Road facility tracking method and device based on vehicle motion characteristics

Abstract

This disclosure provides a road facility tracking method and apparatus based on vehicle motion characteristics in some embodiments. In one aspect, the disclosure provides a road facility tracking apparatus, comprising: a coordinate generation unit configured to generate initial coordinates based on the vehicle's position and multiple detection information items collected by radar included in the vehicle, the initial coordinates being used to update the tracking coordinates of the road facility; and a coordinate updating unit configured to update the tracking coordinates of the road facility in response to vehicle coordinates changing over time, based on the vehicle's motion characteristics. This road facility tracking method and apparatus has a guardrail tracking function based on guardrail initialization and a dynamic model, is capable of removing ghosting tracking based on guardrail detection information, and has the function of detecting tracking performance degradation based on guardrail detection information.

Description

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to Korean Patent Application No. 10-2021-0165621, filed on November 26, 2021, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] In some embodiments, this disclosure relates to a method and apparatus for tracking road infrastructure based on vehicle motion characteristics. Background Technology

[0004] The statements in this section are provided only as background information in connection with this disclosure and do not necessarily constitute prior art.

[0005] Radar (Radio Detection and Ranging) is a detection device that uses a transmitting antenna to emit radio waves and a receiving antenna to receive signals reflected from objects. Radar detects information about objects by using the time difference between the transmitted and received signals, as well as the Doppler shift of the received signal relative to the transmitted signal. For example, information about the object includes the relative distance between the signal source and the object, the relative velocity of the object relative to the signal source, and the angle of the object's direction of movement relative to the signal source.

[0006] In addition to detecting surrounding vehicles, automotive radar installed in vehicles also detects road infrastructure located around the vehicle. Typically, software applications integrated with the vehicle radar use tracking information about surrounding vehicles to estimate the distance between the vehicle and moving adjacent vehicles, as well as the relative speed of those adjacent vehicles. This software application can improve the tracking performance of surrounding vehicles by using tracking information about continuous structures, such as guardrails and tunnels. However, when the continuous structure is parallel to the vehicle's direction of movement, the relative distance between the structure and the vehicle is inversely proportional to the strength of the reflected signal. The reduced received signal strength reflected from the structure degrades the detection performance of that structure. The result is decreased accuracy and performance in tracking road infrastructure. Summary of the Invention

[0007] According to at least one embodiment, this disclosure provides a road infrastructure tracking device, including a coordinate generation unit and a coordinate updating unit. The coordinate generation unit is configured to generate initial coordinates based on the position of a vehicle and multiple detection information items collected by radar included in the vehicle, the generated initial coordinates being used to update the tracking coordinates of the road infrastructure. The coordinate updating unit is configured to update the tracking coordinates of the road infrastructure based on the motion characteristics of the vehicle and in response to vehicle coordinates changing over time.

[0008] According to another embodiment, this disclosure provides a method implemented by a road infrastructure tracking device, comprising: generating initial coordinates based on the position of a vehicle and multiple detection information collected by radar included in the vehicle, wherein the initial coordinates are used to update the tracking coordinates of the road infrastructure; and updating the tracking coordinates of the road infrastructure based on the motion characteristics of the vehicle and in response to vehicle coordinates changing over time.

[0009] According to yet another embodiment, this disclosure provides a vehicle including the road infrastructure tracking device. Attached Figure Description

[0010] Figure 1 This is a conceptual diagram illustrating the operation of a road infrastructure tracking device according to at least one embodiment of the present disclosure.

[0011] Figure 2 This is a block diagram of a road facility tracking device according to at least one embodiment of the present disclosure.

[0012] Figure 3A and 3B This is a schematic diagram of a road facility tracking device for tracking one or more guardrails according to at least one embodiment of the present disclosure.

[0013] Figure 4A , 4B 4C is a schematic diagram of a road facility tracking device updating guardrail coordinates that change over time according to at least one embodiment.

[0014] Figure 5A and 5B This is a schematic diagram illustrating the removal of ghost tracking by a road infrastructure tracking device according to at least one embodiment of the present disclosure.

[0015] Figure 6A Existing technical methods for tracking target vehicles are shown, while Figure 6B The invention illustrates how a road infrastructure tracking device according to at least one embodiment improves the accuracy of tracking target vehicles.

