Apparatus and method for determining the position of an object sensed by radar using spatial voxelization

Abstract

According to the present disclosure, a radar sensing file in which a reflected signal obtained by receiving a radio wave signal transmitted by a radar and reflected by an object is stored is loaded, a voxel corresponding to the position of a point stored in the radar sensing file is searched, and the reflected signal intensity of the point is accumulated and stored in the voxel ID of the searched voxel to generate a dictionary; a voxelization step, the radar sensing file is loaded, a voxel corresponding to the position of a point stored in the radar sensing file is searched, and when the ID of the searched voxel is the same as the voxel in which the accumulated value of the reflected signal intensity is the largest in the dictionary, the position coordinates of the point are separately stored; a point extraction step, and based on the position coordinates of the separately stored points, a step of determining the position of a reference point serving as a calibration reference are included, and a method for determining the position of an object sensed by a radar using spatial voxelization is provided, and the reference point of the radar for calibration can be accurately determined.

Description

Technical Field

[0001] The present disclosure relates to an apparatus and a method for determining the position of an object sensed by a radar using spatial voxelization.

Background Art

[0002] A radar outputs a radio wave signal and receives the signal reflected by an object. Depending on the characteristics of the object surface, the radio wave signal is reflected in various directions and intensities. When various objects exist in space, the reflected signals may be received in various directions and intensities. Therefore, complex calculations must be performed to analyze the reflected signals received by the radar and select the position of the object.

[0003] On the other hand, with the development of autonomous driving related technologies, technologies for calibrating sensors such as radars, lidars, and cameras are under development. Calibration is to adjust the radar, lidar, and camera so that they recognize the position of a specific object as the same position. In the calibration process, the radar has a problem that it is difficult to obtain the position of a specific object based on the characteristics that the reflected signals are received in various directions and intensities. Such characteristics require that no other objects exist in the space where calibration is performed. Therefore, space and other tools are required for calibration.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure provides an apparatus and a method for determining the position of an object sensed by a radar using spatial voxelization.

Means for Solving the Problem

[0006] A method for determining the position of an object sensed by radar using spatial voxelization according to the present disclosure loads a radar sensing file that receives and stores a reflected signal obtained by reflecting a radio wave signal transmitted by the radar from the object, searches for voxels corresponding to the positions of the points stored in the radar sensing file, and accumulates and stores the reflected signal intensity of the points in the voxel IDs of the searched voxels to generate a dictionary in a voxelization stage, loads the radar sensing file, searches for voxels corresponding to the positions of the points stored in the radar sensing file, and separately stores the position coordinates of the points when the ID of the searched voxel is the same as the voxel in the dictionary in which the accumulated value of the reflected signal intensity is the largest in a point extraction stage, and may include a stage of determining the position of a reference point serving as a calibration reference based on the separately stored position coordinates of the points.

[0007] According to one embodiment, the radar sensing file may be generated by the radar receiving a reflected signal and storing the position coordinates and the reflected signal intensity of the points in the form of point cloud data.

[0008] According to one embodiment, the voxelization stage may include a stage of setting parameters including a voxel size, a lower threshold value and an upper threshold value of the reflected signal intensity, and a spatial range for generating a voxel grid, a filtering stage of excluding points whose reflected signal intensity of the points is not included in the range from the lower threshold value to the upper threshold value, a stage of generating a voxel grid based on the voxel size and the spatial range, and a stage of searching for voxels corresponding to the positions of the points stored in the radar sensing file from the voxel grid, and accumulating and storing the reflected signal intensity of the points in the voxel IDs of the searched voxels to generate a dictionary.

[0009] According to one embodiment, the step of generating the dictionary includes searching for a voxel corresponding to the position of the point stored in the radar sensing file from the voxel grid, determining whether the voxel ID of the searched voxel exists in the dictionary, and when the voxel ID of the searched voxel does not exist in the dictionary, adding the voxel ID of the searched voxel to the dictionary, storing the reflected signal intensity in the voxel ID, storing the count of the recorded points in the voxel ID, dividing the reflected signal intensity by the count to save the average of the reflected signal intensity, and when the voxel ID of the searched voxel exists in the dictionary, cumulatively storing the reflected signal intensity in the voxel ID of the searched voxel in the dictionary, cumulatively storing the count of the recorded points in the voxel ID, and dividing the reflected signal intensity by the count to save the average of the reflected signal intensity.

[0010] According to one embodiment, the point extraction step includes setting parameters including voxel size, lower and upper threshold values of the reflected signal intensity, and the spatial range for generating the voxel grid, a filtering step of excluding points whose reflected signal intensity of the points is not included in the range from the lower threshold value to the upper threshold value, a step of generating a voxel grid based on the voxel size and the spatial range, loading the radar sensing file, searching for a voxel corresponding to the position of the point stored in the radar sensing file, and separately saving the position coordinates of the point when the voxel ID of the searched voxel is the same as the voxel ID of the top voxel with the largest cumulatively reflected signal intensity value in the dictionary, and extracting the points of the top voxel.

[0011] According to an embodiment, the step of extracting the point of the top voxel may include: searching, from the voxel grid, for a voxel corresponding to the position of the point stored in the radar sensing file; determining whether the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary; and when the voxel ID of the top voxel matches the voxel ID of the searched voxel, storing the position of the point in the voxel ID of the top voxel.

[0012] According to an embodiment, the step of extracting the point of the top voxel may further include: when the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary, determining whether the current file containing the point matches the target file; when the current file matches the target file, storing the position of the point, and when the current file does not match the target file, not storing the position of the point.

