Road monitoring system and method

Abstract

A method and system for road monitoring, comprising the steps of: receiving, by a communication module, first point cloud data from one or more designated Road Side Units (RSUs) of a plurality of RSUs located within a determined geographic area; receiving, by the communication module, second point cloud data from one or more designated on-board data processing units of vehicles located within the determined geographic area; processing, by a processing module, the first and second point cloud data to generate processed point cloud data; and transmitting, by the communication module, information derived from the processed point cloud data to one or more RSUs and / or on-board data processing units of vehicles located within the determined geographic area.

Description

TECHNICAL FIELD

[0001] The present invention relates to a system and method for road monitoring, in particular, but not limited to, a system and method for detecting blind spots of vehicles and / or other monitoring agents on a road. BACKGROUND

[0002] Connected and Autonomous Vehicles (CAVs) are vehicles configured for the purpose of assisting or replacing human drivers, which can at least automatically complete part of the driving tasks. In contrast to traditional vehicles, which are typically configured to determine or detect potential threats on the road using only real-time data obtained from on-board modules (e.g. vision sensors), CAVs are configured to communicate information from the vehicle to any entity that can potentially affect the vehicle, and vice versa, using Vehicle-to-Everything (V2X) communication protocols, a type of vehicle communication protocol. V2X protocols help with road safety, management and / or threat determination by enabling communication of information and / or data exchange between on-board data processing units and, for example, roadside infrastructure. V2X systems contain other more specific types of communication, including but not limited to Vehicle-to-Infrastructure (V2I), Vehicle-to-Vehicle (V2V), Vehicle-to-Pedestrian (V2P), Vehicle-to-Device (V2D) and Vehicle-to-Grid (V2G).

[0003] Typically, CAVs are equipped with sensors that collect point clouds; a point cloud comprises a collection of individual data points of a three-dimensional space, each data point being assigned a set of coordinates of X, Y and Z axes. Point cloud data is particularly useful in object detection, path planning and vehicle control of CAVs. Similarly, road-side units (RSUs), such as road-side sensors or other connected devices, are also able to collect point clouds, which are then transmitted to edge servers through cellular-vehicle-to-everything (C-V2X) channels.

[0004] It is well known that the field of view of conventional vision sensors mounted on vehicles is limited due to the size and height of the vehicle and the presence of other objects near and around the vehicle on the road. In various V2X networks, V2V cooperative perception requires each vehicle to transmit its precise position, which is sometimes a challenge due to common environmental limitations, such as when vehicles are located in dense urban areas. Furthermore, V2V communication networks, such as Dedicated Short Range Communication (DSRC) and Long Term Evolution Direct (LTE-direct) networks, which provide approximately 10 Mbps bandwidth, will not be suitable to support direct sharing of raw point cloud data from sensors between multiple agents, such as CAVs and RSUs. Sharing processed data instead of raw point cloud data is generally undesirable because it misses valuable information that can be extracted from point clouds, which is crucial for robust positioning of vehicles, and furthermore, can introduce latency in the transmission of processed data.

[0005] CN114173307A discloses an optimization method based on a roadside perception fusion system. The method includes the following steps: taking vehicle end positioning (vehicle end high-precision GNSS, inertial navigation or high-precision map combined positioning) as the true value of positioning, and transmitting the true value of positioning to the roadside unit according to the vehicle-road cooperation mode; and determining the sensing accuracy of the roadside sensing device.

[0006] CN114332494A discloses a three-dimensional target detection and recognition method for vehicles based on multi-source fusion. Different environmental information is collected by different roadside device sensors, multi-modal features are extracted, and then transmitted to a roadside feature fusion center. The roadside feature fusion center then fuses the obtained multi-path multi-modal features into multi-source fusion features for target recognition and detection by vehicles.

[0007] CN112767475A discloses an intelligent roadside perception system based on C-V2X, radar and vision. For vision target detection and radar multi-target tracking, a lightweight target detection neural network model and a weighted neighborhood data association multi-target tracking algorithm based on traceless Kalman filtering are applied. A multi-sensor fusion time synchronization method based on interpolation and extrapolation is designed to synchronize the data collected by different sensors, and then combined with C-V2X communication, the fusion results are corrected and compensated through vehicle-road cooperative data.

