Paving road boundary line determination method, device, electronic device and storage medium

Abstract

The present application provides a method, device, electronic device, and computer-readable storage medium for determining the boundary line of a paved road surface. After obtaining preprocessed data of the target paved road surface collected and processed by each sensor, the method determines corrected point cloud data based on the point cloud, positioning, and inertial preprocessing data, determines fused data based on the corrected point cloud data and the image preprocessing data, determines a feature point set based on the fused data and the image preprocessing data in the preprocessing data, and generates first boundary line data of the target paved road surface based on the feature point set. The first boundary line data is optimized based on the corrected point cloud data to obtain optimized boundary line data, and is converted according to a preset target format to generate target boundary line information. The present application determines the boundary line based on the road surface data directly measured by each sensor. Through multi-sensor fusion technology, it reduces the requirements for hardware and operators and the risks on site, and improves measurement accuracy, efficiency, and flexibility.

Description

Technical Field

[0001] The present application relates to the technical field of road pavement engineering measurement, and in particular to a method, device, electronic device, and computer-readable storage medium for determining a paved road boundary line. Background Art

[0002] In existing pavement projects, unmanned construction systems based on unmanned paving and compaction have gradually been applied to multiple engineering projects.

[0003] However, the determination of paving and compaction boundary lines still mainly relies on traditional manual RTK (real-time dynamic positioning) layout, installation of baffles or direct use of designed line data, but this method is not efficient; the accuracy of the method of indirectly calculating the boundary line by measuring the paving width is easily affected by factors such as the arch of the ironing plate and assembly adjustment, and has poor flexibility; the paving width detection method based on vehicle-mounted image acquisition devices still has problems of insufficient accuracy and poor adaptability; the method of obtaining orthophotos and extracting boundary lines through drones has high requirements on hardware and operators, and there are problems of on-site risks and data redundancy.

[0004] Therefore, the current method for determining the boundary line of paving pavement has the disadvantages of low efficiency and accuracy, low flexibility, high requirements for hardware and operation, and technical problems such as on-site risks and data redundancy. It is difficult to meet the needs of unmanned construction systems and needs to be improved. Summary of the Invention

[0005] The present application provides a method, device, electronic device and computer-readable storage medium for determining the boundary line of a paved road surface, which are used to alleviate the technical problems of the current method for determining the boundary line of a paved road surface, such as low efficiency and accuracy, low flexibility, high hardware and operation requirements, and the existence of on-site risks and data redundancy.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] The present application provides a method for determining a paved road boundary line, comprising:

[0008] Acquire pre-processed data of the target paved road surface collected and processed by each sensor, wherein the pre-processed data includes point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data, and image pre-processed data;

[0009] Determining corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data;

[0010] Determining fused data based on the corrected point cloud data and the image preprocessing data;

[0011] determining a feature point set according to the fused data and the image preprocessing data, and generating first boundary line data of the target paved road surface based on the feature point set;

[0012] Optimizing the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data;

[0013] The optimized boundary line data is converted according to a preset target format to generate target boundary line information of a target paved road surface.

[0014] Accordingly, the present application also provides a device for determining a paved road boundary line, comprising:

[0015] A data acquisition module is used to acquire pre-processed data of the target paved road surface collected and processed by each sensor, wherein the pre-processed data includes point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data and image pre-processed data;

[0016] a point cloud correction module, configured to determine corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data;

[0017] A data fusion module, configured to determine fused data based on the corrected point cloud data and the image preprocessing data;

[0018] a feature extraction module, configured to determine a feature point set according to the fused data and the image preprocessing data, and generate first boundary line data of the target paved road surface based on the feature point set;

[0019] a boundary line optimization module, configured to optimize the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data;

[0020] The data format conversion module is used to convert the optimized boundary line data according to a preset target format to generate target boundary line information of a target paved road surface.

[0021] At the same time, the present application provides an electronic device, which includes a processor and a memory, the memory is used to store computer programs, and the processor is used to run the computer programs in the memory to execute the steps in the above-mentioned paved road boundary line determination method.

[0022] In addition, the present application also provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps in the above-mentioned paved road boundary line determination method.

