decision-making control of unmanned vehicles.
[0077] In some embodiments, the method further includes: integrating the ramp layer into the high-precision map.
[0078] Specifically, after generating the ramp layer, the server will fuse the newly generated ramp layer of the target work area with the high-precision map to obtain a fused high-precision map; if there is no ramp layer of the target work area in the high-precision map, the ramp layer will be added to the fused high-precision map, that is, the newly generated ramp layer will be added to the high-precision map; if there is already a ramp layer of the target work area in the high-precision map, the newly generated ramp layer will be used to cover or replace the existing ramp layer in the fused high-precision map to ensure the accuracy of the high-precision map.
[0079] Here, a high-definition map (HD map), also known as a high-precision map, refers to a high-precision, high-freshness, and high-richness electronic map with absolute and relative accuracy within 1 meter. High-precision maps can help vehicles predict road information, environmental object information, real-time dynamic information, etc. to better avoid potential risks. Road information may include but is not limited to road type, slope, curvature, lane line position, etc. Environmental object information may include but is not limited to roadside infrastructure, obstacles, traffic signs, etc. Real-time dynamic information may include but is not limited to traffic participants, events, etc.
[0080] Furthermore, considering the frequency of data changes, high-precision maps can be divided into static maps and dynamic maps. Static maps refer to data updated on a monthly or daily basis, while dynamic maps refer to data updated on an hourly, minutely, or secondly basis. For example, the primary dynamic data within an open-pit mine is event reports such as vehicles within the mine and obstacles on the mine roads.
[0081] High-precision map data is the foundation of autonomous driving. It comprises two map layers: a static HD map layer and a dynamic HD map layer. The static HD map layer, the base map layer, provides vector information such as lane models, road components, and road attributes, including semantic information. It also includes feature layers for multi-sensor positioning.
[0082] According to the technical solution provided in the embodiment of the present disclosure, by fusing the ramp layer with the high-precision map, accurate and effective terrain data support can be provided to the autonomous driving system, so that the autonomous driving system can provide better path planning and make correct decision-making control for the unmanned vehicle based on the fused high-precision map. Therefore, the real-time calculation of the autonomous driving system is guaranteed, and the driving safety of the unmanned vehicle is guaranteed.
[0083] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present disclosure, and will not be described in detail here. In addition, the order of the sequence numbers of the steps in the above embodiments does not imply a specific order of execution. The order of execution of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.
[0084] FIG5 is a flow chart of another ramp layer generation method provided by an exemplary embodiment of the present disclosure. The ramp layer generation method of FIG5 can be executed by a server or electronic device in an autonomous driving system or a remote driving system. As shown in FIG5 , the ramp layer generation method includes:
[0085] S501, obtaining digital terrain model data of an operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions, and the terrain factors include slope and aspect;
[0086] S502, determining a target operating area in the operating area based on slope classification, and obtaining digital terrain model data of the target operating area, wherein the slope classification is obtained by dividing the ramp based on the slope;
[0087] S503, using an erosion algorithm and a dilation algorithm, performing an opening operation on the digital terrain model data of the target operation area to obtain target digital terrain model data;
[0088] S504, clustering the target digital terrain model data based on a preset threshold of slope classification to obtain a plurality of first digital terrain model data clusters;
[0089] S505, dividing the plurality of first digital terrain model data clusters using a region growing algorithm to obtain a plurality of second digital terrain model data clusters;
[0090] S506, filtering the plurality of second digital terrain model data clusters to obtain a plurality of target digital terrain model data clusters;
[0091] S507, using a scatter contour algorithm, obtaining a plurality of boundary points of each target digital terrain model data cluster in the plurality of target digital terrain model data clusters;
[0092] S508, connecting the multiple boundary points in sequence to obtain the outer contour of the target digital terrain model data cluster as a ramp layer;
[0093] S509, obtaining slope aspect information of each target boundary polygon among the multiple target boundary polygons;
[0094] S510, determining whether the target boundary polygon has a slope change based on the slope aspect information, if yes, executing S511; otherwise, executing S513;
[0095] S511, determining the location where the target boundary polygon has a slope change;
[0096] S512, segmenting the target boundary polygon based on the location where the slope aspect changes, to obtain at least two sub-target boundary polygons as a ramp layer;
[0097] S513, integrate the ramp layer into the high-precision map.
[0098] According to the technical solution provided by the embodiment of the present disclosure, by dividing the ramps in the target operation area based on the slope, and using the erosion algorithm and the expansion algorithm to perform an open operation on the digital terrain model data of the target operation area, it is possible to effectively filter out abnormal terrain points in the target operation area, thereby improving the accuracy of the calculation results of the ramp layer. Furthermore, by clustering and grading the target digital terrain model data and extracting multiple boundary points of the target digital terrain model data cluster using the scatter contour algorithm, the ramp polygon can be accurately and efficiently calculated. In addition, by clustering and segmenting the ramp polygons based on the slope aspect, and integrating the obtained sub-ramp polygons with generally consistent slope aspects as the ramp layer into the high-precision map, it is possible to provide terrain data support for the path planning and decision-making control of the unmanned vehicle, thereby ensuring the real-time calculation of the autonomous driving system and thus ensuring the driving safety of the unmanned vehicle.