[0008] US2021225171A1 discloses a method for processing vehicle-to-infrastructure collaborative information, comprising: generating first vehicle-mounted perception data, including data of obstacles around a target vehicle perceived by the target vehicle; generating virtual obstacle data representing the target vehicle according to positioning data of the target vehicle; generating second vehicle-mounted perception data according to the virtual obstacle data and the first vehicle-mounted perception data; and fusing the second vehicle-mounted perception data with roadside perception data to obtain fusion data, the fusion data including all obstacle data in the second vehicle-mounted perception data and the roadside perception data, the obstacle data in the roadside perception data including obstacle data representing the target vehicle.

[0009] CN111524357A discloses a multi-data fusion method for safe driving of a vehicle. The method comprises the following steps: acquiring dynamic information, feature information, road condition information and traffic state information of a driving vehicle within a target range by using a plurality of roadside sensors installed on a roadside; acquiring motion state information, surrounding road conditions and environmental information of the driving vehicle by using a vehicle-mounted unit arranged on the vehicle; performing first fusion of information acquired by the roadside sensors and information acquired by the vehicle-mounted unit through a roadside service platform; performing second fusion of data through the roadside service platform; analyzing to obtain abnormal event data information, performing third fusion of the abnormal event data information and abnormal event data information of the vehicle, and obtaining final abnormal event information; and performing fourth fusion of the generated final abnormal event information and high-precision map data of the region to generate a new high-precision map and corresponding collaborative traffic scheme, early warning information, alarm information and vehicle control information.

[0010] WO2022141912A1 relates to a perception information fusion representation and target detection method for vehicle-road cooperation, wherein compressed voxel features are sent from a vehicle to a roadside device for map fusion.

[0011] CN111222441A relates to a method and system for point cloud target detection and blind area target detection based on vehicle-road cooperation. The method comprises the following steps: image target detection and position measurement and calculation; target classification based on an inspector; determining a target detection scheme according to the target classification result of the inspector; and performing point cloud target detection using a Pointnet++ algorithm.

[0012] Despite the above disclosures, there is still a need to develop a mechanism based on multi-agent collaborative perception to improve vehicle road safety.

[0013] Objectives of the invention

[0014] An object of the present invention is to alleviate or avoid, to some extent, one or more problems associated with known road monitoring systems and methods for improving vehicle road safety.

[0015] The above objective is achieved through the combination of features in the main claim; the dependent claims disclose further advantageous embodiments of the invention.

[0016] Other objects of the invention will become apparent to those skilled in the art from the following description. Therefore, the foregoing statement of objects is not exhaustive, but merely illustrative of some of the many objects of the invention. Summary of the Invention

[0017] In a first principal aspect, the present invention provides a method for road monitoring. The method includes the following steps: receiving first point cloud data from one or more designated RSUs among a plurality of RSUs located in a defined geographic area via a communication module; receiving second point cloud data from one or more designated on-board data processing units of vehicles located in the defined geographic area via the communication module; processing the first and second point cloud data via a processing module to generate processed point cloud data; and transmitting information derived from the processed point cloud data to one or more on-board data processing units of the plurality of RSUs and / or vehicles located in the defined geographic area via the communication module.

[0018] In a second key aspect, the present invention provides a method for detecting road blind spots. The method includes the following steps: receiving first point cloud data from one or more RSUs located in a defined geographical area via a communication module; receiving second point cloud data from one or more on-board data processing units of vehicles located in the defined geographical area via the communication module; processing the first and second point cloud data via a processing module to generate processed point cloud data to identify potential blind spots within the defined geographical area; dividing the identified potential blind spots into multiple sub-areas via the processing module; and acquiring point cloud data corresponding to one or more sub-areas from the on-board data processing units of one or more designated vehicles located in the defined geographical area.

