Point cloud road surface extraction system and method

Abstract

Disclosed are a point cloud road surface extraction system and method. The point cloud road surface extraction system comprises: a point cloud data storage unit that stores point cloud (PCL) data collected on a road; a grid generation unit that generates a grid including a plurality of cells by using an X coordinate and a Y coordinate while ignoring a Z coordinate of the point cloud data; and a surface data extraction unit that sets a Z-coordinate value of each of the cells by using a minimum Z-coordinate value of the point cloud data included in each of the cells of the grid, and filters the point cloud data by using the plurality of cells, thereby extracting surface data of the road.

Description

Point cloud road surface extraction system and method

[0001] The present invention relates to a point cloud road floor extraction system and method, which ignores the z coordinate of point cloud (PCL) data collected on a road, creates a grid including a plurality of cells using x and y coordinates, sets the z coordinate value of each cell using the minimum z coordinate value of point cloud data included in each cell of the grid, and extracts road floor data by filtering point cloud data using the plurality of cells, thereby enabling a point cloud road floor extraction system and method to quickly and simply extract road floor data having information necessary for autonomous driving, such as lanes, road signs, crosswalks, and stop lines.

[0002]

[0003] Autonomous vehicles are vehicles capable of sensing their surroundings and movements with little or no human intervention or input. To realize these autonomous vehicles, a variety of sensors capable of sensing their surroundings, such as radar, computer vision, GPS, odometry, and inertial measurement units, must be integrated.

[0004] Furthermore, technologies are needed to provide autonomous vehicles with vehicle operation support information, enabling them to easily understand surrounding traffic conditions that are difficult for autonomous vehicles to detect. For example, Local Dynamic Map (LDM) is a technology that links, stores, and manages standardized vehicle operation support information for autonomous cooperative driving. Based on a lane-level precision electronic map (or static information), it integrates road traffic and surrounding vehicle conditions (dynamic information) to provide real-time information to autonomous vehicles.

[0005] The unmanned autonomous driving of a vehicle (autonomous vehicle) can be broadly divided into three stages: recognizing the surrounding environment, planning a driving route based on the recognized environment, and driving along the planned route.

[0006] The technology for recognizing the environment around a vehicle will vary depending on the target environment in which the autonomous vehicle is driving. In particular, in order to drive autonomously in a road environment designed and constructed for existing manned vehicles, technology for recognizing various rules existing on the road may be essential.

[0007] In particular, recognizing lanes and following a designated lane is the most basic technology for safe driving with manned vehicles.

[0008] While there are methods for recognizing road lanes based on images captured by cameras, they suffer from reduced recognition accuracy when ambient light is insufficient. Consequently, lane recognition technology using Lidar is currently being developed.

[0009] Lidar is a device that precisely draws the surroundings by measuring the distance to objects and other things by emitting laser pulses and then reflecting them back. It has the same principle as radar using radio waves, but since it uses the frequency of the visible light range, which is called light among electromagnetic waves, the actual technology and scope of use can be seen to be different.

[0010] These lidars are one component of the Mobile Mapping System (MMS), and in addition to lidars, the MMS includes a camera, an inertial measurement unit (IMU), GPS, and a distance measurement indicator (DMI).

[0011] Accordingly, MMS can obtain precise digital map data by matching the information obtained through lidar with the coordinates obtained from GPS.

[0012] Typically, point cloud data collected by vehicles equipped with MMS contains a variety of information, including roadside structures, buildings, and vehicles. However, the information actually needed for autonomous driving is road surface data, including lanes, road signs, crosswalks, and stop lines. Providing point cloud data directly to autonomous vehicles requires the vehicles to process more than just road surface data, which is inefficient and ultimately time-consuming.

[0013]

[0014] The purpose of the present invention is to provide a point cloud road floor extraction system and method capable of quickly and simply extracting road floor data having information necessary for autonomous driving, such as lanes, road signs, crosswalks, and stop lines, by ignoring the z coordinate of point cloud (PCL) data collected on a road, generating a grid including a plurality of cells using x and y coordinates, setting the z coordinate value of each cell using the minimum z coordinate value of point cloud data included in each cell of the grid, and filtering the point cloud data using the plurality of cells to extract road floor data.

[0015] The purpose of the present invention is not limited to the purposes mentioned above, and other purposes not mentioned will be clearly understood by those skilled in the art from the description below.