[0099] In the case of dividing each functional module into corresponding functional modules, an embodiment of the present disclosure provides a ramp layer generation device, which can be a server or a chip applied to a server. Figure 6 is a schematic diagram of the structure of a ramp layer generation device provided by an exemplary embodiment of the present disclosure. As shown in Figure 6, the ramp layer generation device 600 includes:
[0100] An acquisition module 601 is configured to acquire digital terrain model data of an operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions;
[0101] A filtering module 602 is configured to filter the digital terrain model data based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data;
[0102] The segmentation module 603 is configured to segment the target digital terrain model data to obtain multiple target digital terrain model data clusters;
[0103] The extraction module 604 is configured to perform boundary extraction on multiple target digital terrain model data clusters to obtain multiple target boundary polygons as ramp layers.
[0104] According to the technical solution provided by the embodiments of the present disclosure, digital terrain model data of an operating area is obtained, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; the digital terrain model data is filtered based on the terrain factors of the digital terrain model data at a target resolution to obtain target digital terrain model data; the target digital terrain model data is segmented to obtain multiple target digital terrain model data clusters; and the boundaries of the multiple target digital terrain model data clusters are extracted to obtain multiple target boundary polygons as ramp layers. Thus, the ramp layer can be generated based on the terrain factors in the digital terrain model data. Thus, the data volume of the ramp layer is reduced, the accuracy of the calculation results of the ramp layer is improved, the real-time requirements of unmanned driving are met, and the driving safety of the unmanned vehicle is ensured.
[0105] In some embodiments, the terrain factor includes slope. The filtering module 602 of Figure 6 determines the target working area in the working area based on the slope classification, and obtains the digital terrain model data of the target working area, wherein the slope classification is obtained by dividing the ramp based on the slope; and uses the erosion algorithm and the expansion algorithm to perform an opening operation on the digital terrain model data of the target working area to obtain the target digital terrain model data.
[0106] In some embodiments, the segmentation module 603 of FIG6 clusters the target digital terrain model data based on a preset threshold value of slope classification to obtain a plurality of first digital terrain model data clusters; divides the plurality of first digital terrain model data clusters using a region growing algorithm to obtain a plurality of second digital terrain model data clusters; and filters the plurality of second digital terrain model data clusters to obtain a plurality of target digital terrain model data clusters.
[0107] In some embodiments, the extraction module 604 of FIG. 6 utilizes a scatter contour algorithm to obtain a plurality of boundary points of each target digital terrain model data cluster in the plurality of target digital terrain model data clusters; the plurality of boundary points are sequentially connected to obtain an outer contour of the target digital terrain model data cluster as a ramp layer.
[0108] In some embodiments, the terrain factor includes slope aspect, and the ramp layer generating apparatus 600 of FIG6 further includes: a determination module 605, wherein the acquisition module 601 acquires slope aspect information of each target boundary polygon among a plurality of target boundary polygons; the determination module 605 is configured to, when it is determined based on the slope aspect information that a target boundary polygon has undergone a slope aspect change, determine a location where the target boundary polygon has undergone a slope aspect change; and the segmentation module 603 of FIG6 segments the target boundary polygon based on the location where the slope aspect change has occurred, to obtain at least two sub-target boundary polygons as the ramp layer.
[0109] In some embodiments, the ramp layer generating apparatus 600 of FIG6 further includes: a fusion module 606 configured to fuse the ramp layer into the high-precision map.
[0110] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.
[0111] The embodiment of the present disclosure also provides a high-precision map, including a ramp layer generated by the steps of the above-mentioned ramp layer generation method disclosed in the embodiment of the present disclosure.
[0112] An embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; a memory for storing instructions executable by at least one processor; wherein the at least one processor is used to execute instructions to implement the steps of the above-mentioned ramp layer generation method disclosed in the embodiment of the present disclosure.
[0113] Figure 7 is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present disclosure. As shown in Figure 7, the electronic device 700 includes at least one processor 701 and a memory 702 coupled to the processor 701. The processor 701 can execute the corresponding steps in the above method disclosed in the embodiment of the present disclosure.
[0114] The processor 701 can also be referred to as a central processing unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the above method disclosed in the embodiment of the present disclosure can be completed by the hardware integrated logic circuit in the processor 701 or by instructions in the form of software. The processor 701 can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present disclosure can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in the memory 702, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The processor 701 reads the information in the memory 702 and completes the steps of the above method in combination with its hardware.
[0115] In addition, when various operations / processes according to the present disclosure are implemented via software and / or firmware, the programs constituting the software can be installed from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system 800 shown in FIG8 . When the various programs are installed, the computer system can perform various functions, including those described above. FIG8 is a schematic diagram of the structure of a computer system provided by an exemplary embodiment of the present disclosure.