[0023] The present application provides a method, device, electronic device, and computer-readable storage medium for determining the boundary line of a paved road surface. Specifically, the method first obtains preprocessed data of a target paved road surface collected and processed by various sensors. The preprocessed data includes point cloud preprocessed data, positioning preprocessed data, inertial preprocessed data, and image preprocessed data. Corrected point cloud data is then determined based on the point cloud preprocessed data, positioning preprocessed data, and inertial preprocessed data. Fusion data is then determined based on the corrected point cloud data and image preprocessed data. A feature point set is then determined based on the fusion data and image preprocessed data. First boundary line data of the target paved road surface is generated based on the feature point set. The first boundary line data is then optimized based on the corrected point cloud data to obtain optimized boundary line data. Finally, the optimized boundary line data is converted according to a preset target format to generate target boundary line information. The method uses various sensors to measure and collect road surface data of the target paved road surface, and then determines the boundary line based on this data. This multi-sensor fusion technology reduces hardware and operator requirements and reduces on-site risks. Furthermore, the direct measurement and data fusion approach improves measurement accuracy, efficiency, and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The following detailed description of the specific embodiments of the present application in conjunction with the accompanying drawings will make the technical solutions and other beneficial effects of the present application apparent.

[0025] Figure 1 This is a system architecture diagram of the paved road boundary line determination system provided in an embodiment of the present application.

[0026] Figure 2 It is a flow chart of the method for determining the boundary line of a paved road surface provided in an embodiment of the present application.

[0027] Figure 3 This is a scene diagram of the method for determining the boundary line of a paved road surface provided in an embodiment of the present application.

[0028] Figure 4 It is a structural schematic diagram of the paving road surface boundary line determination device provided in an embodiment of the present application.

[0029] Figure 5 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0031] The terms "including" and "having" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions; the division of modules appearing in this application is merely a logical division, and there may be other division methods when implemented in actual applications, for example, multiple modules may be combined into or integrated into another system, or some features may be ignored or not executed.

[0032] The present application provides a method, device, electronic device and computer-readable storage medium for determining the boundary line of a paved road surface, wherein the paved road surface boundary line determination device can be integrated into an electronic device, which can be a handheld terminal or a terminal mounted on a mobile vehicle.

[0033] See also Figure 1 , Figure 1 This is a system architecture diagram of the paving road boundary line determination system provided by the embodiment of the present application, such as Figure 1 As shown, the system may include terminals and devices, and the terminals, devices, and terminals and devices are connected and communicated through the Internet composed of various gateways. The system at least includes a sensor terminal 101, a server 102, and an automatic construction device 103:

[0034] Sensor terminal 101 refers to a SLAM 3D scanning terminal composed of at least one sensor. It may include a radar module (such as a 360° lidar), a positioning module (such as a GNSS positioning module), an inertial measurement module (such as an inertial navigation unit), and an image acquisition module (such as a panoramic camera). Sensor terminal 101 is primarily used to collect various road surface data of the target paved road surface. For example, the radar module primarily collects point cloud data, the positioning module primarily collects positioning data, the inertial measurement module primarily collects inertial data, and the image acquisition module primarily collects image data.

[0035] Server 102 can be a standalone server or a server network or server cluster. For example, the servers described in this application include, but are not limited to, computers, network hosts, database servers, and application servers, or cloud servers comprised of multiple servers, where a cloud server is comprised of a large number of computers or network servers based on cloud computing. Server 102 can be integrated with a data processing module that can perform preprocessing, data fusion, coordinate conversion, data optimization, and format conversion on various types of data collected by sensor terminals.

[0036] The automatic construction equipment 103 refers to unmanned equipment for paving roads, and mainly includes unmanned pavers and unmanned rollers.

[0037] A communication link is provided between the sensor terminal 101, the server 102, and the automatic construction equipment 103 to enable information exchange. The type of the communication link may include a wired or wireless communication link or an optical fiber cable, etc., which is not limited in this application.

[0038] The sensor terminal 101 collects various types of road surface data of the target paved road surface through its sensors, mainly including point cloud data, positioning data, inertial data and image data, and transmits this data to the server 102 for preprocessing to obtain preprocessed data corresponding to the various types of road surface data. The preprocessed data mainly includes point cloud preprocessing data, positioning preprocessing data, inertial preprocessing data and image preprocessing data. Then, the server 102 determines the corrected point cloud data based on the point cloud preprocessing data, positioning preprocessing data and inertial preprocessing data, and then determines the fused data based on the corrected point cloud data and the image preprocessing data. Then, a feature point set is determined based on the fused data and the image preprocessing data, and first boundary line data of the target paved road surface is generated based on the feature point set. The first boundary line data is then optimized based on the corrected point cloud data to obtain optimized boundary line data. The server 102 converts the optimized boundary line data according to a preset target format to generate target boundary line information. Finally, the server 102 sends the generated target boundary line information to the automatic construction equipment 103, and the automatic construction equipment 103 performs construction based on the received target boundary line information.