[0016]

[0017] According to one embodiment of the present invention, a point cloud road floor extraction system comprises: a point cloud data storage unit that stores point cloud (PCL) data collected on a road; a grid generation unit that ignores the z coordinate of the point cloud data and generates a grid including a plurality of cells using x and y coordinates; and a floor data extraction unit that sets a z coordinate value of each cell using a minimum z coordinate value of point cloud data included in each cell of the grid, and extracts floor data of the road by filtering point cloud data using the plurality of cells.

[0018] The grid generation unit may include a driving interval point generation module that generates driving interval points using only x-coordinate values ​​and y-coordinate values, ignoring the z-coordinate value of the point cloud data along the driving direction based on the driving line on the road; and a grid generation module that generates the grid using the x-coordinate and y-coordinate before and after the driving interval point using the driving interval point.

[0019] The above-mentioned floor data extraction unit may include a z-coordinate value setting module that sets the minimum z-coordinate value of point cloud data included in each cell of the grid as the z-coordinate value of each cell; and a filtering module that filters point cloud data existing under the plurality of cells.

[0020] The above z-coordinate value setting module can interpolate the z-coordinate value of the contact point between cells positioned forward and backward along the driving direction when there is an increase or decrease in the z-coordinate value between cells positioned forward and backward along the driving direction among a plurality of cells within the grid.

[0021] The above z-coordinate value setting module may interpolate the z-coordinate value of the first cell to the z-coordinate value of the first tangent line where the first cell and the second cell meet when the z-coordinate value increases from the first cell to the second cell along the driving direction among the plurality of cells in the grid, and may set the z-coordinate value of the first cell to the z-coordinate value of the second tangent line opposite the first tangent line portion in the first cell, so that the z-coordinate value of the first cell increases from the second tangent line to the first tangent line.

[0022] The above z-coordinate value setting module may interpolate the z-coordinate value of the fourth cell by setting the z-coordinate value of the third cell to the z-coordinate value of the third tangent line where the third cell and the fourth cell meet, and by setting the z-coordinate value of the fourth cell to the z-coordinate value of the fourth tangent line opposite the third tangent line portion in the fourth cell, so that the z-coordinate value of the fourth cell decreases from the third tangent line to the fourth tangent line, when the z-coordinate value of the fourth cell decreases from the third tangent line to the fourth tangent line, among the plurality of cells in the grid.

[0023] The above filtering module can filter the point cloud data by determining whether a point of the point cloud data is located below two points included in the cell using a Counter ClockWise (CCW) algorithm.

[0024] According to one embodiment of the present invention, a point cloud road floor extraction method comprises: a point cloud data storage step of storing point cloud (PCL) data collected on a road; a grid generation step of generating a grid including a plurality of cells using an x-coordinate and a y-coordinate while ignoring a z-coordinate of the point cloud data; and a floor data extraction step of setting a z-coordinate value of each cell using a minimum z-coordinate value of point cloud data included in each cell of the grid, and filtering point cloud data using the plurality of cells to extract floor data of the road.

[0025] The above grid generation step may include a step of generating a driving interval point using only the x-coordinate and y-coordinate values ​​of the point cloud data, ignoring the z-coordinate value along the driving direction based on the driving line on the road; and a step of generating the grid using the x-coordinate and y-coordinate before and after the driving interval point using the driving interval point.

[0026] The above-mentioned bottom surface data extraction step may include a step of setting the minimum z-coordinate value of point cloud data included in each cell of the grid as the z-coordinate value of each cell; and a step of filtering point cloud data existing under the plurality of cells.

[0027]

[0028] According to one aspect of the present invention, a point cloud road floor extraction system and method can be provided, which can quickly and simply extract road floor data having information necessary for autonomous driving, such as lanes, road signs, crosswalks, and stop lines, by ignoring the z-coordinate of point cloud (PCL) data collected on a road, generating a grid including a plurality of cells using x-coordinates and y-coordinates, setting the z-coordinate value of each cell using the minimum z-coordinate value of point cloud data included in each cell of the grid, and filtering the point cloud data using the plurality of cells.

[0029] In addition, the point cloud road floor extraction system and method according to one embodiment of the present invention extracts only road floor data that has information necessary for autonomous driving, such as lanes, road signs, crosswalks, and stop lines, and provides the data to the autonomous vehicle, thereby reducing the amount of data that the autonomous vehicle must process during autonomous driving, thereby enabling autonomous driving to be performed efficiently.

[0030] The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention belongs from the description below.

[0031]

[0032] FIG. 1 is a diagram illustrating an example of mobile cloud data collected by a vehicle equipped with a mobile mapping system (MMS).