[0116] Computer system 800 is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic equipment can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0117] As shown in FIG8 , the computer system 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the computer system 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0118] Multiple components within computer system 800 are connected to I / O interface 805, including an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. Input unit 806 can be any type of device capable of inputting information into computer system 800. Input unit 806 can receive input numeric or character information and generate key input signals related to user settings and / or function control of an electronic device. Output unit 807 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 808 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 809 allows computer system 800 to exchange information / data with other devices over a network, such as the Internet, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.
[0119] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above. For example, in some embodiments, the above-mentioned method disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. In some embodiments, the computing unit 801 may be configured to perform the above-mentioned method disclosed in the embodiments of the present disclosure by any other appropriate means (e.g., by means of firmware).
[0120] An embodiment of the present disclosure further provides a computer-readable storage medium, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above method disclosed in the embodiment of the present disclosure.
[0121] The computer-readable storage medium in the embodiments of the present disclosure can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. The above-mentioned computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specifically, the above-mentioned computer-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
[0122] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0123] The embodiments of the present disclosure further provide a computer program product, including a computer program, wherein when the computer program is executed by a processor, the method disclosed in the embodiments of the present disclosure is implemented.
[0124] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof, including but not limited to object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.
[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0126] The modules, components, or units described in the embodiments of the present disclosure may be implemented in software or hardware. The names of the modules, components, or units do not necessarily limit the modules, components, or units themselves.
[0127] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, and without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
[0128] The above descriptions are merely some embodiments of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present disclosure.
[0129] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art will appreciate that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art will appreciate that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims
1. A ramp layer generation method, characterized in that: include: Acquire digital terrain model data of the operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; filtering the digital terrain model data based on the terrain factors of the digital terrain model data at the target resolution to obtain target digital terrain model data; Segmenting the target digital terrain model data to obtain a plurality of target digital terrain model data clusters; Boundaries of the plurality of target digital terrain model data clusters are extracted to obtain a plurality of target boundary polygons as ramp layers.
2. The method according to claim 1, characterized in that The terrain factor includes a slope, and the digital terrain model data is filtered based on the terrain factor of the digital terrain model data at a target resolution to obtain target digital terrain model data, including: Determining a target working area in the working area based on a slope classification, and acquiring digital terrain model data of the target working area, wherein the slope classification is obtained by dividing a ramp based on the slope; The digital terrain model data of the target operation area is opened by using a corrosion algorithm and a dilation algorithm to obtain the target digital terrain model data.
3. The method according to claim 2, characterized in that The step of segmenting the target digital terrain model data to obtain a plurality of target digital terrain model data clusters includes: Clustering the target digital terrain model data based on a preset threshold of the slope classification to obtain a plurality of first digital terrain model data clusters; Dividing the plurality of first digital terrain model data clusters using a region growing algorithm to obtain a plurality of second digital terrain model data clusters; The plurality of second digital terrain model data clusters are filtered to obtain the plurality of target digital terrain model data clusters.
4. The method according to claim 1, characterized in that The step of extracting boundaries of the plurality of target digital terrain model data clusters to obtain a plurality of target boundary polygons as ramp layers includes: Using a scattered point contour algorithm, a plurality of boundary points of each target digital terrain model data cluster in the plurality of target digital terrain model data clusters are obtained; The plurality of boundary points are connected in sequence to obtain the outer contour of the target digital terrain model data cluster as the ramp layer.
5. The method according to claim 1, characterized in that: The terrain factor includes slope aspect, and the method further includes: Acquire slope aspect information of each target boundary polygon among the plurality of target boundary polygons; In a case where it is determined based on the aspect information that the target boundary polygon has a slope aspect change, determining a position where the target boundary polygon has a slope aspect change; The target boundary polygon is segmented based on the position where the slope direction changes, to obtain at least two sub-target boundary polygons as the ramp layer.
6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The ramp layer is integrated into the high-precision map.
7. A ramp layer generating device, characterized in that: include: An acquisition module is configured to acquire digital terrain model data of an operation area, wherein the digital terrain model data includes terrain factors of the digital terrain model data at different resolutions; A filtering module, configured to filter the digital terrain model data based on a terrain factor of the digital terrain model data at a target resolution to obtain target digital terrain model data; a segmentation module configured to segment the target digital terrain model data to obtain a plurality of target digital terrain model data clusters; The extraction module is configured to perform boundary extraction on the plurality of target digital terrain model data clusters to obtain a plurality of target boundary polygons as ramp layers.
8. A high-precision map, characterized in that: The high-precision map includes a ramp layer generated by the ramp layer generation method as described in any one of claims 1 to 6.
9. An electronic device, characterized in that: include: at least one processor; a memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method as claimed in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 6.
Citation Information
Patent Citations
Method and equipment for calculating road gradient information
CN102538754A
Surface cover surface area raster calculation method and device
CN107239664A
Construction method and device of digital elevation model, equipment and storage medium
CN112907744A
Water catchment area extraction method and device based on digital elevation model, equipment and medium
CN113360594A
Slope unit extraction method and device, electronic equipment and storage medium
CN114299233A
Cited By
Slope map generation method and system, terminal and medium
CN121437791A