[0016] Figure 7 A flowchart is provided to illustrate step-by-step a road infrastructure tracking method according to at least one embodiment of the present disclosure.

[0017] Figure Labels

[0018] 100: Vehicles 102: Guardrails

[0019] 104: Detection Information 106: Viewpoint

[0020] 200: Road facility tracking device; 300: Detection area

[0021] 302: Static Detection Information Detailed Implementation

[0022] This disclosure aims to provide a road facility tracking method and a road facility tracking device in some embodiments, which have a guardrail tracking function based on guardrail initialization and a dynamic model.

[0023] This disclosure aims to provide a road facility tracking method and a road facility tracking device in some embodiments, which can remove ghosting tracking based on guardrail detection information.

[0024] In some embodiments, this disclosure aims to provide a road facility tracking method and a road facility tracking device, which has the function of detecting the degradation of tracking performance based on guardrail detection information.

[0025] The problems to be solved by this disclosure are not limited to those described above, and other unmentioned problems will become clear to those skilled in the art from the following description.

[0026] In the following description, some embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the following description, the same reference numerals preferably denote the same elements, although these elements are shown in different drawings. Furthermore, in the following description of some embodiments, for the purpose of clarity and brevity, detailed descriptions of related known components and functions that would be considered to obscure the subject matter of the present disclosure will be omitted.

[0027] Furthermore, terms such as first, second, A, B, (a), (b), etc., are used only to distinguish one component from another and do not imply or indicate the substance, order, or sequence of the components. Throughout the specification, unless specifically stated to the contrary, when a component "includes" or "comprises" a component, it means that the component also includes other components, not excludes other components. Terms such as "unit" and "module" refer to one or more units used to perform at least one function or operation that can be implemented by hardware, software, or a combination thereof.

[0028] This disclosure provides a method and apparatus for tracking road infrastructure based on vehicle motion characteristics. For example, the road infrastructure tracking apparatus according to at least one embodiment of this disclosure can remove ghosting targets generated due to speed ambiguity or detection performance degradation. Therefore, the road infrastructure tracking apparatus can provide improved detection performance for road infrastructure located around a vehicle.

[0029] In this disclosure, software applications refer to advanced driver assistance systems (ADAS), such as rear side collision warning (Blind-Spot Collision Warning (hereinafter referred to as "BCW") or rear cross-traffic collision warning (hereinafter referred to as "RCCW").

[0030] In this disclosure, road facilities refer to facilities installed on a road in a direction parallel to the direction of vehicle travel, such as guardrails or tunnel walls.

[0031] The detailed description set forth below with reference to the accompanying drawings is intended to describe exemplary embodiments of the present disclosure and is not intended to represent only embodiments in which the present disclosure may be practiced.

[0032] Figure 1 This is a conceptual diagram illustrating the operation of a road infrastructure tracking device according to at least one embodiment of the present disclosure.

[0033] A road facility tracking device according to at least one embodiment is installed in a vehicle 100 and tracks road facilities using radio signals reflected from external objects. For example, the road facility tracking device tracks the position of a guardrail 102 based on detection information 104 present within the field of view (FOV). This embodiment assumes the road facility is a guardrail 102 or a tunnel wall to illustrate the operation of the road facility tracking device. However, the specific type of road facility is not limited to the embodiments shown in this disclosure. The road facility tracking device tracks changes in the relative distance between the vehicle 100 and the guardrail 102 due to the movement of the vehicle 100.

[0034] Figure 2 This is a block diagram of a road facility tracking device 200 according to at least one embodiment of the present disclosure.

[0035] The road facility tracking device 200 according to at least one embodiment includes a processor (e.g., a computer, microprocessor, CPU, ASIC, electronic circuit, logic circuit, etc.) and a related non-transient memory storing software instructions that, when executed by the processor, provide all or part of the functions of the coordinate generation unit 202, the coordinate update unit 204, the ghost removal unit 206, and the detection information classification unit 208. Figure 2 The road facility tracking device 200 shown is according to at least one embodiment of this disclosure, and is not... Figure 2All the frames shown are essential components; in another embodiment, some frames included in the road facility tracking device 200 may be added, modified, or deleted. The various components included in the road facility tracking device 200 may be logic components for operating control logic. Here, the memory and processor may be implemented as separate semiconductor circuits. Alternatively, the memory and processor may be implemented as a single integrated semiconductor circuit. The processor may be embodied as one or more processors.