[0039] Optionally, the sensor terminal 101 and server 102 can be integrated into the same device or equipment. A surveyor can use this device or equipment to measure the target paved surface, or the device can be mounted on an autonomous vehicle to automatically measure the target paved surface. This device or equipment can be combined with automated construction equipment into an unmanned road construction system, forming a complete unmanned or reduced-management construction system.

[0040] In the above-mentioned process of determining the paving road boundary line, the pavement data of the target paving road surface is measured and collected by each sensor in the sensor terminal 101, and the boundary line is determined based on this data through the server 102. The server 102 sends the target boundary line information to the construction equipment 103 to realize the navigation function, replacing the surveyor's early collection of the actual paving boundary line of the construction, and providing reliable navigation data for the unmanned construction system. This multi-sensor fusion technician reduces the requirements for hardware and operators and the on-site risks, and the direct measurement and data fusion method improves the measurement accuracy, efficiency and flexibility.

[0041] It should be noted that Figure 1The system architecture diagram shown is only an example. The terminals, devices, and scenarios described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will know that with the evolution of the system and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems. The following are detailed descriptions. It should be noted that the order of description of the following embodiments does not limit the preferred order of the embodiments.

[0042] In the examples of this application, please refer to Figure 2 As shown, Figure 2 : is a flow chart of a method for determining a paved road boundary line provided in an embodiment of the present application. The method includes at least the following steps:

[0043] S201: Acquire pre-processed data of the target paved road surface collected and processed by each sensor, where the pre-processed data includes point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data, and image pre-processed data.

[0044] In the embodiments of the present application, each sensor may include a radar module (e.g., a 360° lidar), a positioning module (e.g., a GNSS positioning module), an inertial measurement module (e.g., an inertial navigation unit), and an image acquisition module (e.g., a panoramic camera). The radar module may collect local point cloud data of the target paved road surface, the positioning module may collect positioning data of the target paved road surface, the inertial measurement module may collect inertial data of the target paved road surface, and the image acquisition module may collect image data of the target paved road surface.

[0045] It should be noted that the radar module is suitable for most road construction scenarios. It can collect complete three-dimensional information of the equipment's surrounding environment and three-dimensional geometric information of the road surface (including boundary lines) (such as curbstones, steel templates, etc.) in real time, and can accurately describe the subtle features of the road surface and boundaries (such as the edges of curbstones, the corners of steel templates, etc.) to ensure the comprehensiveness and continuity of boundary line generation and high boundary line generation accuracy; the positioning module can obtain RTK coordinates with centimeter-level accuracy in real time, achieve high-precision real-time positioning, and is suitable for dynamic construction environments. It provides high-precision global positioning information for the SLAM (Simultaneous Localization and Mapping) algorithm, ensuring the accuracy of boundary line generation; the inertial measurement module supports real-time data acquisition and processing to adapt to dynamic construction environments. This module is mainly used to correct the equipment's posture deviation and ensure the accuracy of sensor data. It provides high-precision and high-reliability posture and motion state information for the unmanned construction system, ensuring the accuracy of boundary line generation; the image acquisition module supports real-time video streaming and static image acquisition, can capture detailed visual information, provide high-precision visual feature points, and assist in boundary line generation.

[0046] In one embodiment, step S201 includes: filtering and denoising local point cloud data to obtain point cloud preprocessing data; correcting positioning data to obtain positioning preprocessing data; correcting inertial navigation data based on the positioning preprocessing data to obtain inertial preprocessing data; and performing distortion correction on image data to obtain image preprocessing data.

