Digital traffic perception device and its management method, cloud control platform and its management method, digital traffic system

Abstract

The present invention relates to the field of computer technology, and provides a digital traffic perception device and its management method, a cloud control platform and its management method, and a digital traffic system. Among them, the management method of the digital traffic perception device includes: in response to power-on, obtaining a local map corresponding to the installation location of the digital traffic perception device from the cloud control platform; performing feature matching on its own sensor data and the local map to obtain pose data based on the installation location; and starting based on the pose data by obtaining corresponding configuration information from the cloud control platform. The solution disclosed by the present invention improves the accuracy of calibrating the pose data of the perception device, reduces the risk of abnormal startup of the perception device, and is beneficial to the perception device to realize the function of plug and play.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a digital traffic perception device and its management method, a cloud control platform and its management method, and a digital traffic system. Background Art

[0002] With the application of technologies such as artificial intelligence and big data, the intelligence level of digital traffic perception devices will continue to improve. The digital traffic perception devices work more closely with other traffic participants such as in-vehicle terminals and traffic management centers, and realize real-time sharing and interaction of information through more efficient communication protocols and data transmission technologies, ensuring collaborative work and collaborative decision-making between vehicles and road infrastructure.

[0003] Since the perception device cannot work directly after installation and needs to be powered on and restarted to work properly, in the existing digital traffic perception device management method, the pose of the perception device is manually calibrated, that is, a specific calibration tool is used manually, such as using an aerial work vehicle to calibrate the pose data of the perception device, so as to work after restarting based on the pose data. However, the method of manually calibrating the perception device is time-consuming and laborious, and the calibration error is large. The accurate pose data of the perception device cannot be obtained in the preparation stage, which increases the risk of abnormal startup of the perception device and is not conducive to the perception device realizing the plug-and-play function. Summary of the Invention

[0004] In view of this, the present invention provides a digital traffic perception device and its management method, a cloud control platform and its management method, and a digital traffic system, which solve the problems that in the existing digital traffic perception device management method, the method of manually calibrating the perception device is time-consuming and laborious, and the calibration error is large. The accurate pose data of the perception device cannot be obtained in the preparation stage, which increases the risk of abnormal startup of the perception device.

[0005] Based on the above purpose, in one aspect of the present invention, a management method for a digital traffic perception device is provided, including:

[0006] In response to power-on, obtain a local map corresponding to the installation location of the digital traffic perception device from the cloud control platform;

[0007] Match the sensor data of itself with the local map to obtain pose data based on the installation location;

[0008] Start based on the pose data to obtain corresponding configuration information from the cloud control platform.

[0009] In some embodiments, the step of obtaining a local map corresponding to the installation location of the digital traffic perception device from the cloud control platform in response to power-on includes:

[0010] In response to power-on, the digital traffic perception device sends its own located longitude and latitude coordinates to the cloud control platform;

[0011] Receive the local map centered on the longitude and latitude coordinates and with a preset size as the radius returned by the cloud control platform.

[0012] In some embodiments, the step of performing feature matching between its own sensor data and the local map to obtain pose data based on the installation position includes:

[0013] Obtain the real-time image data and real-time point cloud data of the digital traffic perception device itself;

[0014] Perform feature matching between the real-time image data and the local map to obtain a first matching result;

[0015] Perform feature matching between the real-time point cloud data and the local map to obtain a second matching result;

[0016] Determine the optimal matching result among the first matching result and the second matching result based on the optimal matching rule, so as to obtain pose data based on the installation position based on the optimal matching result.

[0017] In some embodiments, the step of performing feature matching between the real-time image data and the local map to obtain a first matching result includes:

[0018] Perform rasterization processing on the local map to obtain raster data;

[0019] Extract corners and points from the real-time image data and match them with the raster data to obtain the spatial relationship information corresponding to the corners and points in the raster data;

[0020] Calculate a first rotation matrix and a first translation vector for converting the real-time image data to the coordinate system of the local map based on the spatial relationship information, so as to serve as the first matching result.