[0036] The following reference Figure 2 The various components included in the road facility tracking device 200 are described below.

[0037] Based on the position of vehicle 100 and multiple detection information items 104 collected by radar included in vehicle 100, coordinate generation unit 202 generates initial coordinates for updating the tracking coordinates of road facilities. For example, coordinate generation unit 202 generates detection information corresponding to the object closest to the radar in the broadside direction as the initial coordinates. The broadside direction refers to the direction perpendicular to the travel direction of vehicle 100.

[0038] When detecting objects with a high signal-to-noise ratio (SNR), radar typically exhibits high estimation performance for the object's range, angle, and velocity. Among objects with the same radar cross-section (RCS), those closer to the vehicle have a higher SNR. Therefore, for nearby targets with the same RCS, radar provides the target object's position and velocity with high estimation accuracy. In addition to SNR, radar can also calculate and generate the object's position based on its range and angle information. However, even when the object is positioned at the same angle relative to the radar, the positioning error increases significantly as the object's distance from the radar increases. Therefore, the road infrastructure tracking device 200 initializes itself by using short-range detection of guardrails approaching the vehicle.

[0039] Based on the vehicle's motion characteristics, the coordinate update unit 204 updates the tracking coordinates of the road infrastructure in response to the vehicle coordinates changing over time. For example, the coordinate update unit 204 uses the vehicle coordinates and the tracking coordinates of the road infrastructure before a preset detection time interval as a basis to calculate the changed vehicle coordinates. The coordinate update unit 204 updates the tracking coordinates using the direction cosine matrix and the difference between the changed vehicle coordinates and the tracking coordinates of the road infrastructure before the preset detection time interval.

[0040] The coordinate update unit 204 determines the tracking coordinates of the guardrail using radio signals based on multiple collected detection information items. When the lateral distance of the detection information corresponding to the object closest to the vehicle coordinate reference in the wide-side direction is less than a preset maximum distance d... t When the coordinate update unit 204 determines that road facilities exist, the lateral distance of the detection information corresponding to the nearest object is greater than the preset minimum distance d. min When a road facility is detected, the coordinate update unit 204 sets up a detection area for tracking the road facility. Simultaneously, when no road facility is detected, the coordinate update unit 204 determines whether the detection information present in the width direction is stationary. When stationary detection information is detected in the width direction, the coordinate update unit 204 sets up the detection area. The coordinate update unit 204 counts and outputs the total number of detection information items and the number of stationary detection information items in the detection area. When the number of stationary detection information items is greater than a preset standard number and the ratio of the number of stationary detection information items to the total number of detection information items is greater than a preset standard ratio, the coordinate update unit 204 determines the tracking coordinates based on linear regression. When determining the tracking coordinates based on linear regression, the coordinate update unit 204 determines the ordinate of the road facility as the ordinate of the radar included in the vehicle. The coordinate update unit 204 determines the average abscissa of the stationary detection information items present in the detection area as the abscissa of the road facility.

[0041] Based on the updated tracking coordinates, the ghosting removal unit 206 removes ghosted targets existing outside the road facilities. Based on multiple detection information items, the ghosting removal unit 206 generates a linearized road facility section to identify ghosted targets. The ghosting removal unit 206 extracts the boundary coordinates corresponding to the ordinates in the new detection information on the linearized road facility section. The ghosting removal unit 206 compares the abscissas in the new detection information with the abscissas in the boundary coordinates. For example, to track the left guardrail relative to the driving direction of vehicle 100, the ghosting removal unit 206 checks whether the abscissa in the new detection information is greater than the abscissa in the boundary coordinates, and if so, the ghosting removal unit 206 identifies the new detection information as a ghosted target. Here, it is assumed that the abscissa on the coordinate axis is positive on the left relative to the driving direction of vehicle 100.

[0042] The detection information classification unit 208 classifies detection information located outside of road facilities into either detection information of interest or ghosting targets. The ghosting removal unit 206 excludes detection information classified as ghosting targets by the detection information classification unit 208 from the measurement update information.

[0043] Figure 3A and 3B This is a schematic diagram of a road facility tracking device 200 for tracking one or more guardrails according to at least one embodiment of the present disclosure.