[0047] In an embodiment of the present application, the radar module first collects local point cloud data (including three-dimensional coordinate information) of the target paved road surface, and then performs pre-processing operations such as filtering, denoising, and feature point extraction (such as curbstones, steel templates, etc.) to remove noise and no-viewpoints (such as vehicles, pedestrians, etc.) in the point cloud data to obtain point cloud pre-processed data, thereby improving the quality of the point cloud data. The positioning module first collects positioning data (including pseudorange, carrier phase, satellite status, etc.) from the device where the module is located. It then performs preprocessing operations such as data verification, error correction, differential correction, data filtering, and coordinate conversion on the collected positioning data to obtain preprocessed positioning data. Among them, data verification mainly eliminates invalid or low-quality positioning data. Error correction mainly corrects atmospheric errors, multipath effects, satellite clock errors, and orbit errors to obtain preliminary corrected positioning data. Differential correction mainly uses differential correction data provided by a base station or CORS (Continuously Operating Reference Station System) to calculate high-precision positioning information in real time. Afterward, differential correction is performed using the base station data to obtain preliminary corrected positioning data, further improving positioning accuracy and achieving centimeter-level positioning accuracy. The preliminary corrected positioning data is then smoothed using a filtering algorithm to eliminate noise and jitter in the data to obtain smoothed positioning data, ensuring the continuity and stability of the positioning data. Finally, the WGS84 coordinate system is converted to the local coordinate system required for construction to obtain preprocessed positioning data (i.e., corrected high-precision positioning data). The inertial measurement module first collects inertial data from the device where the module is located (such as attitude information (pitch, roll, and yaw angles) and displacement information). It then performs preprocessing operations such as verification, filtering, zero-bias correction, temperature compensation, coordinate system alignment, attitude solution, velocity and position solution to obtain inertial preprocessed data (i.e., corrected attitude and displacement data). The image acquisition module first collects high-resolution image data of the target paved road surface. Then, through preprocessing operations such as image stitching, distortion correction, image enhancement, feature point extraction, image segmentation, and data compression, it obtains image preprocessed data (i.e., image data after distortion correction and feature point extraction).

[0048] The pre-processed data collected by various sensors provides the unmanned construction system with high-precision and high-reliability point cloud data, positioning data, inertial data and visual information, supporting real-time navigation, global map construction, environmental perception and boundary line generation, ensuring the accuracy and efficiency of the construction process.

[0049] S202: Determine the corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data.

[0050] In one embodiment, step S202 includes: determining first point cloud data based on the point cloud preprocessed data and the positioning preprocessed data; and determining corrected point cloud data based on the first point cloud data and the inertial preprocessed data. The point cloud preprocessed data uses a local coordinate system (e.g., the coordinate system of the device where the sensor resides) as a reference; the positioning preprocessed data uses a global coordinate system (e.g., the WGS84 coordinate system) as a reference; the first point cloud data refers to the local point cloud data in the global coordinate system; and the corrected point cloud data refers to the local point cloud data after posture correction.

[0051] Specifically, using the positioning preprocessing data as a reference, the point cloud preprocessing data is converted from the local coordinate system to the global coordinate system to obtain the first point cloud data to determine the position of the device where the sensor is located in the global coordinate system and support global map construction; then the first point cloud data is posture corrected based on the inertial preprocessing data to correct the posture deviation of the point cloud data (such as pitch angle, roll angle, yaw angle), and obtain corrected point cloud data to ensure the consistency of the point cloud data in the global coordinate system.

[0052] S203: Determine fusion data based on the corrected point cloud data and the image preprocessing data.

[0053] In the embodiment of the present application, the fused data refers to three-dimensional point cloud data with texture information. Specifically, data fusion and coordinate transformation are performed on the corrected point cloud data and image preprocessing data: the calibration parameters of the image acquisition module (such as intrinsic parameters and extrinsic parameters) are used for coordinate system transformation, and the corrected point cloud data is transformed from the global coordinate system to the image coordinate system to obtain point cloud data in the image coordinate system. Geometric feature points (such as edges, corners, etc.) are extracted from the point cloud data in the image coordinate system, and visual feature points (such as SIFI, SURF, ORB, etc.) are extracted from the image preprocessing data. The correspondence between geometric feature points and visual feature points is found using a feature point matching algorithm (such as nearest neighbor matching, RANSAC, etc.) to obtain matched feature point pairs. The point cloud data and image data are aligned using a registration algorithm (such as ICP algorithm), and the registration error is eliminated through an optimization algorithm (such as least squares method) to obtain registered point cloud data and registered image data. The texture information in the registered image data is mapped to the registered point cloud data to obtain three-dimensional point cloud data with texture information, which is fused with the registered image data, and the fused data is smoothed using a filtering algorithm to obtain fused data.

[0054] S204: Determine a feature point set according to the fused data and the image preprocessing data, and generate first boundary line data of the target paved road surface based on the feature point set.

[0055] In one embodiment, step S204 includes: extracting geometric feature points from the fused data and visual feature points from the image preprocessing data; obtaining a matched fused feature point set based on the geometric feature points and the visual feature points; and processing the feature point set to generate first boundary line data of the target paved road surface.