[0021] In some embodiments, the step of performing feature matching between the real-time point cloud data and the local map to obtain a second matching result further includes:

[0022] Extract background data from the real-time point cloud data;

[0023] Perform full-angle matching between the background data and the point cloud data of the local map based on a preset step length to obtain a second rotation matrix and a second translation vector corresponding to converting the real-time point cloud data to the point cloud data of the local map, so as to serve as the second matching result.

[0024] In some embodiments, the step of determining the optimal matching result from the first matching result and the second matching result based on the optimal matching rule and obtaining the pose data based on the installation position based on the optimal matching result further includes:

[0025] Comparing the rotation angles corresponding to the first rotation matrix and the second rotation matrix respectively, and the translation distances corresponding to the first translation vector and the second translation vector respectively;

[0026] Taking the smallest rotation angle and the smallest translation distance of the digital traffic perception device rotating based on the installation position as the optimal matching rule to determine the optimal matching result from the first matching result and the second matching result, and obtaining the pose data based on the installation position based on the optimal matching result.

[0027] Another aspect of the embodiments of the present invention provides a cloud control platform management method, including:

[0028] In response to receiving the position data of the installation position sent by the digital traffic perception device, obtaining the local map corresponding to the installation position based on the position data and returning it to the digital traffic perception device;

[0029] In response to receiving the pose data sent by the digital traffic perception device, obtaining the corresponding configuration information based on the pose data and returning it to the digital traffic perception device.

[0030] Another aspect of the embodiments of the present invention provides a digital traffic perception device, including:

[0031] An image sensor and / or a radar sensor, respectively used to obtain their own sensor data;

[0032] A control unit, the control unit is used for: in response to power-on, sending the position data of the installation position of the digital traffic perception device to the cloud control platform and receiving the returned local map corresponding to the installation position; matching the data of the image sensor and / or the radar sensor with the local map to obtain the pose data based on the installation position; and sending the pose data to the cloud control platform and receiving the returned corresponding configuration information to start.

[0033] Another aspect of the embodiments of the present invention further provides a cloud control platform, including:

[0034] At least one processor;

[0035] And a memory, the memory stores computer instructions that can run on the processor, and when the instructions are executed by the processor, the following steps are implemented:

[0036] In response to receiving the location data of the installation location sent by the digital traffic perception device, obtain the local map corresponding to the installation location based on the location data and return it to the digital traffic perception device;

[0037] In response to receiving the pose data sent by the digital traffic perception device, obtain the corresponding configuration information based on the pose data and return it to the digital traffic perception device.

[0038] Another aspect of the embodiments of the present invention further provides a digital traffic system, including:

[0039] A number of digital traffic perception devices as described above;

[0040] The cloud control platform as described above; and

[0041] A digital base station, which is used to receive the pose data of the digital traffic perception device and the corresponding configuration information sent by the cloud control platform and establish a one-to-one binding relationship between the two, so as to perform data storage and monitoring based on the binding relationship.

[0042] The present invention has at least the following beneficial effects: A management method for digital traffic perception devices according to the present invention can obtain high-precision map information within a local range based on the installation location from the cloud control platform based on the association between the perception device and the cloud control platform, and obtain accurate pose data based on the installation location in the preparation stage through feature matching between the high-precision map information within the local range and its own sensor data, without manually calibrating the pose data of the perception device, reducing time costs and manpower, and improving the accuracy of calibrating the pose data of the perception device. Further, obtain the corresponding configuration information from the cloud control platform based on the accurate pose data and start based on the configuration information. Since the accuracy of the calibrated pose data is high and the corresponding configuration information is also highly accurate, the risk of abnormal startup of the perception device is reduced, which is beneficial to the perception device to achieve the function of plug and play.

[0043] In addition, the cloud control platform management method, digital traffic perception device, cloud control platform, and digital traffic system of the present invention also have at least the above beneficial effects, which will not be elaborated here. Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative efforts.