[0013] An apparatus for determining the position of an object sensed by radar using spatial voxelization according to the present disclosure may include a radar that transmits a radio wave signal and receives a reflected signal reflected by the object, and a determination module that analyzes a radar sensing file storing the reflected signal received by the radar using spatial voxelization to determine the position of a reflector serving as a calibration reference.

[0014] According to an embodiment, the determination module may include a processor that executes program code, a storage unit that is communicatively connected to the processor and stores the program code, a radar sensing file storing the reflected signal received by the radar, and a dictionary, and an input / output unit that is communicatively connected to the processor and receives parameters necessary for voxelization. The program code may be created to perform any one of the methods for determining the position of an object sensed by radar using spatial voxelization.

[0015] The features and advantages of the present disclosure will become more apparent from the following detailed description based on the accompanying drawings.

[0016] In this description, terms and words used in this specification and the claims should not be construed in a normal and dictionary sense, but should be construed in a meaning and concept that conforms to the technical idea of the present disclosure based on the principle that the inventor can appropriately define the concept of the terms in order to explain his invention in the best way.

Effects of the Invention

[0017] According to the present disclosure, using one radar, the position of a reference object for calibration can be determined in an environment where various objects exist.

Brief Description of the Drawings

[0018]

Figure 1

[0019]

Figure 2

[0020]

Figure 3

[0021]

Figure 4

[0022]

Figure 5

[0023]

Figure 6

[0024]

Figure 7

[0025]

Figure 8

[0026]

Figure 9

Mode for Carrying Out the Invention

[0027] The objects, advantages, and features of the present disclosure will become more apparent from the following detailed description and preferred embodiments with reference to the accompanying drawings, but the present disclosure is not necessarily limited thereto. Also, when explaining the present disclosure, if it is determined that a specific explanation regarding related known technologies may obscure the gist of the present disclosure, the detailed explanation thereof will be omitted.

[0028] When attaching reference numerals to the components of the drawings, it should be noted that the same components are given the same reference numerals as much as possible even if they are shown on other drawings, and similar components are given similar reference numerals.

[0029] The terms used to explain an embodiment of the present disclosure are not intended to limit the present disclosure. It can be understood that a singular expression includes plural expressions unless otherwise specified in the context.

[0030] The drawings may be shown schematically or exaggeratedly for the explanation of the embodiments.

[0031] In this document, expressions such as "have", "may have", "include", or "may include" refer to the presence of corresponding features (e.g., components such as numerical values, functions, operations, or parts), and do not exclude the presence of further features.

[0032] Terms such as "one", "other", "another", "first", "second", etc. are used to distinguish one component from other components, and the components are not limited by these terms.

[0033] It should be understood that terms indicating directions such as up, down, left, right, X-axis, Y-axis, Z-axis, etc. are merely for convenience of explanation, and different expressions are possible depending on the position of the observer and the position of the object.

[0034] The embodiments described in this document and the accompanying drawings are not intended to limit the present disclosure to specific embodiments. The present disclosure should be understood to include various modifications, equivalents, and / or alternatives of the embodiments.

[0035] Hereinafter, with reference to the accompanying drawings, one embodiment of the present disclosure will be described in detail.

[0036] FIG. 1 is a diagram showing an environment En in which an apparatus 1 for determining the position of an object sensed by radar using spatial voxelization according to one embodiment is utilized. FIG. 2 is a diagram showing an apparatus 1 for determining the position of an object sensed by radar using spatial voxelization according to one embodiment.

[0037] An apparatus 1 for determining the position of an object sensed by radar using spatial voxelization according to an embodiment of the present disclosure may be used in an environment En in which other objects Ob coexist in a space where a radar 20 and a reflector 10 are present. For example, the environment En may be a space in which a desk, chair, partition, clock, picture frame, and various other objects Ob are arranged. The environment En of an embodiment of the present disclosure may include a state in which the radar 20 and the reflector 10 are arranged together in a space where various objects Ob are arranged.

[0038] Generally, an environment En for calibration using a radar 20, lidar, or camera is a space in which only a reflector 10 for use as a reference exists. When various objects exist in the space, the radio wave signal of the radar 20 is diffusely reflected, making it difficult to accurately distinguish the reference object. Therefore, conventionally, a method of determining the position of the reflector 10 using two or more radars 20 has been used.

[0039] In contrast, an embodiment of the present disclosure can accurately distinguish the position of the reflector 10 even when various objects Ob exist in the environment En. And the position of the reflector 10 can be accurately determined using only one radar 20. Therefore, when performing calibration, only a single radar 20 needs to be prepared, so the equipment cost can be minimized, and it can be performed even in a normal office space, so the cost of securing space can be minimized.

[0040] An apparatus 1 for determining the position of an object sensed by radar using spatial voxelization according to an embodiment may include a radar 20 and a determination module 30. An apparatus 1 for determining the position of an object sensed by radar using spatial voxelization according to an embodiment may further include a reflector 10.

[0041] The radar 20 may utilize a single radar 20. The radar 20 can transmit radio wave signals and receive reflected signals that are reflected by an object and return. The radar 20 can transmit radio wave signals with a frequency of 79 GHz. The radio wave signals transmitted by the radar 20 may have other frequencies. The reflected signals may be received by the radar 20 through various paths and intensities due to various factors such as the shape and material of the object, the distance from the radar 20, and others. The radar 20 can output the position coordinates and the reflected signal intensity of the point from which the received reflected signal originated. The point means the part of the object from which the reflected signal originated. The position coordinates may include the values of the X-axis, Y-axis, and Z-axis. The reflected signal intensity refers to the intensity of the reflected signal that is reflected by the object and received by the radar 20. The reflected signal intensity may be the radar cross section (RCS) of the radar 20.