[0056] Boundary lines refer to virtual or actual markings used to define paving areas or construction scopes during road construction or maintenance. They are an important reference during the construction process to ensure that paving materials (such as asphalt, concrete, etc.) are laid evenly within the specified area while avoiding material waste or exceeding the design range. Figure 3 , the boundary line AD is the dividing line between the target road surface AB and the non-road surface CD.

[0057] Specifically, a point cloud processing algorithm (such as a method based on curvature or normal vector) is used to extract the geometric feature points of the rigid formwork or curbstones on both sides of the target paved road surface (such as the edge points of the curbstones) from the fused data; an edge detection algorithm (such as the Canny algorithm) is used to extract edge features in the image preprocessing data, and a corner detection algorithm (such as Harris corner detection) is used to extract corner features in the image preprocessing data to obtain visual feature points (such as edges and corners in the image); the geometric feature points are matched with the visual feature points to find the corresponding relationship, and a fusion algorithm (such as weighted average or least squares method) is used to generate a matched and fused feature point set; finally, the feature point set is clustered, fitted, and optimized to generate the first boundary line data of the target paved road surface.

[0058] In one embodiment, the steps of processing the feature point set to generate the first boundary line data of the target paved road surface include: clustering the feature point set to obtain classified feature point clusters; fitting the feature point clusters to obtain preliminary boundary line data; and smoothing the preliminary boundary line data to obtain the first boundary line data of the target paved road surface.

[0059] Specifically, a clustering algorithm (such as K-means or DBSCAN) is used to cluster the feature points, distinguish different boundary areas, extract the feature point clusters on both sides of the target paving road surface, and obtain the classified feature point clusters; a curve fitting algorithm (such as polynomial fitting or spline curve fitting) is used to fit the feature point clusters to generate preliminary boundary line data; a smoothing algorithm (such as Gaussian filtering or moving average) is used to smooth the boundary line, and the boundary line is segmented and optimized according to construction requirements to obtain the first boundary line data of the target paving road surface.

[0060] S205: Optimizing the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data.

[0061] In one embodiment, step S205 includes: constructing a global point cloud map based on the corrected point cloud data; and optimizing the first boundary line data based on the global point cloud map to obtain optimized boundary line data. The corrected point cloud data is the local point cloud data after posture correction.

[0062] Specifically, SLAM technology is used to stitch the local corrected point cloud data obtained after multiple acquisitions and processing in the above steps into a preliminary global point cloud map, and the local point cloud data are aligned through a point cloud registration algorithm (such as the ICP algorithm) to eliminate errors in overlapping areas. A filtering algorithm (such as a Gaussian filter) is used to remove noise in the preliminary global point cloud map, and the map is smoothed to improve map quality and obtain a global point cloud map; the first boundary line information is compared with the global point cloud map, and a registration algorithm (such as the ICP algorithm) is used to correct the position deviation of the boundary line to obtain a registration verification result, and then the boundary line is dynamically adjusted according to the registration verification result to correct errors, ensure the accuracy and stability of the boundary line, and obtain optimized boundary line data.

[0063] It should be noted that the global point cloud map serves as reference data for boundary line generation, ensuring the global consistency of the boundary line. It also supports dynamic updating and accuracy verification of the boundary line, adapts to changes in construction conditions, and provides high-precision and high-reliability environmental information for the unmanned construction system.

[0064] S206: Convert the optimized boundary line data according to a preset target format to generate target boundary line information.

[0065] In one embodiment, step S206 includes: obtaining actual construction requirements for paving the road surface; segmenting the optimized boundary line data based on the actual construction requirements to obtain segmented boundary line data; and converting the segmented boundary line data according to a preset target format to generate target boundary line information. The actual construction requirements refer to requirements that can be met, including those based on construction accuracy, efficiency, quality, and safety. The preset target format refers to a data format that is manually or automatically set for ease of transmission and use. In this application, the preset target format may be the WGS84 format.

[0066] Specifically, the optimized boundary line data is divided into several segments according to the needs of different construction areas to obtain segmented boundary line data; the segmented boundary line data is then converted into a preset target format for easy transmission and use, thereby generating target boundary line information of the target paving road surface.

[0067] In one embodiment, after step S206, the method further includes: establishing a communication connection with a construction device; and sending target boundary line information of the target paved road surface to the construction device. The construction device may be an unmanned paver or unmanned roller control device.

[0068] In this embodiment of the present application, a communication connection can be established with the construction equipment via wireless communication methods such as 4G / 5G networks to achieve data transmission. The target boundary line information can be transmitted to the construction equipment in the form of a navigation file or text message to implement a navigation function. The construction equipment can determine the boundary line based on the received target boundary line information and set an appropriate construction width.