[0045] Figure 1Flow chart of a digital traffic perception device management method provided by an embodiment of the present invention;

[0046] Figure 2 Flow chart of a cloud control platform management method provided by another embodiment of the present invention;

[0047] Figure 3 Schematic structural diagram of a digital traffic perception device provided by another embodiment of the present invention;

[0048] Figure 4 Schematic structural diagram of a cloud control platform provided by another embodiment of the present invention;

[0049] Figure 5 Schematic structural diagram of a digital traffic system provided by another embodiment of the present invention is shown;

[0050] Figure 6 Interaction schematic diagram inside the digital traffic system provided by another embodiment of the present invention is shown. Detailed implementation manners

[0051] Embodiments of the present invention are described below. However, it should be understood that the disclosed embodiments are merely examples, and other embodiments may take various alternative forms.

[0052] In addition, it should be noted that the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements that are not explicitly listed or are inherent to these processes, methods, articles or devices.

[0053] One or more embodiments of the present application will be described below with reference to the accompanying drawings.

[0054] For the above purposes, in the first aspect of the embodiments of the present invention, an embodiment of a digital traffic perception device management method is proposed. Figure 1 A flow chart of a digital traffic perception device management method provided by an embodiment of the present invention is shown, as Figure 1 shown, including:

[0055] Step 101, in response to power-on, obtain a local map corresponding to the installation location of the digital traffic perception device from the cloud control platform;

[0056] Step 102, perform feature matching between its own sensor data and the local map to obtain pose data based on the installation location;

[0057] Step 103, start based on the pose data by obtaining corresponding configuration information from the cloud control platform.

[0058] Among them, the pose data represents the position data and pose data of the digital traffic perception device based on the installation position, and the pose data includes installation angle, direction, etc. The configuration information includes the IP (Internet Protocol, the protocol for interconnecting networks), port, name, installation position, perception result identifier, etc. of the digital traffic perception device. After the digital traffic perception device is powered on, it registers in the cloud control platform. After calculating the pose data, the pose data is uploaded to its registered position in the cloud control platform to receive the configuration information based on the pose data from the cloud control platform, and is started based on the configuration information. For example, for the digital traffic perception device installed on the north side of intersection A, the configuration information received by the digital traffic perception device from the cloud control platform includes the set name RoadSide_A / Deivce_N for it.

[0059] The above-mentioned method for managing a digital traffic perception device can obtain high-precision map information within a local range based on the installation position from the cloud control platform based on the association between the perception device and the cloud control platform, and obtain accurate pose data based on the installation position in the preparation stage through the feature matching between the high-precision map information within the local range and its own sensor data, without manually calibrating the pose data of the perception device, reducing the time cost and manpower, and improving the accuracy of calibrating the pose data of the perception device. Further, based on the accurate pose data, the corresponding configuration information is obtained from the cloud control platform, and the device is started based on the configuration information. Since the accuracy of the calibrated pose data is high, the accuracy of the corresponding configuration information is also high. Therefore, the risk of abnormal startup of the perception device is reduced, which is beneficial to the perception device to achieve the plug-and-play function.

[0060] According to several embodiments of the present invention, the step of obtaining a local map corresponding to the installation position of the digital traffic perception device from the cloud control platform in response to power-on includes:

[0061] In response to power-on, the digital traffic perception device sends its own located latitude and longitude coordinates to the cloud control platform;

[0062] Receive the local map centered on the latitude and longitude coordinates and with a preset size as the radius returned by the cloud control platform.

[0063] In a specific embodiment, after the sensing device is powered on, it obtains latitude and longitude coordinate data from GPS (Global Positioning System) information, such as 40.12345°N, 120.87964°E. There is a large gap between this latitude and longitude coordinate data and the actual pose, generally a gap of 30m. Therefore, the accurate pose data of the device installation location cannot be directly obtained. This latitude and longitude coordinate data is sent to the cloud control platform, and a local map centered on 40.12345°N, 120.87964°E and with a preset size as the radius is received from the cloud control platform. Among them, the complete map data of the monitoring range is stored in the cloud control platform. Preferably, the complete map data is high-precision map data based on point clouds. The accuracy of calibrating pose data based on high-precision map data is higher than that based on GPS information. The cloud control platform crops out a local map centered on 40.12345°N, 120.87964°E and with a preset size as the radius from the complete map. The preset radius is set according to the actual accuracy requirements, generally set to 200m. The coverage range of the local map covers the error range of the GPS information, ensuring that the installation location of the sensing device falls within the coverage range of the local map to reduce errors.