[0042] The reflector 10 is an object formed of a material that reflects radio wave signals well. The reflector 10 may include a corner reflector. The reflector 10 may be formed in a form that reflects the radio wave signals output by the radar 20 back towards the radar 20 with minimal loss. The reflector 10 is placed at a position to be utilized as a reference point for calibration with respect to the radar 20.

[0043] The determination module 30 can save the position coordinates and the reflected signal intensity of the points received from the radar 20 and generate a radar sensing file F. The determination module 30 can also receive the radar sensing file F generated using the radar 20. The determination module 30 can analyze the radar sensing file F that stores the reflected signals received by the radar 20 using spatial voxelization and determine the position of the reflector 10 that serves as a calibration reference.

[0044] The determination module 30 may include a computer device. For example, the determination module 30 may include a PC, a notebook PC, a server computer, a tablet PC, or other devices capable of executing information processing functions. The determination module 30 is connected to the radar 20 and can receive the position coordinates and reflection signal intensity of the points output from the radar 20.

[0045] The determination module 30 may include a processor 310 that executes program code, a storage unit 320 that is connected to the processor 310 so as to be capable of data transmission and reception and stores the program code, the radar sensing file F that stores the reflection signals received by the radar 20, and a dictionary, and an input / output unit 340 that is connected to the processor 310 so as to be capable of data transmission and reception and receives the parameters necessary for voxelization. The determination module 30 may further include a communication unit 330 that is connected to the processor 310 so as to be capable of data transmission and reception and transmits and receives data to and from an external device. Here, the program code may be created to perform a method of determining the position of the object sensed by the radar using spatial voxelization.

[0046] The processor 310 may include an element capable of information processing. The processor 310 may be a CPU, a GPU, an AP, or various other computing elements. The determination module 30 may include a plurality of processors 310. The plurality of processors 310 may be connected to transmit and receive data to and from each other. The processor 310 can execute a method of determining the position of the object sensed by the radar using the spatial voxelization according to an embodiment created with the program code.

[0047] The memory unit 320 can store the data necessary to perform the method of determining the position of the object sensed by the radar using spatial voxelization. The memory unit 320 may include a RAM, a ROM, a memory, a hard disk, cloud storage, etc. The memory unit 320 can store the program code created to perform each stage of the method of determining the position of the object sensed by the radar using spatial voxelization. The program code may be executed by the processor 310. The memory unit 320 can store the radar sensing file F, the voxel dictionary, the position coordinates of the separately stored points, parameters, and other data.

[0048] The input / output unit 340 may include a keyboard, a mouse, a touchpad, a touch screen, a pen, etc. for receiving input from the user. The input / output unit 340 may include a display, a speaker, etc. for displaying information to the user. The input / output unit 340 can provide a screen for the user to input parameters and can visually provide the analysis results.

[0049] The communication unit 330 can be connected to a communication network to transmit and receive data. The processor 310 can download the radar sensing file F via the communication unit 330 and can transmit the analysis results. The communication unit 330 can utilize various communication methods such as 5G, 6G, satellite communication, wi-fi, bluetooth, LAN, WAN, ethernet, IP4, IP6, etc.

[0050] Figure 3 is a flowchart showing a method of determining the position of an object sensed by radar using spatial voxelization according to an embodiment.

[0051] The processor 310 performs a method for determining the position of an object sensed by the radar 20 using spatial voxelization according to an embodiment. The method for determining the position of an object sensed by the radar 20 using spatial voxelization according to an embodiment includes loading a radar sensing file F that has received and stored a reflected signal obtained by reflecting a radio wave signal transmitted by the radar 20 from an object, searching for a voxel corresponding to the position of a point stored in the radar sensing file F, and generating a dictionary by accumulating and storing the reflected signal intensity of the point in the voxel ID of the searched voxel (voxelization step (S200)), loading the radar sensing file F, searching for a voxel corresponding to the position of a point stored in the radar sensing file F, and separately storing the position coordinates of the point when the ID of the searched voxel is the same as the voxel in which the accumulated value of the reflected signal intensity is the largest in the dictionary (point extraction step (S300)), and determining the position of a reference point serving as a calibration reference based on the separately stored position coordinates of the point (step (S400)). The voxelization step (S200), the point extraction step (S300), and the step of determining the position of the reference point (S400) may be performed by the processor 310.

[0052] The voxelization step (S200) is a process of determining a voxel corresponding to a point stored in the radar sensing file F and matching the point information to the voxel and storing it in a dictionary. The dictionary can store the information of the points included in the voxel. The dictionary can store the voxel ID, the reflected signal intensity, the count, and the average reflected signal intensity. The dictionary does not store the position of the point. If the dictionary stores the position of the point, the capacity of the dictionary may increase, and the data processing speed may slow down. When arranging the voxels in descending order of the reflected signal intensity, the voxel with the largest reflected signal intensity can be referred to as the top voxel. Since the top voxel has the largest accumulated reflected signal intensity, it contains many points and can be analyzed as having a large reflected signal intensity. Therefore, it can be analyzed as a space where the reflector 10 is likely to be located.

[0053] The point extraction stage (S300) reads the points stored in the radar sensing file F, determines whether the points are included in the top voxels stored in the dictionary, and extracts only the points included in the top voxels. By separating the voxelization stage (S200) for generating the dictionary and the point extraction stage (S300) for the points included in the top voxels, it is possible to achieve an improvement in the data processing speed and minimization of the dictionary capacity. The points extracted in the point extraction stage (S300) may have their position coordinates separately stored.