[0069] See also Figure 3 , Figure 3 A schematic diagram of a method for determining the boundary of a paved road provided in an embodiment of the present application. Through steps S201 to S206, the sensor terminal uses each sensor to detect boundary line marks (such as Figure 3 The boundary line AD shown in the figure can be a steel template or a curbstone) is scanned or measured to obtain pre-processed data. The pre-processed data is combined and edge-processed by the server to obtain the target boundary line information. The target boundary line information is output in segments as a WGS84 format navigation file or text information, and transmitted to the construction equipment via wireless communication to realize the navigation function, replacing the surveyor's early collection of the actual paving boundary line of the construction. This multi-sensor fusion technology reduces the requirements for hardware and operators and the on-site risks, and the direct measurement and data fusion method improves the measurement accuracy, efficiency and flexibility.

[0070] Based on the content of the above embodiment, the embodiment of the present application provides a device for determining the boundary line of a paved road surface. Specifically, please refer to Figure 4 , the device comprises:

[0071] The data acquisition module 301 is used to acquire pre-processed data of the target paved road surface collected and processed by each sensor, the pre-processed data including point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data and image pre-processed data;

[0072] The point cloud correction module 302 is used to determine the corrected point cloud data based on the point cloud pre-processed data, the positioning pre-processed data and the inertial pre-processed data;

[0073] The data fusion module 303 is used to determine fused data based on the corrected point cloud data and the image preprocessing data;

[0074] A feature extraction module 304 is configured to determine a feature point set based on the fused data and the image preprocessing data, and generate first boundary line data of the target paved road surface based on the feature point set;

[0075] A boundary line optimization module 305 is configured to optimize the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data;

[0076] The data format conversion module 306 is used to convert the optimized boundary line data according to a preset target format to generate target boundary line information.

[0077] In one embodiment, the point cloud correction module 302 includes:

[0078] A first determining module, configured to determine first point cloud data based on the point cloud preprocessing data and the positioning preprocessing data;

[0079] The second determination module is used to determine the corrected point cloud data according to the first point cloud data and the inertial pre-processing data.

[0080] In one embodiment, the feature extraction module 304 includes:

[0081] A first extraction module is used to extract geometric feature points in the fused data and visual feature points in the image preprocessing data;

[0082] The matching fusion module is used to obtain a set of matched and fused feature points based on geometric feature points and visual feature points;

[0083] The first processing module is used to process the feature point set to generate first boundary line data of the target paving road surface.

[0084] In one embodiment, the first processing module includes:

[0085] Clustering module, used to perform clustering processing on the feature point set to obtain classified feature point clusters;

[0086] The fitting module is used to fit the feature point cluster to obtain preliminary boundary line data;

[0087] The smoothing processing module is used to smooth the preliminary boundary line data to obtain the first boundary line data of the target paving road surface.

[0088] In one embodiment, the boundary line optimization module 305 includes:

[0089] A map construction module is used to construct a global point cloud map based on the corrected point cloud data;

[0090] The information optimization module is used to optimize the first boundary line data based on the global point cloud map to obtain optimized boundary line data.

[0091] In one embodiment, the data format conversion module 306 includes:

[0092] Demand acquisition module, used to obtain actual construction requirements for paving the road surface;

[0093] A segmentation processing module is used to segment the optimized boundary line data based on actual construction requirements to obtain segmented boundary line data;

[0094] The information generation module is used to convert the segmented boundary line data into a format according to a preset target format to generate target boundary line information of the target paved road surface.

[0095] In one embodiment, the paved road surface boundary line determination device further includes:

[0096] A communication establishment module is used to establish a communication connection with the construction equipment;

[0097] The information sending module is used to send the target boundary line information to the construction equipment.

[0098] Different from the current technology, the paving pavement boundary line determination device provided by this application is equipped with a data acquisition module, a point cloud correction module, a data fusion module, a feature extraction module and a data format conversion module. The data acquisition module obtains the pre-processed data of the target paving pavement collected and processed by each sensor, and the pre-processed data is subjected to a series of processing by the point cloud correction module, the data fusion module, the feature extraction module and the data format conversion module to obtain the boundary line information of the target paving pavement. This multi-sensor fusion technology reduces the requirements for hardware and operators and the on-site risks, and the direct measurement and data fusion methods improve the measurement accuracy, efficiency and flexibility.