[0064] According to several embodiments of the present invention, the step of performing feature matching between its own sensor data and the local map to obtain pose data based on the installation location includes:

[0065] Obtain the real-time image data and real-time point cloud data of the digital traffic sensing device itself;

[0066] Perform feature matching between the real-time image data and the local map to obtain a first matching result;

[0067] Perform feature matching between the real-time point cloud data and the local map to obtain a second matching result;

[0068] Determine the optimal matching result among the first matching result and the second matching result based on the optimal matching rule, so as to obtain the pose data based on the installation location based on the optimal matching result.

[0069] Among them, the image data is generally the image information captured by a camera, including pixel values, color information, etc. The coordinate systems for describing image data include the pixel coordinate system (u, v), which is used to describe the positions of pixel points in the image. The origin is located at the upper left corner of the image, the horizontal direction is the u-axis, and the vertical direction is the v-axis; the image coordinate system (x, y), which is a two-dimensional coordinate system of the camera sensor imaging plane. The origin is at the intersection of the optical axis and this plane, and the x-axis and y-axis are parallel to the u-axis and v-axis of the pixel coordinate system respectively; the camera coordinate system (Xc, Yc, Zc), which is a coordinate system inside the camera and is used to describe the image information in the camera sensor. With the optical center of the lens (optical center) as the origin, the Zc-axis is consistent with the optical axis of the camera and points forward, and the Xc and Yc axes are parallel to the x-axis and y-axis of the image coordinate system respectively. The point cloud data is a set of vectors in a three-dimensional coordinate system. Each point contains three-dimensional coordinates, and some may also contain color information (RGB) or reflection intensity information (Intensity). The point cloud data is usually represented using the world coordinate system and is used to describe and locate the positions of objects in three-dimensional space, reflecting the positions and orientations of objects in the real world.

[0070] For the perception device, feature points in the image data are extracted through image processing and computer vision techniques and matched with the points in the local map data to obtain richer three-dimensional information; distance and angle information are obtained from the real-time point cloud data and feature-matched with the local map to accurately calibrate the pose data of the perception device. Through reasonable coordinate system transformation and feature point matching, the effective matching and fusion between the sensor data and the local map data (high-precision map data) are achieved, improving the accuracy and robustness of the calibration of the pose data of the perception device.

[0071] According to several embodiments of the present invention, the step of performing feature matching between the real-time image data and the local map to obtain the first matching result includes:

[0072] Performing rasterization processing on the local map to obtain raster data;

[0073] Extracting corners and points from the real-time image data and matching them with the raster data to obtain the spatial relationship information corresponding to the corners and points in the raster data;

[0074] Calculating a first rotation matrix and a first translation vector corresponding to the coordinate system of the local map for converting the real-time image data based on the spatial relationship information as the first matching result.

[0075] In a specific example, corner points are extracted from real-time image data based on corner detection algorithms (such as Harris corner detection, Shi-Tomasi corner detection, etc.). By identifying the points with obvious angle changes in the image, that is, corner points, the corner point data is used as feature data, retaining the key features of the image, reducing the amount of information data, and improving the image calculation speed. Further, for each extracted corner point, its corresponding feature descriptor is calculated. For example, feature descriptor algorithms such as SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), and ORB (Oriented FAST and Rotated BRIEF) are used to calculate the corresponding feature descriptor, obtaining a vector for describing the image information around the point.