[0044] like Figure 3A As shown, the road infrastructure tracking device 200 included in vehicle 100 tracks the position of guardrail 102 based on detection information 104. The Doppler velocity v of the detection information of vehicle 100 relative to guardrail 102 is collected at time t. d This is represented by Equation 1. Here, v h This represents the vehicle's speed. θ represents the vector of the vehicle's direction of movement and the vehicle's detection information x. t The estimated angle between the direction vectors.

[0045]

[0046] Because the guardrail is a continuous structure installed on the road, it can be considered a stationary target. The Doppler velocity of this stationary target is determined by the estimated angle of the stationary target. Therefore, when the Doppler information of an object at the estimated position is within a preset threshold range, the detected object can be identified as a stationary target. Here, the threshold range is determined by the capacity of the radar sensor. In at least one embodiment, the vehicle coordinate plane can be set to have an x-axis and a y-axis, with the x-axis representing the vehicle's travel direction and the y-axis representing the direction toward the left guardrail and perpendicular to the vehicle's travel direction. Because vehicles typically travel in a direction almost parallel to the guardrail, when the radar uses the guardrail for detection, it can obtain detection information items with similar component values ​​in the y-axis direction. When the radar uses the guardrail for detection, the guardrail may be incorrectly identified as a moving target due to errors in the angle information generated by the Doppler effect. To eliminate this misjudgment, the road facility tracking device 200 tracks the guardrail 102 based on the number of stationary detection information items.

[0047] like Figure 3B As shown, the road facility tracking device 200 uses stationary detection information items 302 included in the detection area 300 to track the guardrail 102. When the road facility tracking device 200 tracks the guardrail 102, the detection information in the wide-side direction has the highest reliability, and the detection information in the wide-side direction is frequently detected among other detection information in each direction. Therefore, the road facility tracking device 200 uses the detection information items 302 in the wide-side direction as a reference to track the guardrail 102. The road facility tracking device 200 checks whether the number of stationary detection information items 302 in the detection area 300 along the wide-side direction is greater than a preset reference number, and checks whether the ratio of the number of stationary detection information items 302 to the total number of detection information items is greater than a preset reference ratio. If so, it determines the tracking coordinates based on linear regression. Simultaneously, the coordinates of the i-th stationary detection information among the multiple stationary detection information items 302 collected in the preset detection area 300 are... It can be represented by the following equation 2.

[0048]

[0049] When determining tracking coordinates based on linear regression, the road infrastructure tracking device 200 can determine the longitudinal coordinate X of the radar included in the vehicle 100. FR The vertical coordinate of guardrail 102 is determined. The road facility tracking device 200 can determine the horizontal coordinate of multiple static detection information items 302 existing in the detection area 300. The average value is determined as the x-coordinate of guardrail 102. The y-coordinate of guardrail 102 is... and x-axis This can be represented by Equation 3. The tracking point interval of guardrail 102 is set considering the calculability and memory of the road facility tracking device 200. This tracking point interval can be expressed as d. GR .

[0050]

[0051]

[0052] Figure 4A , 4B 4C is a schematic diagram of a road facility tracking device 200 updating guardrail coordinates that change over time according to at least one embodiment.

[0053] The following describes an embodiment of the road infrastructure tracking device 200 using a motion model of its own vehicle to update the position of the guardrail.

[0054] exist Figure 4A In the context of time t being 0, vehicle 100 is currently traveling in a direction parallel to guardrail 102. Figure 4B In this context, when the update period is defined as Δt, the position of the ego vehicle is shown as having changed after Δt. The change in position can be calculated using the relationship between the ego vehicle's speed and yaw rate. However, since the origin of the vehicle coordinate plane is the current position of vehicle 100, the road facility tracking device 200 needs to update the position information of guardrail 102 as vehicle 100 moves. For example, based on the vehicle 100's current position and direction of movement, which have changed over time, the road facility tracking device 200 updates the guardrail position information included in the previously collected detection information 104. Meanwhile, targets farther from vehicle 100 than a preset detection distance may cause larger errors in the detection information. When updating the guardrail position information, the road facility tracking device 200 determines that the absolute position of the target estimated at short distances has not changed. The road facility tracking device 200 only updates the relative position of the target with respect to the position of vehicle 100, which has changed due to movement.