[0033] FIG. 2 is a drawing illustrating an example of road floor data extracted from the mobile cloud data of FIG. 1 by a point cloud road floor surface extraction system and method according to one embodiment of the present invention.

[0034] FIG. 3 is a schematic diagram illustrating a point cloud road floor extraction system according to one embodiment of the present invention.

[0035] FIG. 4 is a diagram illustrating a process of generating a grid by a grid generation unit of a point cloud road floor extraction system according to one embodiment of the present invention.

[0036] FIG. 5 is a diagram illustrating a process in which a z-coordinate value setting module of a floor surface data extraction unit of a point cloud road floor surface extraction system according to one embodiment of the present invention interpolates the z-coordinate value of a cell.

[0037] FIG. 6 is a diagram illustrating a process in which a filtering module of a floor data extraction unit of a point cloud road floor extraction system according to one embodiment of the present invention filters point cloud data.

[0038] Figure 7 is a flowchart for explaining a point cloud road floor surface extraction method according to one embodiment of the present invention.

[0039] FIG. 8 is a block diagram illustrating a computer system for implementing a point cloud road floor surface extraction method according to one embodiment of the present invention.

[0040]

[0041] The advantages and features of the present invention, and the methods for achieving them, will become clear with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and these embodiments are provided only to make the disclosure of the present invention complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Meanwhile, the terminology used in this specification is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated in the phrase. The terms "comprises" and / or "comprising" as used in the specification do not exclude the presence or addition of one or more other components, steps, operations, and / or elements mentioned.

[0042] In describing the present invention, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the present invention, the detailed description is omitted.

[0043] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. In order to facilitate an overall understanding in describing the present invention, the same reference numbers will be used for the same means regardless of the drawing numbers.

[0044]

[0045] FIG. 1 is a diagram illustrating an example of mobile cloud data collected by a vehicle equipped with a mobile mapping system (MMS).

[0046] Referring to Figure 1, the mobile cloud data initially collected by a vehicle equipped with an MMS includes not only road floor data, which includes information such as lanes, road signs, crosswalks, and stop lines that are practically necessary for autonomous driving, but also various information such as structures, buildings, and vehicles around the road. Therefore, if the point cloud data collected by a vehicle equipped with an MMS is directly provided to an autonomous vehicle, the autonomous vehicle must process data other than road floor data during autonomous driving, which is inefficient and results in more time being consumed.

[0047]

[0048] FIG. 2 is a drawing illustrating an example of road floor data extracted from the mobile cloud data of FIG. 1 by a point cloud road floor surface extraction system and method according to one embodiment of the present invention.

[0049] Referring to FIG. 2, according to the point cloud road floor extraction system and method according to an embodiment of the present invention, only the road floor data including information such as lanes, road signs, crosswalks, and stop lines, which are practically necessary information for autonomous driving, can be extracted. As illustrated, it can be confirmed that point cloud data of structures, buildings, vehicles, etc. around the road that are unnecessary for autonomous driving of an autonomous vehicle have been removed. In this way, the point cloud road floor extraction system and method according to an embodiment of the present invention extracts only the road floor data containing information necessary for autonomous driving and provides it to an autonomous vehicle, thereby reducing the amount of data that the autonomous vehicle must process during autonomous driving, thereby enabling autonomous driving to be performed efficiently.

[0050]

[0051] FIG. 3 is a schematic diagram illustrating a point cloud road floor extraction system according to one embodiment of the present invention.

[0052] Referring to FIG. 3, a point cloud road floor extraction system (100) according to an embodiment of the present invention is configured to include a point cloud data storage unit (110), a data filtering unit (120), a grid generation unit (130), and a floor data extraction unit (140). The point cloud road floor extraction system (100) illustrated in FIG. 3 is according to an embodiment, and the components of the point cloud road floor extraction system (100) according to the present invention are not limited to the embodiment illustrated in FIG. 3, and may be added, changed, or deleted as needed.

[0053]

[0054] The point cloud data storage unit (110) stores point cloud (PCL) data collected on the road. Point cloud data is data collected by Lidar sensors, RGB-D sensors, etc. These sensors send light / signals to objects and record the return time, calculate distance information for each light / signal, and create a single point. Point cloud data refers to a set cloud of multiple points spread across a three-dimensional space collected from these sensors. In one embodiment, the point cloud data stored in the point cloud data storage unit (110) may be data collected from a Lidar sensor equipped in the MMS. An example of point cloud data stored in the point cloud data storage unit (110) may be the same as the point cloud data illustrated in FIG. 1.