[0076] The local map is divided into regular grids (rasters), and corresponding information (such as occupied, free, or unknown status) is stored in each grid. At the same time, based on the matching algorithm of feature descriptors, the corner points extracted from the image are matched with the grid information of the high-precision map. Specifically, search for positions similar to the descriptor in the grid data of the high-precision map, calculate the similarity score between the descriptors (such as Euclidean distance or Hamming distance), and obtain the match with the lowest score; introduce spatial constraints, for example, limit the search range of the corner points on the local map, or require the matched corner points to have a similar spatial position relationship between the image and the map to increase the accuracy of the match; match multiple corner points instead of relying only on one corner point to increase the robustness of the match. Through matching the corner point data, the spatial relationship information of the corner points in the grid data, such as angle, direction, distance, etc., is obtained. Calculate the first rotation matrix and the first translation vector corresponding to the coordinate system of converting the real-time image data to the local map as the first matching result. For example, calculate the rotation matrix between the real-time image data and the local map based on the Euler angle method, and calculate the first translation vector based on the displacement relationship between the coordinate system of the real-time image data and the coordinate system of the local map.

[0077] According to several embodiments of the present invention, the step of performing feature matching between the real-time point cloud data and the local map to obtain the second matching result further includes:

[0078] Extract background data from the real-time point cloud data;

[0079] Perform full-angle matching on the background data and the point cloud data of the local map based on a preset step size to obtain the second rotation matrix and the second translation vector corresponding to the point cloud data of converting the real-time point cloud data to the local map as the second matching result.

[0080] In a specific example, the background data of real-time point cloud data is matched with the point cloud data of the local map, with rough matching first and then fine matching. Specifically, for rough matching, the background data is sparsified, and feature data is extracted from it. The background data and the point cloud data of the local map are scanned at a fixed step size in a rotational full-angle manner for matching to prevent local matching during rough matching. The matching results and corresponding angles of each rotation are recorded and sorted respectively. Based on the sorting results, several points are selected for fine matching. Small-angle rotational scanning is performed near multiple rotation angles based on the original background data (without sparsification processing) and the point cloud data of the local map for matching. The matching results and corresponding angles of each rotation are recorded again and sorted respectively to obtain the matching result of this point cloud matching. Multiple rounds of matching are performed in the above combined manner of rough matching and fine matching, and finally, the optimal matching result is obtained based on the least squares method as the second matching result.

[0081] According to several embodiments of the present invention, the step of determining the optimal matching result among the first matching result and the second matching result based on the optimal matching rule to obtain the pose data based on the installation position further includes:

[0082] Comparing the rotation angles corresponding to the first rotation matrix and the second rotation matrix respectively, and the translation distances corresponding to the first translation vector and the second translation vector respectively;

[0083] Taking the rule that the rotation angle of the digital traffic perception device based on the installation position is the smallest and the translation distance is the smallest as the optimal matching rule to determine the optimal matching result among the first matching result and the second matching result, and obtaining the pose data based on the installation position based on the optimal matching result.

[0084] According to the second aspect of the embodiments of the present invention, a cloud control platform management method is further proposed. Figure 2 The flowchart of a cloud control platform management method provided by the embodiments of the present invention is shown as Figure 2 shown, and includes:

[0085] Step 201, in response to receiving the position data of the installation position sent by the digital traffic perception device, obtaining the local map corresponding to the installation position based on the position data and returning it to the digital traffic perception device;

[0086] Step 202, in response to receiving the pose data sent by the digital traffic perception device, obtaining the corresponding configuration information based on the pose data and returning it to the digital traffic perception device.

[0087] According to the third aspect of the embodiments of the present invention, a digital traffic perception device is further proposed. Figure 3The following is a schematic structural diagram of a digital traffic perception device provided by an embodiment of the present invention, as Figure 3 shown, including:

[0088] An image sensor 301 and / or a radar sensor 302, which are respectively used to obtain their own sensor data;

[0089] A control unit 303, and the control unit 303 is used for: in response to power-on, sending the position data of the installation location of the digital traffic perception device to the cloud control platform and receiving the returned local map corresponding to the installation location; performing feature matching on the data of the image sensor and / or the radar sensor with the local map to obtain pose data based on the installation location; and sending the pose data to the cloud control platform and receiving the returned corresponding configuration information for startup.