[0055] Figure 4CThe diagram illustrates the change in the vehicle's position before and after a time interval. Since vehicle 100 is moving while guardrail 102 is stationary, the coordinates of guardrail 102 relative to vehicle 100 change in real time. Therefore, it is necessary to ensure that the relative position of guardrail 102 conforms to the motion characteristics of vehicle 100. Here, it is assumed that the velocity change of vehicle 100 is 0 at times k and k+1. The angular velocity of vehicle 100 can be represented by equations 4A and 4B. Here, T represents the time interval for collecting the vehicle's position information. The radius of curvature of vehicle 100 can be represented by equation 4C. When vehicle 100 is in state k, the linear velocity vector and angular velocity vector of vehicle 100 can be represented by equations 4D and 4E.

[0056]

[0057]

[0058]

[0059]

[0060]

[0061] Figure 4C The position coordinates of guardrail 102 can be represented by equation 5A. The vehicle position at time k+1 relative to the vehicle position at time k is shown in equation 5B. The vehicle velocity at time k+1 relative to the vehicle velocity at time k is shown in equation 5C. The vehicle position and vehicle velocity at time k+1 are shown in equations 5D and 5E. Here, the velocity v in the x-axis direction of vehicle 100 can be changed. x .

[0062]

[0063]

[0064]

[0065]

[0066]

[0067] The coordinates of the guardrail 102 at time k+1 can be calculated according to equation 6A. Here, the direction cosine matrix R(θ) is shown in equation 6B.

[0068]

[0069]

[0070] Figure 5A and 5B A schematic diagram illustrating the removal of ghosting tracking by a road infrastructure tracking device 200 according to at least one embodiment of the present disclosure.

[0071] exist Figure 5A The image shows a vehicle 402 in the oncoming lane and a ghost target 404, which can lead to radar performance degradation. When using a radar system to detect targets, clutter or degradation in detection performance can cause ghost targets 404 at short or long ranges. Clutter refers to the signal received by the radar after being reflected by an object that is not of interest. In this disclosure, ghost targets 404 include a target that exists outside guardrail 102, such as a vehicle 402 traveling in the oncoming lane. Oncoming lane vehicle 402 is the most frequent target that the radar system does not need to track. Ghost targets 404 are prone to causing false alarms in BCW or RCCW (Blind Spot Collision Warning or Rear Cross-Traffic Collision Warning) software applications. Ghost targets 404 also cause unnecessary tracking by software applications, thus significantly increasing computational complexity. Therefore, the road facility tracking device 200 excludes ghost targets 404, which are not of interest, from the measurement update information as vehicle 100 is traveling, thereby solving the undesirable increase in computational complexity of the software application. The process of excluding detection information classified as ghost targets 404 when the road infrastructure tracking device 200 updates its measurements can be referred to as ghost tracking removal. Detection information of interest 400 is displayed to indicate targets present in the driving direction of the vehicle 100 or targets approaching the vehicle 100. The road infrastructure tracking device 200 prevents software application malfunctions by removing ghost tracking 406, thereby ensuring the driving safety of its own vehicle.

[0072] Figure 5B The static detection information items 104_A and 104_B used for linearization are shown. For example, the static detection information item... and The intervals between them can be set to several meters, and the curvature of that interval can be ignored. The road facility tracking device 200 generates data passing through... and The road infrastructure section. The equation of the straight line of this road infrastructure section is shown in equation 7A. The road infrastructure tracking device 200 extracts the boundary coordinates 404 corresponding to the ordinate of the new detection information 104. The boundary coordinates 404 and the abscissa in the boundary coordinates are shown in equations 7B and 7C.

[0073]

[0074]

[0075]

[0076] After performing data association processing on the new detection information 104, the road facility tracking device 200 filters and predicts targets within the detection information. For example, when tracking the left guardrail, the road facility tracking device 200 checks the horizontal coordinate y in the new detection information 104. G Is it greater than the x-coordinate in boundary coordinate 404? And if so, it determines the new detection information 104 as a ghost target. Just as when determining a ghost target for the left guardrail, the road facility tracking device 200 checks whether the abscissa in the new detection information has a value less than the abscissa in the boundary coordinates, and if so, it can determine the new detection information as a ghost target. The road facility tracking device 200 filters the new detection information 104 that is classified as a ghost target. For example, the road facility tracking device 200 can improve the tracking accuracy of the target of interest by excluding the new detection information 104 from the measurement update information.

[0077] Figure 6A Existing technical methods for tracking target vehicles are shown, while Figure 6B The invention illustrates how a road infrastructure tracking device according to at least one embodiment improves the accuracy of tracking target vehicles.