[0054] The stage (S400) for determining the position of the reference point is a process of determining the position of the reflector 10 using the position coordinates of the points determined to be included in the top voxels. The position of the top voxel generally refers to the coordinates of the center point of the voxel. The position coordinates of the points determined to be included in and extracted from the top voxels are different from the center point coordinates of the top voxels. Therefore, in order to accurately determine the position of the reflector 10, the position coordinates of the extracted points are utilized. The position of the reflector 10 can be a reference point that serves as a calibration reference for matching the sensing data of the radar 20, lidar, and camera.

[0055] FIG. 4 is a diagram for explaining data for storing the reflected signal received by the radar 20 according to an embodiment. Refer to both FIG. 3 and FIG. 4.

[0056] A method for determining the position of an object sensed by a radar using spatial voxelization according to an embodiment may further include a sensing stage (S100) in which the radar 20 transmits a radio wave signal and receives a reflected signal reflected by the object. The sensing stage (S100) may further include an operation in which the determination module 30 organizes the data received from the radar 20 to generate a radar sensing file F. The radar sensing file F may be generated by the radar 20 receiving a reflected signal and storing the position coordinates of the points and the reflected signal intensity in the form of point cloud data.

[0057] The raw data that the radar 20 receives the reflected signal and provides to the determination module 30 may be in various forms. The data that the radar 20 provides to the determination module 30 may be the X-axis, Y-axis, and Z-axis coordinates, and may be various forms of data depending on the type of the radar 20. The determination module 30 can organize the data received from the radar 20 as the X-axis, Y-axis, Z-axis, and reflected signal intensity to generate the radar sensing file F. The radar sensing file F may be generated at a defined size or time.

[0058] The data acquisition period of the radar 20 may be 10 to 20 Hz. The radar 20 can receive the reflected signal for each data acquisition period to generate data and provide it to the determination module 30, or generate the radar sensing file F. For example, the radar sensing file F may be generated by receiving the reflected signal for the radio wave signal every 10 to 20 Hz, which is the data acquisition period, and may be generated as a file with a length of 50 to 60 ms. The data acquisition period of the radar 20 may be various, and the length or size of the radar sensing file F may be various. A plurality of radar sensing files F may be generated while performing the sensing step (S100) using the radar 20.

[0059] FIG. 4 shows the first radar sensing file F1 to the Nth radar sensing file FN. Here, N is a positive number. Refer to Table A in which the data of the fourth radar sensing file F4 in FIG. 4 is enlarged. The fourth radar sensing file F4 may include values corresponding to the X-axis, Y-axis, and Z-axis, and may include a value corresponding to the reflected signal intensity (RCS). The radar sensing file F may include data in such a form. The radar sensing file F generated by the determination module 30 may be stored in the storage unit 320.

[0060] The determination module 30 can load the radar sensing file F stored in the storage unit 320 and perform the voxelization step (S200).

[0061] The voxelization stage (S200) may include a stage (S210) of setting parameters including a voxel size, a lower threshold value and an upper threshold value of the reflection signal intensity, and a spatial range for generating a voxel grid, a filtering stage (S220) of excluding points whose reflection signal intensity of the points is not included in the range from the lower threshold value to the upper threshold value, a stage (S230) of generating a voxel grid based on the voxel size and the spatial range, and a stage (S240) of searching for a voxel corresponding to the position of the points stored in the radar sensing file F from the voxel grid, and accumulating and storing the reflection signal intensity of the points in the voxel ID of the searched voxel to generate a dictionary.

[0062] The stage (S210) of setting parameters can further set a dictionary generation range DB.

[0063] The dictionary generation range DB is the range of the file for which voxelization is performed to generate a dictionary. The setting of the dictionary generation range DB may be performed in a manner of determining a target file (File_target) and the number (n) of files selected from before and after the target file. For example, if the 8th radar sensing file F8 is selected as the target file and the number (n) of files selected from before and after is 6, the 2nd radar sensing file F2 (File_target - n) to the 14th radar sensing file F14 (File_target + n) can be set as the dictionary generation range DB.

[0064] Alternatively, the setting of the dictionary generation range DB may be performed in a manner of selecting a start file and an end file. For example, by selecting the 2nd radar sensing file F2 as the start file and the 14th radar sensing file F14 as the end file, the 2nd to 14th radar sensing files F2 to F14 can be set as the dictionary generation range DB.

[0065] FIG. 5 is a diagram for explaining spatial voxelization according to an embodiment. Refer to both FIG. 3 and FIG. 4.

[0066] The voxel size can be set at the stage of setting parameters (S210). The voxel size may be displayed in terms of R. The value of R can be input by the user. The voxel may be in the form of a cube. The cubic voxel may include eight vertices V1 to V8. The spatial coordinates of the first to eighth vertices V1 to V8 may be displayed as [-R, -R, -R] to [R, R, R]. In such a case, the distance between adjacent vertices may be 2R. The larger the voxel size is set, the more points it can contain inside.

[0067] At the stage of setting parameters (S210), the spatial range for generating the voxel grid can be set. The spatial range may be determined by the size of the space sensed by the radar 20. The spatial range is preferably set to be larger than the distance from the radar 20 to the reflector 10. The spatial range may be set with the values of the X-axis, Y-axis, and Z-axis.

[0068] When the voxel size and the spatial range are set, the voxel grid can be generated. The voxel grid is a division of the space into a plurality of voxels. FIG. 5 shows a part of the voxel grid with the origin as a reference. Each of the plurality of voxels included in the voxel grid is given a voxel ID that can distinguish them. The voxel ID may be given in a predetermined manner.