[0019] In a third key aspect, the present invention provides a road monitoring system. The system includes a communication module configured to receive first point cloud data from one or more designated RSUs among a plurality of RSUs located in a defined geographic area; and to receive second point cloud data from one or more designated on-board data processing units of vehicles located in the defined geographic area. The system also includes a processing module configured to process the received first and second point cloud data to generate processed point cloud data; wherein the processed point cloud data is transmitted via the communication module to one or more of the multiple RSUs and / or on-board data processing units of vehicles located in the defined geographic area.

[0020] In a fourth principal aspect, the present invention provides a road monitoring system. The system includes a memory for storing data and a processor for executing computer-readable instructions, wherein the processor is configured by the computer-readable instructions to implement the methods described in the first and / or second principal aspects.

[0021] This invention does not necessarily disclose all the features necessary to define the invention; the invention may exist in sub-combinations of the disclosed features. Attached Figure Description

[0022] The above and further features of the present invention will become apparent from the following description of preferred embodiments, which are provided by way of example only in conjunction with the accompanying drawings, wherein:

[0023] Figure 1 This is a schematic diagram illustrating an exemplary road condition;

[0024] Figure 2 This is a schematic diagram of a road monitoring system according to an embodiment of the present invention;

[0025] Figure 3 It is a display Figure 2 A flowchart illustrating the characteristics of a road monitoring system;

[0026] Figure 4 This is a flowchart of point cloud data processing according to an embodiment of the present invention;

[0027] Figure 5 This is a diagram showing the blind spot created when an obstacle enters the coverage area of ​​the RSU;

[0028] Figure 6 A flowchart illustrating the features of a road monitoring system according to another embodiment of the present invention;

[0029] Figure 7 This is a flowchart showing the allocation of CAV for data transmission. Detailed Implementation

[0030] The following description is merely an example of preferred embodiments and does not limit the combination of necessary features for carrying out the invention.

[0031] The phrase "one embodiment" or "an embodiment" as used in this specification means that a particular feature, structure, or characteristic related to that embodiment is included in at least one embodiment of the invention. The phrase "in one embodiment" appearing throughout the specification does not necessarily refer to the same embodiment, nor is it a single or alternative embodiment that is mutually exclusive with other embodiments. Furthermore, the various features described may be shown in some embodiments but not in others. Similarly, various requirements are described that may be requirements of some embodiments but not in others.

[0032] It should be understood that the components shown in the figure can be implemented in various forms of hardware, software, or a combination thereof. These components can be implemented in a combination of hardware and software on one or more appropriately programmed general-purpose devices, which may include processors, memory, and input / output interfaces.

[0033] This specification illustrates the principles of the invention. Therefore, it should be understood that those skilled in the art will be able to devise various arrangements, although not expressly described or shown herein, that embody the principles of the invention and are included within its spirit and scope.

[0034] Furthermore, this document describes the principles, aspects, and embodiments of the invention, along with specific examples thereof, and is intended to cover its structural and functional equivalents. Moreover, such equivalents include both currently known equivalents and those developed in the future, i.e., any developed element that performs the same function, regardless of its structure.

[0035] Therefore, for example, those skilled in the art will understand that the block diagrams presented herein represent conceptual diagrams of systems and devices embodying the principles of the present invention.

[0036] The functionality of the various components shown in the diagram can be provided using dedicated hardware and hardware capable of executing software together with appropriate software. When provided by a processor, these functions can be provided by a single dedicated processor, a single shared processor, or multiple separate processors, some of which may be shared. Furthermore, the explicit use of the terms "processor" or "controller" should not be construed as referring only to hardware capable of executing software, and may implicitly include, but is not limited to, digital signal processor ("DSP") hardware, read-only memory ("ROM"), random access memory ("RAM"), and non-volatile memory for storing software.

[0037] In the claims, any element referred to as a means of performing a particular function is intended to cover any manner in which that function is performed, including, for example, a) a combination of circuit elements performing that function or b) any form of software, thus including firmware, microcode, etc., combined with appropriate circuitry to perform the function. The invention as defined by these claims lies in the fact that the functions provided by the various mentioned means are combined and brought together in the manner claimed in the claims. Therefore, any means providing these functions is considered equivalent to the means shown herein.