[0078] Figure 6A This illustrates a scenario where errors occur in the detection information of interest due to the persistent presence of ghosting targets. Radar systems emit radio waves in outdoor road environments and track target vehicles based on signals reflected from them. However, when radar detects target vehicles in tunnels, detection performance can degrade due to multipath interference. For example, in addition to the target vehicle, the radio waves emitted from the radar may also be scattered by the tunnel walls. The radar receives the scattered multipath signals and detects the target vehicle based on the received signals. Compared to radar performance in outdoor road environments, this significantly increases the target vehicle localization error and the frequency of software application failures. Software application failures can result in warnings becoming silent even when the target vehicle is approaching the vehicle. Such software application failures can even highly jeopardize the safety of vehicle occupants due to the lack of warning of the risk of collision with the target.

[0079] However, Figure 6B A road facility tracking device 200 according to at least one embodiment of the present disclosure is shown using guardrail tracking technology to solve the problem of detection performance degradation due to multipath interference. For example, when tracking a target vehicle, the road facility tracking device 200 excludes detection information existing outside the guardrail from the measurement update information. Because the road facility tracking device 200 excludes detection information existing outside the guardrail, the problem of inaccurate tracking point movement when updating detection information can be solved.

[0080] Figure 7 A flowchart is provided to illustrate step-by-step a road infrastructure tracking method according to at least one embodiment of the present disclosure.

[0081] The following reference Figure 7 This describes the individual steps of the road facility tracking method implemented by the road facility tracking device 200. (and) Figure 1 -6 Duplicate descriptions will be omitted.

[0082] The coordinate generation unit 202 initializes the parameters (S700). For example, based on the vehicle's position and multiple detection information items 104 collected by the radar included in the vehicle, the coordinate generation unit 202 generates initial coordinates for updating the tracking coordinates of the road facilities.

[0083] The coordinate update unit 204 updates the location information of the road facilities (S702). In some embodiments, step S702 is an operation performed after steps S704 to S712.

[0084] The coordinate generation unit 202 sets the lateral position of the road facility closest to the vehicle in the wide-side direction as the abscissa Y in the detection information for tracking the guardrail 102. g (S704).

[0085] Coordinate update unit 204 checks whether the lateral distance of the detection information corresponding to the nearest object in the width direction is less than the preset maximum distance d. t If so, it determines that road facilities exist and declares the GR value as 1 (S706). Here, GR refers to the variable used to determine whether guardrail 102 exists. When it is determined that the guardrail does not exist, coordinate update unit 204 declares the GR value as 0.

[0086] Coordinate update unit 204 determines whether the GR value has a value greater than 0 (S708), and if so, it updates the x-coordinate Y. g The absolute value and the preset minimum distance value d min Compare (S710). When the x-coordinate Y... g The absolute value is equal to or less than the preset minimum distance value d min At that time, coordinate update unit 204 repeats steps S702 to S712.

[0087] The coordinate update unit 204 checks whether the GR value is less than or equal to 0 (S708), and if so, it determines whether the stationary detection information 104 exists in the wide side direction (S712). When there is no stationary detection information in the wide side direction, the coordinate update unit 204 repeats steps S702 to S712.

[0088] When the x-coordinate value Y gThe absolute value is greater than the preset minimum distance value d min When the static detection information 104 exists in the wide side direction, the coordinate update unit 204 updates the coordinates based on the horizontal coordinate value Y. g Set the detection area to 300 (S714).

[0089] Coordinate update unit 204 counts and generates the total number N of detection information items present in detection region 300. T The number of static detection information items N ST (S716).

[0090] Coordinate update unit 204 determines the number N of static detection information items. ST Is it greater than the preset reference quantity N? Th And the number N of static detection information items. ST The total number of detection information items N T Is the ratio greater than the preset reference ratio (S718)? When the number N of static detection information items is N ST Less than or equal to the preset reference quantity N Th The number of static detection information items N ST The total number of detection information items N T When the ratio is less than or equal to the preset reference ratio, the coordinate update unit repeats steps S702 to S718.

[0091] When the conditions of step S718 are met, the coordinate update unit 204 determines the tracking coordinates based on linear regression (S720).