[0069] At the stage of setting parameters (S210), the lower threshold value and the upper threshold value of the reflected signal intensity can be set. The radio wave signal of the radar 20 is reflected by an object and is reflected in various directions and repeatedly reflected several times and attenuates. Therefore, among the reflected signals received by the radar 20, it is preferable to ignore the signals having a reflected signal intensity with a size equal to or less than the determined lower threshold value. Since the radio wave signal of the radar 20 attenuates while being reflected by an object, when it has a reflected signal intensity equal to or higher than the upper threshold value, it may not be a reflected signal by the radio wave signal transmitted from the radar 20, and it is preferable to ignore it. The lower threshold value and the upper threshold value of the reflected signal intensity may be input by the user. Alternatively, the lower threshold value and the upper threshold value may be determined according to the characteristics of the radar 20.

[0070] After setting the voxel size, spatial range, lower threshold, upper threshold, and dictionary generation range DB in the parameter setting stage (S210), the filtering stage (S220) can be performed.

[0071] The filtering stage (S220) is a process of excluding points whose reflected signal intensity of the points stored in the radar sensing file F is not included in the range from the lower threshold to the upper threshold. The processor 310 can compare the reflected signal intensity of the points with the lower threshold and the upper threshold, and exclude the points not included in the range between the lower threshold and the upper threshold. The processor 310 can repeatedly perform the filtering stage (S220) for each loaded radar sensing file F.

[0072] After performing the filtering stage (S220), a voxel grid can be generated. The voxel grid may be generated based on the voxel size and the spatial range. The processor 310 can repeatedly perform the stage (S230) of generating a voxel grid for each loaded radar sensing file F. If a voxel grid is generated, a plurality of voxels are generated within the spatial range, and the processor 310 can determine which voxel the position coordinates of the point correspond to.

[0073] When the voxel grid is generated, the dictionary generation stage (S240) can be performed. The dictionary generation stage (S240) is a process of checking which voxel the point corresponds to and recording the information of the point in the voxel.

[0074] The step of generating the dictionary (S240) includes a step of searching for a voxel corresponding to the position of the point stored in the radar sensing file F from the voxel grid (S241), a step of determining whether the voxel ID of the searched voxel exists in the dictionary (S242), and when the voxel ID of the searched voxel does not exist in the dictionary, adding the voxel ID of the searched voxel to the dictionary, saving the reflected signal intensity to the voxel ID, saving the count of the recorded points to the voxel ID, dividing the reflected signal intensity by the count to save the average of the reflected signal intensity (additional step S243), and when the voxel ID of the searched voxel exists in the dictionary, cumulatively saving the reflected signal intensity to the voxel ID of the searched voxel in the dictionary, cumulatively saving the count of the recorded points to the voxel ID, and dividing the reflected signal intensity by the count to save the average of the reflected signal intensity (cumulative step S244).

[0075] The step of searching for a voxel (S241) is a process of confirming which voxel corresponds to the position of the point stored in the radar sensing file F. In the voxel grid, the positions of a plurality of voxels are determined, and by comparing the position coordinates of the point with the position of the voxel, the voxel containing the point can be searched. For example, in FIG. 5, by comparing the position coordinates of the first point P1 with the position and size of the voxel, it can be searched which voxel it is included in. The first point P1 may be included in the first voxel Vx1, the second point P2 and the third point P3 may be included in the second voxel Vx2, and the fourth point P4 and the fifth point P5 may be included in the third voxel (Vx3). Since the radar sensor file contains a plurality of points, the step of searching for a voxel (S241) may be repeatedly performed for each point.

[0076] By performing the step of searching for a voxel (S241), the voxel corresponding to the point can be confirmed. A voxel ID is given to the voxel. The step of determining whether the voxel ID exists in the dictionary (S242) is to determine whether the voxel ID of the voxel corresponding to the point is recorded in the dictionary. The dictionary may store a plurality of voxel IDs and information of points matched to the voxel IDs. The processor 310 determines whether the voxel ID of the searched voxel matches the voxel ID stored in the dictionary.

[0077] FIG. 6 is a diagram for explaining a voxel dictionary according to an embodiment. Refer to FIGS. 3, 4, and 5 together.

[0078] When the voxel ID of the searched voxel does not exist in the dictionary, an additional step (S243) can be performed, and when the voxel ID of the searched voxel exists in the dictionary, an accumulation step (S244) can be performed.

[0079] The additional step (S243) is a process of adding a new voxel ID that does not exist in the dictionary. In the additional step (S243), the searched voxel ID is newly added to the dictionary, and the reflection signal intensity, count, and average reflection signal intensity of the point may be matched and stored to the voxel ID. For example, in FIG. 6, when the voxel ID of the searched voxel is 2322, it does not match the voxel ID stored in the existing dictionary D1, so the additional step (S243) can be performed to add the point information to the dictionary. The dictionary (D2) after performing the additional step (S243) includes the voxel ID of the searched voxel, the value (14.4) of the reflection signal intensity (RCS) is stored, and since a new point is added, the count is stored as 1, and the average reflection signal intensity (AVG) may be stored as the same value (14.4) as the reflection signal intensity because the count is 1.

[0080] The accumulation stage (S244) is a process of accumulating and storing the point information for the voxel IDs existing in the dictionary. The fact that the same voxel ID as the searched voxel ID exists in the existing dictionary D1 means that it is judged that other points correspond to the same voxel, which means that the point information is stored in the dictionary. For example, in FIG. 6, when the voxel ID of the searched voxel is 1401, there is a matching voxel ID among the voxel IDs stored in the existing dictionary D1. Therefore, the accumulation stage (S244) can be performed. The dictionary (D2) after performing the accumulation stage (S244) may be stored with the reflected signal intensities accumulated from 57.6 to 64.0, the counts accumulated from 3 to 4, and the average reflected signal intensity stored from 19.2 to 16.0, which are matched to the voxel ID of the searched voxel.