[0099] Accordingly, the embodiment of the present application further provides an electronic device, such as Figure 5 As shown, the electronic device may include a processor 401 with one or more processing cores, a wireless (WiFi, Wireless Fidelity) module 402, a memory 403 with one or more computer-readable storage media, a radar module 404, a positioning module 405, an inertial measurement module 406, an image acquisition module 407, a power supply 408, and a radio frequency (RF, Radio Frequency) circuit 409. Those skilled in the art will appreciate that Figure 5 The structure of the electronic device shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0100] Processor 401 is the control center of the electronic device. It connects all parts of the electronic device using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 403 and accessing data stored in memory 403, it performs various functions of the electronic device and processes data, thereby monitoring the entire electronic device. In one embodiment, processor 401 may include one or more processing cores; preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 401.

[0101] WiFi is a short-range wireless transmission technology. Electronic devices can help users send and receive emails, browse web pages, and access streaming media through the wireless module 402. It provides users with wireless broadband Internet access. Figure 5 The wireless module 402 is shown, but it is understandable that it is not an essential component of the terminal and can be omitted as needed without changing the essence of the invention.

[0102] Memory 403 can be used to store software programs and modules. Processor 401 executes various functional applications and data processing by running the computer programs and modules stored in memory 403. Memory 403 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on terminal usage (such as audio data and a phone book). Memory 403 may also include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 403 may also include a memory controller to provide processor 401 with access to memory 403.

[0103] Radar module 404 is a sensor that measures distance and constructs a 3D point cloud by emitting a laser beam and receiving reflected signals. Its optional scanning range is 360° (horizontally) × 96° (vertically), meaning it can scan all directions around the device horizontally and 96° vertically, covering the area from the ground to a certain height. Its point cloud density can reach 64,000 points per second, meaning it can collect 64,000 point cloud data points per second. Its scanning range is 30 meters, with a maximum effective scanning distance of 30 meters. Radar module 404 collects complete 3D information about the device's surroundings and 3D geometric information of the road surface (such as curbstones and steel formwork) in real time, ensuring comprehensive and continuous boundary line generation and supporting boundary line generation in complex construction environments. Its high-density point cloud accurately describes subtle road and boundary features (such as curbstone edges and steel formwork corners), improving boundary line generation accuracy. Its scanning range is suitable for most road construction scenarios, ensuring effective long-range acquisition of road and boundary information in complex construction environments. Optionally, the radar module 404 may be a 360° laser radar.

[0104] Positioning module 405 is a high-precision positioning device that can operate as a rover or connect to a CORS (Continuously Operating Reference Station System) system. It acquires RTK (Real-Time Kinematic) coordinates in real time and supports post-differential data processing, providing real-time correction, verification, and matching for SLAM path algorithms. Specifically, as a rover, it can receive correction data from a reference station to achieve high-precision real-time positioning. It can also connect to the CORS network and utilize correction data from multiple reference stations to improve positioning accuracy and reliability. It can also support post-differential data processing to improve positioning accuracy through post-correction. Optionally, positioning module 405 can be a GNSS positioning module.

[0105] Inertial measurement module 406 is a device based on an inertial measurement unit (IMU). It can provide real-time device attitude information (such as pitch, roll, and yaw) and acceleration information. It can provide precise positioning within a short period of time even when GNSS signals are lost or blocked. Optionally, inertial measurement module 406 can be an inertial navigation unit.

[0106] The image acquisition module 407 is a device that can provide 360° panoramic visual images, and captures complete visual information of the device's surrounding environment through multi-lens or single-lens rotation shooting technology. Optionally, the image acquisition module 407 can be a panoramic camera.

[0107] The electronic device also includes a power supply 408 (e.g., a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 401 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 408 can also include any of one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other components.

[0108] The RF circuit 409 can be used to receive and transmit signals during information transmission or calls. Specifically, it receives downlink information from the base station and transmits it to one or more processors 401 for processing. It also transmits uplink data to the base station. Typically, the RF circuit 409 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, and the like. Furthermore, the RF circuit 409 can communicate with the network and other devices via wireless communication. Wireless communication can utilize any communication standard or protocol, including but not limited to Global System of Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Messaging Service (SMS).

[0109] It should be noted that the electronic device may also include other sensors, such as a light sensor. Specifically, the light sensor may include an ambient light sensor and a distance sensor. The ambient light sensor may adjust the brightness of the display panel according to the brightness of the ambient light. As for other sensors that the electronic device may also be configured with, such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., they will not be elaborated here.