[0092] Although this disclosure presents flowcharts in which the steps are shown to be performed sequentially, they are merely illustrative of the technical concepts of some embodiments of this disclosure. Therefore, those skilled in the art will make various modifications, additions, and substitutions in practicing this disclosure by changing the order of the steps described in the flowcharts or by implementing one or more steps in the flowcharts in parallel, and thus the steps in the flowcharts are not limited to the temporal order shown.

[0093] Various embodiments of the apparatus and methods described herein can be implemented using digital electronic circuits, integrated circuits, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These different embodiments may include those implemented in one or more computer programs executable on a programmable system. The programmable system includes: at least one programmable processor coupled to receive data and instructions from a storage system and to transfer data and instructions to the storage system; at least one input device; and at least one output device; wherein the programmable processor may be a dedicated processor or a general-purpose processor. The computer program (also referred to as a program, software, software application, or code) contains instructions for the programmable processor and is stored in a computer-readable recording medium.

[0094] Computer-readable recording media include any type of recording device on which data that can be recorded can be read by a computer system. Examples of computer-readable recording media include, for example, non-volatile or non-transient media such as ROM, CD-ROM, magnetic tape, floppy disk, memory card, hard disk, optical disk / magnetic disk, and storage devices. Furthermore, computer-readable recording media can be distributed across computer systems connected via a network, where computer-readable code can be distributed for storage and execution.

[0095] Various embodiments of the apparatus and methods described herein can be implemented using a programmable computer. Here, a computer includes a programmable processor, a data storage system (including volatile memory, non-volatile memory, or any other type of storage system, or a combination thereof), and at least one communication interface. For example, the programmable computer may be one of a server, network device, set-top box, embedded device, computer expansion module, personal computer, laptop computer, personal data assistant (PDA), cloud computing system, and mobile device.

[0096] According to at least one embodiment, this disclosure provides a road facility tracking method and a road facility tracking apparatus that can remove short-range ghosting tracking caused by ambiguity in speed information about surrounding objects.

[0097] According to at least one embodiment, this disclosure provides a road facility tracking method and a road facility tracking device that can eliminate long-distance ghosting tracking caused by the deterioration of radar detection performance.

[0098] According to at least one embodiment, this disclosure provides a road facility tracking method and a road facility tracking device, which can reduce computational workload by excluding detection information of vehicles passing by the vehicle in the opposite direction from the vehicle itself from the measurement update information.

[0099] Although exemplary embodiments of this disclosure have been described for illustrative purposes, those skilled in the art will understand that various modifications, additions, and substitutions are possible without departing from the concept and scope of the claimed invention. Therefore, exemplary embodiments of this disclosure have been described for the sake of brevity and clarity. The scope of the technical concept of the embodiments of this disclosure is not limited by the description. Therefore, those skilled in the art will understand that the scope of the claimed invention is not limited to the embodiments explicitly described above.

Claims

1. A road infrastructure tracking device, comprising a processor, the processor being configured to: Initial coordinates are generated based on the vehicle's location and multiple detection information items collected by radar included in the vehicle. These initial coordinates are used to update the tracking coordinates of road infrastructure. Based on the vehicle's motion characteristics and in response to the vehicle's coordinates changing over time, the tracking coordinates of the road infrastructure are updated. in, The processor is also configured to: Detection information corresponding to the object closest to the radar in the wide side direction perpendicular to the vehicle's direction of travel is generated as the initial coordinates; When the lateral distance of the detection information is less than the preset maximum distance, it is determined that the road facility exists, and the detection information corresponds to the object closest to the vehicle coordinates in the wide side direction; When the lateral distance of the most recent detected information is greater than a preset minimum distance, a detection area for tracking the road facility is set. Count and output the total number of detection information items present in the detection area and the number of stationary detection information items in the detection area; When the number of stationary detection information items is greater than a preset reference number and the ratio of the number of stationary detection information items to the total number of detection information items is greater than a preset reference ratio, the tracking coordinates are determined based on linear regression. The processor is further configured as follows: When it is determined that no road facilities exist, it is determined whether the detection information present in the wide side direction is stationary detection information; and When it is determined that the static detection information exists in the wide side direction, the detection area is set.

2. The apparatus according to claim 1, wherein, The processor is also configured to: The vehicle coordinates before the preset detection time interval and the tracking coordinates of the road facilities before the preset detection time interval are used as a basis to calculate the vehicle coordinates that have changed relative to the vehicle coordinates before the preset detection time interval. and The tracking coordinates are updated using the direction cosine matrix and the difference between the changed vehicle coordinates and the tracking coordinates of the road facility before the preset detection time interval.