[0081] In the voxelization stage (S200), when the stage (S210) of setting parameters is performed once, for each of the plurality of radar sensing files F set in the dictionary generation range DB, the filtering stage (S220), the stage (S230) of generating a voxel grid, and the stage (S240) of generating a dictionary are repeatedly performed. In the stage (S240) of generating a dictionary, for each of the plurality of points included in one radar sensing file F, the stage (S241) of searching for a voxel, the stage (S242) of determining whether the voxel ID of the searched voxel exists in the dictionary, the addition stage (S243), and the accumulation stage (S244) are repeatedly performed. When the voxelization stage (S200) is performed for each of the plurality of radar sensing files F set in the dictionary generation range DB, a dictionary in which the reflected signal intensities of the points included in the voxel are accumulated and stored can be obtained.

[0082] A plurality of voxel IDs and reflected signal intensities are stored in the dictionary. They can be arranged in descending order of the reflected signal intensity, and the voxel having the maximum reflected signal intensity can be referred to as the top voxel.

[0083] Refer to FIG. 3. When the dictionary is generated, the point extraction step (S300) can be performed. FIG. 7 is a diagram for explaining the extraction of points and the determination of reference points according to an embodiment. Refer to both FIGS. 3 and 7.

[0084] The point extraction step (S300) includes a step (S310) of setting parameters including a voxel size, a lower threshold value and an upper threshold value of the reflection signal intensity, and a spatial range for generating a voxel grid, a filtering step (S320) of excluding points whose reflection signal intensity of the points is not included in the range from the lower threshold value to the upper threshold value, a step (S330) of generating a voxel grid based on the voxel size and the spatial range, and a step of loading the radar sensing file F, searching for a voxel corresponding to the position of the points stored in the radar sensing file F, and when the voxel ID of the searched voxel is the same as the voxel ID of the top voxel with the largest accumulated value of the reflection signal intensity in the dictionary, separately saving the position coordinates of the points and extracting the points of the top voxel (S340).

[0085] The step (S310) of setting parameters in the point extraction step (S300) may be performed in the same manner as the step (S210) of setting parameters in the voxelization step (S200). Therefore, the step (S310) of setting parameters in the point extraction step (S300) may be omitted. The step (S310) of setting parameters in the point extraction step (S300) can set a voxel size, a lower threshold value and an upper threshold value of the reflection signal intensity, a spatial range, and a range (point extraction range EB) of the radar sensing file F for extracting points. The point extraction range EB may be set to be the same as the dictionary generation range DB for generating the dictionary in the voxelization step (S200), or may be set differently.

[0086] In the point extraction stage (S300), the filtering stage (S320) may be performed in the same manner as the filtering stage (S220) in the voxelization stage (S200). Among the points stored in the radar sensing file F set as the point extraction range EB, points whose reflected signal intensity is not within the range of the lower threshold and the upper threshold can be excluded.

[0087] In the point extraction stage (S300), the stage (S330) of generating a voxel grid may be performed in the same manner as the stage (S230) of generating a voxel grid in the voxelization stage (S200). A grid can be generated with voxels of the set voxel size within the set spatial range.

[0088] The stage (S340) of extracting the points of the top voxel is a process of searching for the voxel corresponding to the points stored in the radar sensing file F set as the point extraction range EB, and extracting the points when the searched voxel is the same as the top voxel. The stage (S340) of extracting the points of the top voxel may include a stage (S341) of searching for the voxel corresponding to the position of the points stored in the radar sensing file F from the voxel grid, a stage (S342) of determining whether the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary, and a stage (S343) of storing the position of the points in the voxel ID of the top voxel when the voxel ID of the top voxel and the voxel ID of the searched voxel match.

[0089] The stage (S341) of searching for voxels in the stage (S340) of extracting the points of the top voxel is similar to the stage (S241) of searching for voxels in the stage (S240) of generating a dictionary. The stage (S341) of searching for voxels in the stage (S340) of extracting the points of the top voxel is a process of confirming the voxel corresponding to the position of the points in the radar sensing file F set in the point extraction range EB. When the voxel corresponding to the points is searched, the voxel ID of the voxel can be confirmed.

[0090] Next, a step (S342) is performed to determine whether the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary. If the voxel ID of the searched voxel is different from the voxel ID of the top voxel, a step (S241) of searching for a voxel for the next point in the radar sensing file F is further performed.

[0091] If the voxel ID of the searched voxel is the same as the voxel ID of the top voxel, a step (S343) of saving the position of the point is performed. The step (S343) of saving the position of the point is a process of separately saving the position coordinates of the point determined to be included in the top voxel. At this time, the position coordinates of the point can be saved by matching the voxel ID of the top voxel. If there are multiple points included in the top voxel, the separately saved data may have the position coordinates of multiple points saved in one top voxel. For example, from the visualization result in FIG. 7, it can be confirmed that the voxel ID of the top voxel is 3027. Referring to the content A of the top voxel recorded in the dictionary, it can be confirmed that the voxel ID of the top voxel is 3027, the accumulated reflected signal intensity is 140.2, the count is 11, and the average reflected signal intensity is 12.7. If the voxel ID of the voxel corresponding to the point included in the radar sensing file F is 3027, since it is the same as the voxel ID of the top voxel, the position coordinates of the point can be separately saved, and the reflected signal intensity of the point can also be separately saved. Referring to the content B in FIG. 7 where the position coordinates and the reflected signal intensity of the point are separately saved, it can be confirmed that multiple position coordinates and reflected signal intensities of points are saved in the voxel ID 3027.