[0038] Reference Figure 1The diagram illustrates an exemplary road condition or environment using a conventional road monitoring system. Conventional systems may include CAVs equipped with various sensors, the purpose of which includes, but is not limited to, collecting data for object detection, path planning, and vehicle control. In the context of this invention, the term "connected automated vehicle (CAV)" should be given a broad meaning to encompass any vehicle equipped with one or more onboard processing units that allow vehicle-to-everything (V2X) connectivity. Additionally, or alternatively, the system may include roadside infrastructure, such as a roadside unit (RSU), which may include static sensors, such as radar equipment, light detection and ranging (LiDAR) equipment, and / or cameras, as well as other communication equipment positioned in fixed locations (e.g., along the roadside) to provide connectivity and / or information support to nearby vehicles and / or other roadside connected agents. In particular, the RSU may be configured to collect data, such as point cloud data, and transmit the collected point cloud data via cellular vehicle-to-everything (C-V2X) channels to one or more servers, such as edge servers and / or remote servers. Figure 1 In the example scenario shown, the presence of vehicle "Car 1" on the road creates a blind spot for vehicle "Car-A". It would be dangerous if any pedestrian in or near this blind spot were to cross the road without the driver of vehicle Car-A being aware of or informed of their presence. Similarly, it would be unsafe if vehicle Car-A were to overtake vehicle Car-2, due to the limited field of vision provided by its own sensors, the obstruction of view caused by vehicle Car-2, and the upcoming road intersection.

[0039] refer to Figure 2 The road monitoring system 100 of the present invention relates to an infrastructure-based multi-agent cooperative perception system to effectively detect objects in blind spots and / or blind areas located on the road and / or on roadside connected agents. For example, the system 100 of the present invention can be effectively implemented in... Figure 1 In road environments, it has been found to significantly extend the field of view coverage provided by the vehicle's onboard processor and / or RSU. For example... Figure 1 The traffic conditions shown indicate that the communication module 110 of system 100 can be provided as one or more edge nodes 110, and can be configured to collect sensor data from multiple agents, including roadside CAVs and roadside infrastructure such as RSUs, to extend the coverage of traditional sensors. When the communication module 100 receives data from an RSU such as RSU 2 ( Figure 1When the communication module 110 detects data of a pedestrian in the blind spot of vehicle Car-A, it can send view information related to the blind spot to vehicle Car-A to avoid accidents. Similarly, before overtaking vehicle Car-2, vehicle Car-A can request view information ahead from the communication module 110 to ensure safety before overtaking.

[0040] System 100 may include one or more communication modules 110, which may be provided in the form of any processor unit, such as an edge node or other processing device. Specifically, communication module 110 is configured to receive first point cloud data from one or more designated RSUs 20A / B located within a defined geographic area. Communication module 110 is also configured to receive second point cloud data from one or more designated on-board data processing units 10A / B / C of vehicles 10 (which may be CAVs) located within the defined geographic area. System 100 also includes a processing module 120 for processing the received first and second point cloud data to generate processed point cloud data. In one embodiment, processing module 120 may be provided as one or more edge servers 120 and / or remote servers 120, or disposed at one or more edge servers 120 and / or remote servers 120. Preferably, the processing module 120 may be configured with one or more V2X platforms for processing and analyzing data received from one or more CAVs 10 and / or RSUs, as well as receiving and transmitting data and information between them. After the processing module 120 processes the point cloud data, the processed point cloud data is transmitted to the onboard data processing units 10A / B / C of one or more RSUs 20 and / or CAVs located within a defined geographical area via the communication module 110. In the context of this invention, roadside infrastructure such as RSUs may be arranged or configured with sensors such as radar equipment, light detection and ranging (LiDAR) equipment and / or cameras, as well as other communication devices, preferably in fixed locations, such as along the road, to provide connectivity and / or information support to nearby vehicles and / or other roadside connected agents. Preferably, the RSU is adapted to communicate with one or more CAV 10 and / or other connected agents via a V2X communication protocol, including receiving and transmitting data; the other connected agents include other RSUs of the same or different types and other processing devices, such as processing module 120; the V2X communication protocol includes one or more cellular vehicle-to-everything (C-V2X) channels. In particular, the RSU 20 can be configured to collect point cloud data and transmit the collected point cloud data to one or more servers, such as edge servers and / or remote servers, via C-V2X channels.