[0090] This digital traffic perception device can be used for road traffic monitoring, facilitating the timely monitoring of road traffic conditions, and can also be used for unmanned aerial vehicle (UAV) supervision, positioning and tracking of UAVs, which is beneficial to the management and monitoring of air traffic, can timely master the flight dynamics of UAVs, and improve the real-time performance and reliability of air management.

[0091] According to the fourth aspect of the embodiments of the present invention, a cloud control platform is further proposed. Figure 4 The following is a schematic structural diagram of a cloud control platform provided by an embodiment of the present invention, as Figure 4 shown, the cloud control platform includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the following steps are implemented: in response to receiving the position data of the installation location sent by the digital traffic perception device, obtaining the local map corresponding to the installation location based on the position data and returning it to the digital traffic perception device; in response to receiving the pose data sent by the digital traffic perception device, obtaining the corresponding configuration information based on the pose data and returning it to the digital traffic perception device.

[0092] According to the fifth aspect of the embodiments of the present invention, a digital traffic system is further proposed. Figure 5 The following is a schematic structural diagram of a digital traffic system provided by an embodiment of the present invention, as Figure 5As shown in the figure, it includes: several digital traffic perception devices 401 as described above; a cloud control platform 402 as described above; and a digital base station 403. The digital base station 403 receives the pose data of the digital traffic perception devices 401 and the corresponding configuration information sent by the cloud control platform 402, and establishes a one-to-one binding relationship between the two, so as to perform data storage and monitoring based on the binding relationship.

[0093] Furthermore, Figure 6 The figure shows an interaction schematic diagram inside the digital traffic system provided by an embodiment of the present invention. As Figure 6 shown, in the digital traffic system, there is an interaction between the digital traffic perception device, the cloud control platform, and the data reference. Specifically:

[0094] (1) After the digital traffic perception device is powered on, it obtains its own installation position based on the positioning of its own sensors. For example, it obtains its own installation position through the GPS positioning module.

[0095] (2) The digital traffic perception device sends the position data of the installation position to the cloud control platform. Here, based on the mobile communication technology, the position data is sent to the cloud control platform in the form of a signal and registered on the cloud platform based on its position data.

[0096] (3) The cloud control platform receives the position signal and obtains the position data therein, and returns the local map data around the installation position to the digital traffic perception device based on the position data. The local map is a local map centered on the installation position and with a preset size as the radius.

[0097] (4) The digital traffic perception device receives the local map data returned by the cloud control platform, and performs feature matching between the local map data and its own sensor data, and obtains the pose data based on the matching result. That is to say, the digital traffic perception device can be adjusted to the best position based on the pose data.

[0098] (5) The digital traffic perception device uploads the pose data to the registered position of the cloud control platform, so that the cloud control platform returns the configuration information based on the pose data, and at the same time sends the configuration information to the digital base station for storage.

[0099] (6) The digital traffic perception device is started based on the configuration information, and sends the pose data to the digital base station for storage, so that the digital base station establishes a binding relationship between the pose data and the corresponding configuration information, and performs data monitoring based on the binding relationship.

[0100] Finally, it should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program of the method for setting system parameters can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiment can achieve the same or similar effect as any of the above-mentioned method embodiments corresponding thereto.

[0101] In addition, the method disclosed in the embodiment of the present invention can also be implemented as a computer program executed by a processor, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the above functions defined in the method disclosed in the embodiment of the present invention are performed.

[0102] In addition, the above method steps and system units may also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.

[0103] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0104] In one or more exemplary designs, the functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. The storage media may be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer or a general purpose or special purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0105] The above are exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present invention as defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments herein need not be performed in any particular order. In addition, although the elements disclosed by the embodiments of the present invention may be described or claimed in individual form, they can also be understood as plural unless explicitly limited to the singular.

[0106] It should be understood that, as used herein, unless the context clearly supports exceptions, the singular forms "a" and "an" are intended to also include the plural forms. It should also be understood that the phrase "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0107] The serial numbers of the disclosed embodiments of the present invention above are merely for description and do not represent the superiority or inferiority of the embodiments.

[0108] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disc, etc.