[0055] In one embodiment, point cloud data may be stored in the point cloud data storage unit (110) in the LAS file format. Due to the characteristics of the LAS file format, when point cloud data is collected on a road using a lidar sensor, the data is collected by dividing it into left and right along the driving path of the MMS vehicle. Accordingly, when point cloud data is collected on a road, a driving line (10) can be expressed by converting the left and right divided time points into points and converting them into lines on the point cloud data.

[0056]

[0057] The data filtering unit (120) filters the point cloud data stored in the point cloud data storage unit (110). The data filtering unit (120) is used to reduce the amount of data to be processed when extracting floor data in the point cloud road floor extraction system (100) according to one embodiment of the present invention, thereby increasing the processing speed and increasing the accuracy of the processing results.

[0058] In one embodiment, the data filtering unit (120) can perform filtering by batch shifting the signal intensity values ​​of the point cloud data stored in the point cloud data storage unit (110) and amplifying and trimming the deviation between the signal intensity values. The point cloud data (.las) collected from the MMS vehicle is composed of a single record of 3D point coordinates composed of x, y, and z, signal intensity, GPS time, etc. First, the data filtering unit (120) batch shifts the signal intensity values. This is the same concept as the brightness filter in image processing. Then, the data filtering unit (120) performs a process of amplifying and trimming the deviation between the signal intensity values. This is the same concept as the contrast filter in image processing. Through this process, the data filtering unit (120) can remove noise from the point cloud data.

[0059] And, in one embodiment, the data filtering unit (120) may perform a drive near filter to extract only point cloud data within a predetermined distance based on a driving line (10), which is converted into a line by collecting points at the left and right points when point cloud data stored in the point cloud data storage unit (110) is collected on the road. The point cloud data also includes information related to trees, structures, etc. around the road, which is unnecessary for extracting the floor surface. Therefore, the data filtering unit (120) may leave only the point cloud data necessary for extracting the floor surface through the drive near filter. In one embodiment, the predetermined distance for the data filtering unit (120) to extract point cloud data based on the driving line (10) may be a distance necessary for leaving only information related to the road in the point cloud data, and may change depending on the width of the road.

[0060]

[0061] The grid generation unit (130) ignores the z-coordinate of the point cloud data and generates a grid including a plurality of cells using the x-coordinate and the y-coordinate. The grid is a collection of horizontal and vertical lines and includes a plurality of cells divided by the horizontal and vertical lines. In one embodiment, the point cloud road floor extraction system (100) according to one embodiment of the present invention sets the z-coordinate value of each cell using the minimum z-coordinate value of the point cloud data included in each cell of the grid, and can filter the point cloud data using these multiple cells.

[0062] And in one embodiment, the grid generation unit (130) may include a driving interval point generation module (131) and a grid generation module (131). With reference to FIG. 4 below, the process of generating a grid by the grid generation unit (130) of the point cloud road floor extraction system (100) according to one embodiment of the present invention will be described in detail.

[0063]

[0064] FIG. 4 is a diagram illustrating a process of generating a grid by a grid generation unit of a point cloud road floor extraction system according to one embodiment of the present invention.

[0065] Referring to FIG. 4, first, a driving line (10) is expressed on point cloud data (S210). The driving interval point generation module (131) generates a driving interval point (20) using only the x-coordinate and y-coordinate values, ignoring the z-coordinate value of the point cloud data along the driving direction based on the driving line (10) on the road (S220). Then, the grid generation module (132) generates a grid (30) using the x-coordinate and y-coordinate before and after the driving interval point (20) using the driving interval point (20) (S230). Then, point cloud data matching the area of ​​each cell is searched for among a plurality of cells of the generated grid (30) (S240). That is, point cloud data matching the x-coordinate and y-coordinate values ​​within each cell is searched for.

[0066]

[0067] Returning to FIG. 1 again, the floor data extraction unit (140) sets the z-coordinate value of each cell using the minimum z-coordinate value of the point cloud data included in each cell of the grid, and extracts the floor data of the road by filtering the point cloud data using a plurality of cells. That is, by setting the minimum z-coordinate value of the point cloud data located at the lowest surface in each cell of the grid as the z-coordinate value of each cell, and filtering the point cloud data using a plurality of cells in which the z-coordinate values ​​are set in this way, it is possible to obtain data with the lowest height, i.e., the floor data.