[0041] In such Figure 3In the illustrated embodiment, the communication module 110 may act as or include one or more edge nodes that can connect to each CAV 10 located in the geographic area to receive general location data, such as via one or more self-localization technologies, such as the Global Positioning System (GPS). When GPS data is unstable, for example when the region of interest is a highly dense area, which may affect the reception from GPS, the communication module 110 may additionally or optionally receive second point cloud data from the CAV 10 and first point cloud data from the RSU 20 of the geographic area. The received data is then processed and analyzed by the processing module 120 (e.g., an edge server 120 implementing a V2X platform) to identify any potential blind spots in traffic conditions or the environment. In one embodiment, the processing module 120 may be configured to divide the detected potential blind spots into multiple sub-regions or partitions, and preferably, into non-overlapping sub-regions or partitions. One or more of the multiple sub-regions may then be assigned to one or more surrounding agents within the geographic area, which may include one or more CAV 10s and / or RSU 20s. Communication module 110 sends a request to collect point cloud data from one or more CAVs 10 and / or RSUs 20, involving the assignment or distribution to corresponding or selected one or more sub-regions or partitions of one or more surrounding agents within the geographic area. The assignment of sub-regions or partitions to surrounding agents can be based on the estimated perception range of these agents and the network bandwidth according to their respective metadata. The point cloud of the requested sub-region is sent from the respective agents to communication module 110, where processing module 120 merges it with existing data to form a complete point cloud map representing a global view of the area. Communication module 110 then sends information derived from the integrated point cloud data (which may include guidance related to potential blind spots) to one or more CAVs 10 in the geographic area to enhance the perception capabilities of the CAVs 10. In one embodiment, a CAV may initiate a request for view information from edge node 110; alternatively, edge server 120 may automatically transmit view information to one or more CAVs that may be affected by detected blind spots based on its data analysis.

[0042] Upon receiving first point cloud data from the RSU and second point cloud data from the CAV, the received first and second point cloud data are compared and / or merged for data processing. Specifically, the first point cloud data received from RSU 20 and the second point cloud data received from CAV 10 are processed by processing module 120 to extract point clouds associated with one or more features of interest. Subsequently, the corresponding point clouds are compared, merged, and matched to determine any desired information, such as information for locating objects and / or to collect information related to potential blind spots. For example, in one embodiment, when GPS data is unstable, objects, such as the location of CAV 10, can be located and tracked based on point cloud registration. Figure 4 As shown.

[0043] In one embodiment, prior to transmission and based on a specific request from edge server 120, the first point cloud data received from RSU 20 and the second point cloud data received from CAV 10 can be partitioned or segmented according to fragments of the geographic region of interest. For example, potential blind spots in road conditions can be estimated by determining the location and shape of blind spots for each surrounding agent, including CAV 10 and RSU 20. The geographic region of interest can be divided into multiple non-overlapping partitions, for example, in the form of a Voronoi diagram, such as... Figure 5 As shown. The division of the region of interest reduces the size of the data to be transmitted, thereby increasing the transmission rate of received point cloud data from CAV 10 and RSU 20 to edge server 120. If the field of view of one RSU is blocked by one or more static obstacles, one or more other RSUs located in that area can extend their coverage area to the specific region. Dynamic blind spots of one or more CAV 10 and RSU 20 can be caused by any object entering the region of interest, and these dynamic blind spots can be further covered by the complete point cloud map generated by the processing module 120 of the edge server. Each CAV located in this geographic area or region of interest can send a polygon of the partitioned area associated with any potential blind spot to communication module 110.