[0109] Those of ordinary skill in the art should understand that the discussion of any above embodiment is only exemplary, and is not intended to imply that the scope (including the claims) disclosed by the embodiments of the present invention is limited to these examples; under the idea of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for managing digital traffic perception devices, characterized in that, Including: In response to power-on, the digital traffic device registers in the cloud control platform and obtains a local map corresponding to the installation location of the digital traffic sensing device from the cloud control platform; Performing feature matching between its own sensor data and the local map to obtain pose data based on the installation location, which includes: Obtaining the real-time image data and real-time point cloud data of the digital traffic sensing device itself; Performing feature matching between the real-time image data and the local map to obtain a first rotation matrix and a first translation vector corresponding to converting the real-time image data to the coordinate system of the local map, as a first matching result; Performing feature matching between the real-time point cloud data and the local map, which includes: extracting background data from the real-time point cloud data, sparsifying it, and performing rough matching with the point cloud data of the local map by rotating and scanning at a fixed step size in all angles, and performing fine matching by rotating and scanning at a smaller angle near multiple rotation angles; Obtaining a second rotation matrix and a second translation vector corresponding to converting the real-time point cloud data to the point cloud data of the local map, as a second matching result; Determining the optimal matching result among the first matching result and the second matching result based on an optimal matching rule, so as to obtain pose data based on the installation location based on the optimal matching result, which includes: determining the optimal matching result among the first matching result and the second matching result with the rule that the rotation angle of the digital traffic sensing device based on the installation location is the smallest and the translation distance is the smallest, and obtaining pose data based on the installation location based on the optimal matching result; The digital traffic device uploads the pose data to its registered location in the cloud control platform; Obtaining corresponding configuration information from the cloud control platform based on the pose data for startup.

2. The digital traffic perception device management method according to claim 1, wherein The step of, in response to power-on, obtaining a local map corresponding to the installation location of the digital traffic sensing device from the cloud control platform includes: In response to power-on, the digital traffic sensing device sends its own located longitude and latitude coordinates to the cloud control platform; Receiving the local map returned by the cloud control platform with the longitude and latitude coordinates as the center and a preset size as the radius.

3. The digital traffic perception device management method according to claim 1, wherein The step of performing feature matching between the real-time image data and the local map to obtain a first matching result includes: Performing rasterization processing on the local map to obtain raster data; Extracting corners and points from the real-time image data and matching them with the raster data to obtain the spatial relationship information corresponding to the corners and points in the raster data; Calculating a first rotation matrix and a first translation vector corresponding to converting the real-time image data to the coordinate system of the local map based on the spatial relationship information, as a first matching result.

4. The digital traffic perception device management method according to claim 3, characterized in that The step of performing feature matching between the real-time point cloud data and the local map to obtain a second matching result further includes: Extracting background data from the real-time point cloud data; Perform a full-angle matching of the background data and the point cloud data of the local map based on a preset step size to obtain a second rotation matrix and a second translation vector corresponding to the point cloud data obtained by converting the real-time point cloud data to the point cloud data of the local map, which are used as the second matching result.

5. The digital traffic perception device management method according to claim 4, characterized in that The step of determining the optimal matching result from the first matching result and the second matching result based on the optimal matching rule and obtaining the pose data based on the installation position based on the optimal matching result further includes: Compare the rotation angles corresponding to the first rotation matrix and the second rotation matrix respectively, and the translation distances corresponding to the first translation vector and the second translation vector respectively.

6. A cloud control platform management method, characterized in that, Includes: In response to receiving the position data of the installation position sent by the digital traffic perception device, obtain the local map corresponding to the installation position based on the position data and return it to the digital traffic perception device; Obtain the pose data based on the installation position through the digital traffic perception device, which includes: Perform feature matching between the real-time image data of itself and the local map to obtain a first rotation matrix and a first translation vector corresponding to the coordinate system obtained by converting the real-time image data to the local map, which are used as the first matching result; Perform feature matching between the real-time point cloud data of itself and the local map, which includes: extracting background data from the real-time point cloud data, sparsifying it, and performing rough matching with the point cloud data of the local map by full-angle rotation scanning at a fixed step size, and performing fine matching by rotating scanning at a smaller angle near multiple rotation angles; Obtain a second rotation matrix and a second translation vector corresponding to the point cloud data obtained by converting the real-time point cloud data to the point cloud data of the local map, which are used as the second matching result; Determine the optimal matching result from the first matching result and the second matching result based on the optimal matching rule, and obtain the pose data based on the installation position based on the optimal matching result; In response to receiving the pose data sent by the digital traffic perception device, obtain the corresponding configuration information based on the pose data and return it to the digital traffic perception device.