[0092] When the step of setting parameters (S210) is performed once in the point extraction step (S300), for each one or more radar sensing files F set as the point extraction range EB, the filtering step (S220), the step of generating a voxel grid (S230), and the step of extracting points of the top voxel (S340) are repeatedly performed. In the step of extracting points of the top voxel (S340), for each of the plurality of points included in one radar sensing file F, the step of searching for a voxel (S241), the step of determining whether the voxel ID of the searched voxel matches the voxel ID of the top voxel (S342), and the step of saving the point position are repeatedly performed. When the point extraction step (S300) is performed for each one or more radar sensing files F set as the radar sensing files F for extracting points, the position coordinates of the points determined to be included in the top voxel can be separately saved.

[0093] When the position coordinates of the points corresponding to the top voxel are extracted, the step of determining the position of the reference point (S400) can be performed. The reference point refers to the position of the reflector 10 that serves as a reference in calibration. In the calibration process, it is necessary to determine the position of the reflector 10 as the reference reference point in order to adjust the radar 20, lidar, and camera to measure the same position of one reflector 10. A method for determining the position of an object sensed by a radar using spatial voxelization according to an embodiment may be used to determine the position of the reference point measured by the radar 20 in the calibration process.

[0094] Referring to the content C that determines the position of the reflector 10 in FIG. 7, the position of the reflector 10 (i.e., the position of the reference point) is calculated using the position coordinates of the points included in the top voxel. The X coordinate of the reflector 10 is calculated as the average of the X coordinates in the position coordinates of the points included in the top voxel, the Y coordinate of the reflector 10 is calculated as the average of the Y coordinates in the position coordinates of the points included in the top voxel, and the Z coordinate of the reflector 10 may be calculated as the average of the Z coordinates in the position coordinates of the points included in the top voxel. At the position of the reflector 10, the distance (Dist) means the distance from the radar 20 to the reflector 10. The distance may be calculated by Equation 1 below using the position coordinates (X, Y, Z) of the reflector 10. The position coordinates of the reflector 10 are the coordinates of the reference point.

[0095]

Number

[0096] Dist: The straight-line distance from the radar 20 to the reflector 10, X: The X coordinate value of the reflector 10, Y: The Y coordinate value of the reflector 10, Z: The Z coordinate value of the reflector 10

[0097] A method for determining the position of an object sensed by a radar using spatial voxelization according to an embodiment may further include visualizing the reflected signal intensities of the voxels stored in a dictionary in descending order of magnitude. The visualizing step may be performed by the user's selection after performing the step of generating a dictionary (S240). The visualization result VR can be provided in such a way that if the reflected signal intensity of the voxel stored in the dictionary is large, it is displayed in a dark color, and if it is small, it is displayed in a light color. The visualization result VR may display the value of the accumulated reflected signal intensity and the voxel ID. The user can sequentially check the accumulated values of the reflected signal intensities of the points included in the voxel with reference to the visualization result VR.

[0098] FIG. 8 is a diagram for explaining calibration according to an embodiment. FIG. 9 is a diagram for explaining a method of extracting a reference point at the time of calibration.

[0099] A method for determining the position of an object sensed by radar using spatial voxelization according to an embodiment may be used for calibration. For example, calibration may be performed in such a way that a radar 20, lidar, and camera sense a single reference point (reflector 10). The reference time point for adjusting the position during the calibration process may be applied identically to all sensors (radar 20, lidar, camera). Lidar and cameras have the advantage of being able to obtain clear data at a specific time point due to the characteristics of optical equipment. However, due to the characteristics of radio wave equipment, the radar 20 needs to collect data collected over a certain period and determine the reference point by summarizing the data, rather than obtaining data at a specific time point. Therefore, it may not be possible to determine the exact reference point only with the target file (File_target) corresponding to the calibration reference time point. For example, the length of the target file may not be long enough. A method for determining the position of an object sensed by radar using spatial voxelization according to an embodiment may use a plurality of radar sensing files F to generate a dictionary and extract points included in the target file corresponding to the calibration reference time point to determine the reference point. Therefore, the position of the reference point measured by the radar 20 at the calibration reference time point can be determined.

[0100] In a method for determining the position of an object sensed by radar using spatial voxelization according to an embodiment, the step (S340) of extracting the points of the top voxel may further include a step (S344) of determining whether the current file containing the points matches the target file when the voxel ID of the searched voxel matches the voxel ID of the top voxel of the dictionary. Then, when the current file matches the target file (Y), a step (S343) of saving the position of the point is performed, and when the current file does not match the target file (Y), the step (S343) of saving the position of the point is not performed.

[0101] Here, the dictionary generation range DB in the dictionary generation stage (S240) and the point extraction range EB in the point extraction stage (S300) may be different. For example, as shown in FIG. 8, the first dictionary generation range DB1 is the 43rd to 49th radar sensing files F43 to F49, which correspond to the calibration reference time point, and the point extraction range EB may be the 53rd radar sensing file F53 which is one target file (File_target). A dictionary can be generated using the radar sensing files F in the first dictionary generation range DB1, and the position of the reference point can be determined by extracting the points corresponding to the top voxels among the points included in the target file.

[0102] Alternatively, the target file corresponding to the calibration reference time point may be included in the dictionary generation range DB in the dictionary generation stage (S240), and a file different from the target file may be further included in the point extraction range EB in the point extraction stage (S300). For example, as shown in FIG. 8, the second dictionary generation range DB2 includes the target file (File_target), and the point extraction range EB also includes the target file (File_target). A dictionary is generated using the radar sensing files F in the second dictionary generation range DB2, and the points corresponding to the target file (File_target) while not corresponding to the top voxels are extracted from the points included in the point extraction range EB to determine the position of the reference point. Here, the points included in the radar sensing file F that correspond to the top voxels but are not the target file (File_target) are not extracted.