[0044] In one embodiment, the communication module 110 may extract dynamic point clouds only from the second point cloud data of CAV 10 and / or the first point cloud data of RSU 20, and then merge them with the static point cloud data previously stored in the memory 130 of system 100, such as... Figure 2 As shown. For example, dynamic first point cloud data from the RSU can be extracted and then merged with previously detected static first point cloud data stored in memory 130. This significantly reduces the size of the transferable data, thereby improving the transmission speed.

[0045] Processing module 120 can collect point clouds from all RSUs and / or CAVs to process an initial point cloud map. The processed point cloud map is then segmented into multiple point cloud data partitions for further processing. Communication module 110 can then request supplementary point cloud data from one or more partitions or sub-regions of the CAVs in that area regarding one or more detected potential blind spots, for further merging to complete the full point cloud map. Information derived from the full point cloud map associated with the potential blind spots can then be transmitted to one or more affected CAVs and / or RSUs. Similarly, data transmission associated with partitions or sub-regions in the area can significantly reduce the size of the transmitted data and improve transmission speed.

[0046] Similar to the embodiments described above, the communication module 110 can identify one or more CAVs covering the detected blind spots of the RSU and request point cloud data from them for specific partitions corresponding to the blind spot regions. The point clouds of the requested partitions are then merged to complete a full point cloud map, obtaining a complete view of the region of interest. Figure 7 As shown, each CAV in the region will be assigned to collect point clouds corresponding to non-overlapping partitions of the region of interest. If multiple CAVs are identified in the region, the assignment will be based on the data transmission rate of the CAV and / or the distance between the CAV and the communication module 110. For example, CAVs with fast and stable networks that can collect denser point cloud data will be preferentially assigned for data transmission. Point cloud segments received from the assigned CAVs will be integrated with the processed point cloud to complete a full point cloud map. In one embodiment, each CAV may be assigned a certain number of data sub-parts, which also depends on its network bandwidth. Ideally, all CAVs are configured to complete data transmission substantially simultaneously, and then the processing module 120 periodically analyzes the integrated point cloud map by processing real-time data and existing data without waiting for all data segments to be received.

[0047] Figure 7 The process steps are illustrated, showing how one or more CAVs are assigned to provide point cloud data segments for partitioned blind areas. First, each non-overlapping sub-region associated with a potential blind area is assigned to a separate CAV within the geographic region of interest. The point cloud data size D of a CAV can be estimated as:

[0048]

[0049] Where c is a constant, r is the sensor resolution, and a d It is the area of ​​the subregion that has a discrete distance d from CAV.

[0050] The point cloud transfer time for each (i)CAV can be estimated in the following way:

[0051]

[0052] Where N is the network bandwidth of CAV.

[0053] Maximum transmission time t max It can be calculated using the following formula:

[0054]

[0055] For each overlapping sub-region that one or more CAVs may cover, the CAVs will be sorted in ascending order of the distance between the corresponding sub-region and the CAV.

[0056] This sub-area will first be allocated to the first CAV in the queue, and the corresponding data transfer time will be recalculated. If determined Less than or equal to the maximum transmission time t max ,Right now Processing module 120 will confirm the allocation and continue to the next sub-region. Otherwise, processing module 120 will repeat the previous steps for the next CAV in the queue. If all CAVs are found to have t c Both are greater than t max Then the processing module 120 will assign the sub-region of the overlapping region to the first CAV in the queue, and then update t. max .

[0057] It should be understood that all or any modules and / or units constituting system 100 may be implemented by machine code stored in a memory device and executable by a processor. In one embodiment, the invention may relate to a road monitoring system 100 for detecting road conditions. The system may include a memory 130 for storing data and a processor for executing computer-readable instructions, wherein the processor is configured by the computer-readable instructions, when executed, to perform the steps described above. In one embodiment, the road monitoring system 100 may be configured to include a vehicle-to-everything (V2X) system.