3. The apparatus according to claim 1, wherein, The processor is also configured to: When the tracking coordinates are determined based on linear regression, the longitudinal coordinate of the radar included in the vehicle is determined as the longitudinal coordinate of the road infrastructure; and The average value of the abscissas of the static detection information items existing in the detection area is determined as the abscissa of the road facility.

4. The apparatus of claim 1, wherein the processor is further configured to exclude ghosting targets existing outside the road infrastructure from the measurement update information based on the updated tracking coordinates.

5. The apparatus according to claim 4, wherein, The processor is also configured to: A linearized road infrastructure section is generated based on the multiple detection information items; Extract the boundary coordinates on the linearized road infrastructure section that correspond to the ordinate in the new detection information; The horizontal coordinates included in the new detection information are compared with the horizontal coordinates included in the boundary coordinates; and When the horizontal coordinate in the new detection information is greater than the horizontal coordinate in the boundary coordinates, the new detection information is determined to be a ghost target of road facilities located on the left side of the vehicle.

6. The apparatus of claim 1, wherein the processor is further configured to classify detection information determined to exist outside the road infrastructure as detection information of interest or ghosting targets.

7. A method implemented by a road infrastructure tracking device, comprising: Initial coordinates are generated based on the vehicle's location and multiple detection information items collected by radar included in the vehicle. These initial coordinates are used to update the tracking coordinates of road infrastructure. and Based on the vehicle's motion characteristics and in response to the vehicle's coordinates changing over time, the tracking coordinates of the road infrastructure are updated. Generating the initial coordinates includes: Detection information corresponding to the object closest to the radar in the wide side direction perpendicular to the vehicle's direction of travel is generated and used as the initial coordinates. Updating the tracking coordinates includes: When the lateral distance of the detection information is less than the preset maximum distance, it is determined that the road facility exists, and the detection information corresponds to the object closest to the vehicle coordinates in the wide side direction; When the lateral distance of the most recent detected information is greater than a preset minimum distance, a detection area for tracking the road facility is set. Calculate the total number of detection information items present in the detection area and the number of stationary detection information items in the detection area; When the number of stationary detection information items is greater than a preset reference number and the ratio of the number of stationary detection information items to the total number of detection information items is greater than a preset reference ratio, the tracking coordinates are determined based on linear regression. Updating the tracking coordinates further includes: When it is determined that no road facilities exist, it is determined whether the detection information present in the wide side direction is stationary detection information; and When it is determined that the static detection information exists in the wide side direction, the detection area is set.

8. The method according to claim 7, wherein, Updating the tracking coordinates includes: Based on the vehicle coordinates prior to the preset detection time interval and the tracking coordinates of the road infrastructure prior to the preset detection time interval, calculate the changed vehicle coordinates relative to the vehicle coordinates prior to the preset detection time interval; and The tracking coordinates are updated using the direction cosine matrix and the difference between the changed vehicle coordinates and the tracking coordinates of the road facility before the preset detection time interval.

9. The method according to claim 7, wherein, Updating the tracking coordinates also includes: When the tracking coordinates are determined based on linear regression, the longitudinal coordinate of the radar included in the vehicle is determined as the longitudinal coordinate of the road infrastructure; and The average value of the abscissas of the static detection information items existing in the detection area is determined as the abscissa of the road facility.

10. The method of claim 7, further comprising: Based on the updated tracking coordinates, ghosting targets existing outside the road infrastructure are excluded from the measurement update information.

11. The method according to claim 10, wherein, Excluding the ghosted targets includes: A linearized road infrastructure section is generated based on the multiple detection information items; Extract the boundary coordinates on the linearized road infrastructure section that correspond to the ordinate in the new detection information; The horizontal coordinates included in the new detection information are compared with the horizontal coordinates included in the boundary coordinates; and When the horizontal coordinate in the new detection information is greater than the horizontal coordinate in the boundary coordinates, the new detection information is determined to be a ghost target of road facilities located on the left side of the vehicle.

12. The method of claim 7, further comprising: Detection information identified outside the road infrastructure will be classified as either detection information of interest or ghosting targets.

13. A vehicle comprising: The road facility tracking device according to any one of claims 1-6.

Images