[0103] Using the described method, the reference point of the radar 20 for calibration can be determined. The method and apparatus according to an embodiment have the advantage that a separate space required for calibration is not necessary because the reference point can be determined in a daily environment where various objects exist.

[0104] As described above, the present disclosure has been described in detail with specific embodiments. The embodiments are for specifically explaining the present disclosure, and the present disclosure is not limited thereto. It will be apparent that those having ordinary knowledge in the art can make modifications and improvements within the technical idea of the present disclosure.

[0105] Any simple modification or change of the present disclosure belongs to the scope of the present disclosure, and the specific protection scope of the present disclosure will be clarified by the appended claims.

Description of Reference Numerals

[0106] 1: Device for determining the position of an object sensed by radar using spatial voxelization

[0107] En: Environment

[0108] Ob: Object

[0109] 10: Reflector

[0110] 20: Radar

[0111] 30: Determination module

[0112] 310: Processor

[0113] 320: Memory unit

[0114] 330: Communication unit

[0115] 340: Input / output unit

Claims

1. Load a radar sensing file that stores the reflected signals received and saved after the radio wave signals transmitted by the radar are reflected by an object, search for voxels corresponding to the positions of the points stored in the radar sensing file, and accumulate and save the reflected signal intensity of the points to the voxel IDs of the searched voxels to generate a dictionary; a voxelization stage, Load the radar sensing file, search for voxels corresponding to the positions of the points stored in the radar sensing file, and when the ID of the searched voxel is the same as the voxel with the largest accumulated value of the reflected signal intensity in the dictionary, separately save the position coordinates of the points; a point extraction stage, Based on the position coordinates of the points saved separately, determining the position of a reference point that serves as a calibration reference; a method for determining the position of an object sensed by a radar using spatial voxelization, including the above steps.

2. The radar sensing file is Generated by the radar receiving a reflected signal and storing the position coordinates and reflected signal intensity of the points in the form of point cloud data. The method for determining the position of an object sensed by a radar using spatial voxelization according to Claim 1.

3. The voxelization stage includes Setting parameters including voxel size, lower and upper threshold values of the reflected signal intensity, and the spatial range for generating a voxel grid; A filtering stage for excluding points whose reflected signal intensity of the points is not within the range from the lower threshold value to the upper threshold value; Generating a voxel grid based on the voxel size and spatial range; Searching for voxels corresponding to the positions of the points stored in the radar sensing file from the voxel grid, and accumulating and saving the reflected signal intensity of the points to the voxel IDs of the searched voxels to generate a dictionary. The method for determining the position of an object sensed by a radar using spatial voxelization according to Claim 2, including the above steps.

4. The stage of generating the dictionary includes Searching for voxels corresponding to the positions of the points stored in the radar sensing file from the voxel grid; Determining whether the voxel ID of the searched voxel exists in the dictionary; When the voxel ID of the searched voxel does not exist in the dictionary, add the voxel ID of the searched voxel to the dictionary, save the reflected signal intensity to the voxel ID, save the count of the points recorded in the voxel ID, and save the average of the reflected signal intensity by dividing the reflected signal intensity by the count. An additional step of doing so. When the voxel ID of the searched voxel exists in the dictionary, accumulate and save the reflected signal intensity to the voxel ID of the searched voxel in the dictionary, accumulate and save the count of the points recorded in the voxel ID, and divide the reflected signal intensity by the count. A cumulative step of saving the average of the reflected signal intensities, and a method for determining the position of an object sensed by radar using the spatial voxelization according to claim 3.

5. The point extraction step includes: Setting parameters including the voxel size, the lower and upper threshold values of the reflected signal intensity, and the spatial range for generating the voxel grid. A filtering step of excluding points whose reflected signal intensity of the points is not included in the range from the lower threshold value to the upper threshold value. Generating a voxel grid based on the voxel size and the spatial range. Loading a radar sensing file, searching for a voxel corresponding to the position of the point stored in the radar sensing file, and if the voxel ID of the searched voxel is the same as the voxel ID of the top voxel with the largest accumulated value of the reflected signal intensity in the dictionary, separately storing the position coordinates of the point, and extracting the points of the top voxel. A method for determining the position of an object sensed by radar using the spatial voxelization according to claim 2.

6. The step of extracting the points of the top voxel includes: Searching for a voxel corresponding to the position of the point stored in the radar sensing file from the voxel grid. Determining whether the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary. When the voxel ID of the top voxel matches the voxel ID of the searched voxel, saving the position of the point to the voxel ID of the top voxel. A method for determining the position of an object sensed by radar using the spatial voxelization according to claim 5.

7. The step of extracting the points of the top voxels includes a step of determining whether the current file containing the points matches the target file when the voxel ID of the searched voxel matches the voxel ID of the top voxel in the dictionary, and performing a step of saving the position of the points when the current file matches the target file, and not performing a step of saving the position of the points when the current file does not match the target file. A method for determining the position of an object sensed by radar using spatial voxelization according to claim 6.

8. A radar that transmits a radio wave signal and receives a reflected signal reflected by an object and returned, and a determination module that analyzes a radar sensing file storing the reflected signal received by the radar using spatial voxelization to determine the position of a reflector serving as a calibration reference. An apparatus for determining the position of an object sensed by radar using spatial voxelization.

9. The determination module includes a processor that executes program code, a storage unit that is connected to the processor so as to be capable of data transmission and reception and stores the program code, a radar sensing file storing the reflected signal received by the radar, and a dictionary, and an input / output unit that is connected to the processor so as to be capable of data transmission and reception and receives parameters necessary for voxelization. The program code is created to perform any one of the methods described in claims 1 to 7. An apparatus for determining the position of an object sensed by radar using spatial voxelization according to claim 8.

Images