[0058] This invention provides an infrastructure-based multi-agent cooperative perception system for monitoring road conditions, particularly for detecting one or more potential blind spots or blind areas related to vehicles on the road, and subsequently providing affected vehicles with information related to these potential blind spots. Through this system, agents such as CAVs and / or RSUs can work collaboratively to detect objects in their blind spots and expand the vehicle's field of vision to avoid accidents. Generally, the size of a single point cloud frame is around 500KB to 2MB, and C-V2X services may require processing frequencies above 10Hz to process point cloud data. The advantage of this invention is that by using approximately 2 to 3 light poles as the infrastructure for RSUs, the amount of roadside point cloud data transmitted is significantly reduced to approximately 100KB to 500KB, and further, the size of the blind spot data requested by the CAV is reduced to approximately 10KB to 50KB. With this reduction in data transmission size, this invention can be used to support the collaboration of multiple agents to cover a larger perception area in real time.

[0059] The aforementioned modules, units, and devices can be implemented, at least partially, in software. Those skilled in the art will understand that the above can be implemented, at least partially, using general-purpose computer equipment or custom-made equipment.

[0060] In this document, various aspects of the methods and apparatus described herein can be executed on any device, including communication systems. The programmatic aspects of this technology can be considered as a “product” or “article,” typically carried or embodied in a machine-readable medium in the form of executable code and / or associated data. “Storage” media include any or all memory, or related modules thereof, of mobile stations, computers, processors, or similar devices, such as various semiconductor memories, tape drives, disk drives, etc., which can provide storage for software programming at any time. All or part of the software can sometimes be communicated via the Internet or various other telecommunications networks. For example, such communication can load software from one computer or processor to another. Therefore, another type of medium that can carry software elements includes light waves, radio waves, and electromagnetic waves, used, for example, at physical interfaces between local devices, via wired and optical terrestrial networks, and via various air links. Physical elements carrying such waves, such as wired or wireless links, optical links, etc., can also be considered as media carrying software. As used herein, unless limited to tangible, non-transitory “storage” media, the term “computer or machine-readable medium” refers to any medium involved in providing instructions to a processor for execution.

[0061] While the invention has been described and illustrated in detail in the accompanying drawings and the foregoing description, it should be considered illustrative rather than restrictive. It should be understood that exemplary embodiments are shown and described only and do not limit the scope of the invention in any way. It will be understood that any feature described herein can be used in any embodiment. The illustrative embodiments do not exclude each other or other embodiments not mentioned herein. Therefore, the invention also provides embodiments that include combinations of one or more of the illustrative embodiments described above. Modifications and variations can be made to the invention without departing from its spirit and scope; therefore, only the limitations set forth in the appended claims should be applied.

[0062] In the appended claims and the foregoing description of the invention, unless the context requires otherwise due to explicit language or necessary implication, the word "comprising" or variations such as "including" are used in an inclusive sense, that is, specifying the presence of the stated features but not excluding the presence or addition of further features in various embodiments of the invention.

[0063] It should be understood that if any prior art publications are mentioned in this document, such reference does not constitute an admission that such publications constitute part of common general knowledge in the art.

Claims

1. A road monitoring method, comprising: The first point cloud data is received from one or more designated roadside units (RSUs) among a plurality of roadside units located in a defined geographic area via the communication module. Second point cloud data is received from one or more designated on-board data processing units of vehicles located in the defined geographical area via the communication module, wherein the on-board data processing units of vehicles located in the defined geographical area are specified based on one of the following: 1) data transmission rate; 2) data transmission rate and distance from the communication module; The processing module processes the first point cloud data and the second point cloud data to generate processed point cloud data. Specifically, it processes the first point cloud data and the second point cloud data to extract point clouds related to one or more features of interest. Subsequently, the corresponding point clouds are compared, merged, and matched to determine information about the located object and / or collect information related to potential blind spots. Dynamic first point cloud data is extracted from the first point cloud data, and the extracted dynamic first point cloud data is compared and / or merged with the static first point cloud data stored in the memory before the processing steps, and then processed by the processing module. The processed point cloud data is divided into multiple non-overlapping point cloud data partitions or sub-regions; and The communication module transmits information derived from one or more selected point cloud data partitions to the onboard data processing unit of one or more RSUs and / or vehicles located within the defined geographical area.