[0110] Although not shown, the electronic device may further include a Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 403 according to the following instructions, and the processor 401 will run the application programs stored in the memory 403, thereby achieving the following functions:

[0111] Acquire pre-processed data of the target paved road surface collected and processed by each sensor, the pre-processed data including point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data, and image pre-processed data;

[0112] Determine the corrected point cloud data based on the point cloud preprocessing data, positioning preprocessing data and inertial preprocessing data;

[0113] Determine fusion data based on the corrected point cloud data and image preprocessing data;

[0114] Determining a feature point set based on the fused data and the image preprocessing data, and generating first boundary line data of the target paved road surface based on the feature point set;

[0115] Optimizing the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data;

[0116] The optimized boundary line data is converted according to a preset target format to generate target boundary line information of the target paving road surface.

[0117] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0118] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores a plurality of instructions that can be loaded by a processor to implement the functions of the above-mentioned paved road boundary line determination method.

[0119] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0120] The above is a detailed introduction to the paved road boundary line determination method, device, electronic device and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for determining a paved road boundary line, characterized in that: include: Acquire pre-processed data of the target paved road surface collected and processed by each sensor, wherein the pre-processed data includes point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data, and image pre-processed data; Determining corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data; Determining fused data based on the corrected point cloud data and the image preprocessing data; determining a feature point set according to the fused data and the image preprocessing data, and generating first boundary line data of the target paved road surface based on the feature point set; Optimizing the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data; The optimized boundary line data is converted according to a preset target format to generate target boundary line information of a target paved road surface.

2. The method for determining a paved road boundary line according to claim 1, wherein: The step of determining the corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data comprises: Determining first point cloud data according to the point cloud preprocessing data and the positioning preprocessing data; Corrected point cloud data is determined based on the first point cloud data and the inertial pre-processed data.

3. The method for determining a paved road boundary line according to claim 1, wherein: The step of determining a feature point set according to the fused data and the image preprocessing data, and generating first boundary line data of the target paved road surface based on the feature point set includes: Extracting geometric feature points from the fused data and visual feature points from the image preprocessing data; Obtaining a matched and fused feature point set based on the geometric feature points and the visual feature points; The feature point set is processed to generate first boundary line data of the target paved road surface.

4. The method for determining a paved road boundary line according to claim 3, wherein: The step of processing the feature point set to generate first boundary line data of the target paved road surface includes: Performing clustering processing on the feature point set to obtain classified feature point clusters; Performing fitting processing on the feature point cluster to obtain preliminary boundary line data; The preliminary boundary line data is smoothed to obtain first boundary line data of the target paved road surface.

5. The method for determining a paved road boundary line according to claim 1, wherein: The step of optimizing the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data includes: Constructing a global point cloud map based on the corrected point cloud data; The first boundary line data is optimized based on the global point cloud map to obtain optimized boundary line data.

6. The method for determining a paved road boundary line according to claim 1, wherein: The step of converting the optimized boundary line data according to a preset target format to generate target boundary line information of a target paved road surface includes: Obtain actual construction requirements for paving pavement; Segment-processing the optimized boundary line data based on the actual construction requirements to obtain segmented boundary line data; The segmented boundary line data is format-converted according to a preset target format to generate target boundary line information.

7. The method for determining a paved road boundary line according to claim 1, wherein: After the step of converting the optimized boundary line data according to a preset target format to generate target boundary line information of a target paved road surface, the method further includes: Establish communication links with construction equipment; The target boundary line information is sent to the construction equipment.

8. A device for determining a paved road boundary line, characterized in that: include: A data acquisition module is used to acquire pre-processed data of the target paved road surface collected and processed by each sensor, wherein the pre-processed data includes point cloud pre-processed data, positioning pre-processed data, inertial pre-processed data and image pre-processed data; a point cloud correction module, configured to determine corrected point cloud data based on the point cloud preprocessing data, the positioning preprocessing data, and the inertial preprocessing data; A data fusion module, configured to determine fused data based on the corrected point cloud data and the image preprocessing data; a feature extraction module, configured to determine a feature point set according to the fused data and the image preprocessing data, and generate first boundary line data of the target paved road surface based on the feature point set; a boundary line optimization module, configured to optimize the first boundary line data according to the corrected point cloud data to obtain optimized boundary line data; The data format conversion module is used to convert the optimized boundary line data according to a preset target format to generate target boundary line information of a target paved road surface.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to run the computer program in the memory to execute the steps in the method for determining a paved road boundary line according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, which are suitable for being loaded by a processor to execute the steps of the paved road boundary line determination method according to any one of claims 1 to 7.

Images