7. A digital traffic perception device, characterized in that, The device includes: An image sensor and / or a radar sensor, which are respectively used to obtain the sensor data of itself; A control unit, and the control unit is used for: In response to power-on, the digital traffic device registers on the cloud control platform, sends the position data of the installation position of the digital traffic perception device to the cloud control platform, and receives the returned local map corresponding to the installation position; Perform feature matching between the data of the image sensor and / or the radar sensor and the local map to obtain the pose data based on the installation position, which includes: Obtain the real-time image data and real-time point cloud data of the digital traffic perception device itself; Perform feature matching between the real-time image data and the local map to obtain a first rotation matrix and a first translation vector corresponding to the coordinate system obtained by converting the real-time image data to the local map, which are used as the first matching result; Performing feature matching between the real-time point cloud data and the local map, which includes: extracting background data from the real-time point cloud data, sparsifying it, and performing rough matching with the point cloud data of the local map by rotating and scanning at a fixed step and full angle, and performing fine matching by rotating and scanning at a smaller angle near multiple rotation angles; Obtaining a second rotation matrix and a second translation vector corresponding to the point cloud data obtained by converting the real-time point cloud data to the point cloud data of the local map as a second matching result; Determining the optimal matching result between the first matching result and the second matching result based on the optimal matching rule, and obtaining pose data based on the installation position based on the optimal matching result, which includes: determining the optimal matching result between the first matching result and the second matching result with the rule that the rotation angle of the digital traffic perception device based on the installation position is the smallest and the translation distance is the smallest, and obtaining pose data based on the installation position based on the optimal matching result; The digital traffic device uploads the pose data to its registered position in the cloud control platform; Sending the pose data to the cloud control platform and receiving the returned corresponding configuration information to start.

8. A cloud control platform, characterized in that, Including: At least one processor; And a memory storing computer instructions executable on the processor, and when the instructions are executed by the processor, the following steps are implemented: In response to receiving the position data of the installation position sent by the digital traffic perception device, obtaining the local map corresponding to the installation position based on the position data and returning it to the digital traffic perception device; In response to receiving the pose data sent by the digital traffic perception device, obtaining the corresponding configuration information based on the pose data and returning it to the digital traffic perception device; Wherein, the pose data is obtained by the digital traffic perception device, and it includes: Performing feature matching between the real-time image data and the local map, obtaining a first rotation matrix and a first translation vector corresponding to the coordinate system obtained by converting the real-time image data to the local map as a first matching result; and Performing feature matching between the own real-time point cloud data and the local map, which includes: extracting background data from the real-time point cloud data, sparsifying it, and performing rough matching with the point cloud data of the local map by rotating and scanning at a fixed step and full angle, and performing fine matching by rotating and scanning at a smaller angle near multiple rotation angles; Obtaining a second rotation matrix and a second translation vector corresponding to the point cloud data obtained by converting the real-time point cloud data to the point cloud data of the local map as a second matching result; Determining the optimal matching result between the first matching result and the second matching result based on the optimal matching rule, and obtaining pose data based on the installation position based on the optimal matching result.

9. A digital transportation system, characterized in that, Including: Several digital traffic perception devices as described in claim 7; The cloud control platform as described in claim 8; And A digital base station, which is used to receive the pose data of the digital traffic perception device and the corresponding configuration information sent by the cloud control platform, and establish a one-to-one binding relationship between the two, so as to perform data storage and monitoring based on the binding relationship.

Images