2. The method according to claim 1, wherein the step of receiving the first point cloud data includes: Receive point cloud data relating to at least a portion of the defined geographic region from one or more designated RSUs located within the defined geographic region.

3. The method according to claim 2, wherein, At least a portion of the defined geographic region includes multiple non-overlapping sub-regions of the defined geographic region.

4. The method according to claim 1, wherein the step of receiving the second point cloud data includes: Point cloud data relating to at least a portion of the defined geographical area is received from one or more designated onboard data processing units of vehicles located within the defined geographical area.

5. The method of claim 4, wherein at least a portion of the determined geographic region comprises a plurality of non-overlapping sub-regions of the determined geographic region.

6. The method of claim 1, wherein the information derived from the processed point cloud data transmitted to the one or more RSUs and / or onboard data processing units via the transmission step comprises: Information relating to one or more blind spots of the one or more RSUs and / or the onboard data processing unit.

7. A method for detecting road blind spots, comprising: The first point cloud data is received from one or more roadside units (RSUs) located in a defined geographical area via a communication module. Second point cloud data is received from one or more on-board data processing units of a vehicle located in the defined geographical area via the communication module, wherein the on-board data processing unit of the vehicle located in the defined geographical area is specified based on one of the following: 1) data transmission rate; 2) data transmission rate and distance from the communication module; The processing module processes the first point cloud data and the second point cloud data to generate processed point cloud data, which is used to identify potential blind spots within the defined geographic area. Specifically, the first point cloud data and the second point cloud data are processed to extract point clouds associated with one or more features of interest. Subsequently, the corresponding point clouds are compared, merged, and matched to determine information about the located object and / or collect information related to potential blind spots. Dynamic first point cloud data is extracted from the first point cloud data, and the extracted dynamic first point cloud data is compared and / or merged with static first point cloud data stored in the memory before the processing steps, and then processed by the processing module. The processing module divides the identified potential blind spots into multiple non-overlapping sub-regions; and Point cloud data corresponding to one or more sub-regions among the plurality of sub-regions is received from one or more designated on-board data processing units of a vehicle located in the defined geographical area.

8. The method according to claim 7, further comprising: The point cloud data corresponding to one or more sub-regions are merged with the processed point cloud data to generate a complete point cloud map.

9. The method according to claim 8, further comprising: Information derived from the complete point cloud map is transmitted to one or more RSUs and / or onboard data processing units in the defined geographic area.

10. A road monitoring system, comprising: The communication module is set to receive: First point cloud data from one or more designated roadside unit (RSU) located within a defined geographic area; as well as Second point cloud data from the onboard data processing units of one or more designated vehicles located within the defined geographical area, wherein the onboard data processing units of the vehicles located within the defined geographical area are specified based on one of the following: 1) data transmission rate; 2) data transmission rate and distance from the communication module; and The processing module is configured to process the received first point cloud data and second point cloud data to generate processed point cloud data. Specifically, it processes the first point cloud data and the second point cloud data to extract point clouds associated with one or more features of interest. Subsequently, the corresponding point clouds are compared, merged, and matched to determine information about the located object and / or collect information related to potential blind spots. Dynamic first point cloud data is extracted from the first point cloud data, and the extracted dynamic first point cloud data is compared and / or merged with static first point cloud data stored in memory before the processing steps, and then processed by the processing module. The processing module is further configured to divide the processed point cloud data into multiple point cloud data partitions, the multiple point cloud data partitions corresponding to multiple non-overlapping sub-regions of the determined geographical region; One or more selected point cloud data partitions are transmitted via the communication module to the onboard data processing unit of one or more RSUs and / or vehicles located in the defined geographical area.

11. The system of claim 10, wherein the communication module is configured to receive and transmit point cloud data and information derived from the point cloud data from onboard data processing units of one or more RSUs and / or vehicles located within the defined geographical area via one or more cellular vehicle-to-everything (C-V2X) communication networks.

12. The system of claim 10, wherein the plurality of non-overlapping sub-regions are associated with one or more blind spots of the onboard data processing units of the one or more RSUs and / or vehicles located in the defined geographic region.

Images