[0068] In one embodiment, the floor data extraction unit (140) may include a z-coordinate value setting module (141) and a filtering module (142). The z-coordinate value setting module (141) sets the minimum z-coordinate value of point cloud data included in each cell of the grid as the z-coordinate value of each cell.

[0069] In the case of an actual road surface, since it is not flat and has an uphill or downhill slope, when the minimum z-coordinate value of the point cloud data included in each cell of the grid is set as the z-coordinate value of each cell in the z-coordinate value setting module (141), the height of each cell may be different. Accordingly, the z-coordinate value setting module (141) can interpolate the z-coordinate value of each cell so that the height of each cell gradually changes to reflect the slope of the actual road surface.

[0070] Referring to FIG. 5 below, a process in which the z-coordinate value setting module (141) of the floor data extraction unit (140) of the point cloud road floor surface extraction system (100) according to one embodiment of the present invention interpolates the z-coordinate value of a cell will be specifically described.

[0071]

[0072] FIG. 5 is a diagram illustrating a process in which a z-coordinate value setting module of a floor surface data extraction unit of a point cloud road floor surface extraction system according to one embodiment of the present invention interpolates the z-coordinate value of a cell.

[0073] In one embodiment, the z-coordinate value setting module (141) of the floor surface data extraction unit (140) interpolates the z-coordinate values ​​of the contact points between the cells located forward and backward along the driving direction when there is an increase or decrease in the z-coordinate values ​​between the cells located forward and backward along the driving direction among a plurality of cells in the grid. The method of interpolating the z-coordinate values ​​of the contact points between the cells differs depending on whether the actual road surface is uphill or downhill, and this will be described with reference to FIG. 5.

[0074] First, as described with reference to FIG. 4, the grid generation unit (130) finds point cloud data matching the area of ​​each cell for a plurality of cells of the generated grid, and then, as illustrated in FIG. 5, the z-coordinate value setting module (141) sets the z-coordinate value of each cell using the minimum z-coordinate value of the point cloud data included in each cell of the grid (S310). As illustrated in step (S310) of FIG. 5, since the z-coordinate value of each cell is set to the minimum z-coordinate value of the point cloud data included in each cell of the grid, in the case of an uphill road, the z-coordinate value of the frontmost end in the driving direction in each cell can be set as the z-coordinate value of the corresponding cell, and in the case of a downhill road, the z-coordinate value of the rearmost end in the driving direction in each cell can be set as the z-coordinate value of the corresponding cell.

[0075] And the z-coordinate value setting module (141) interpolates the z-coordinate value of the contact point between each cell depending on whether the actual road surface is uphill or downhill (S320). In one embodiment, when the actual road surface is an uphill slope, as shown on the left side of step (S320) of FIG. 5, and the z-coordinate value increases from the first cell (31) to the second cell (32) in the driving direction among the plurality of cells in the grid, the z-coordinate value setting module (141) sets the z-coordinate value of the second cell (32) to the z-coordinate value of the first tangent line where the first cell (31) and the second cell (32) meet, and sets the z-coordinate value of the first cell (31) to the z-coordinate value of the second tangent line opposite the first tangent line portion in the first cell (31), thereby interpolating the z-coordinate value of the first cell (31) so that the z-coordinate value of the first cell (31) increases from the second tangent line to the first tangent line.

[0076] And in another embodiment, when the actual road surface corresponds to a downhill slope, as on the right side of step (S320) of FIG. 5, and the z-coordinate value decreases from the third cell (33) to the fourth cell (34) in the driving direction among the plurality of cells in the grid, the z-coordinate value setting module (141) sets the z-coordinate value of the third cell (33) to the z-coordinate value of the third tangent line where the third cell (33) and the fourth cell (34) meet, and sets the z-coordinate value of the fourth cell (34) to the z-coordinate value of the fourth tangent line opposite the third tangent line portion in the fourth cell (34), thereby interpolating the z-coordinate value of the fourth cell so that the z-coordinate value of the fourth cell (34) decreases from the third tangent line to the fourth tangent line.

[0077] When performing interpolation in this way, since the cell located at the very end does not have the z-coordinate value of the subsequent cell, the z-coordinate value setting module (141) calculates the difference in Δz, i.e., the z-coordinate value, between the cell located at the very end and the previous cell, and adds Δz to the z-coordinate value of the cell located at the very end to apply it to the rear tangent of the cell located at the very end.

[0078] By performing interpolation through this process, each cell is interpolated according to the slope of the actual road surface, as shown in the interpolation result in step (S330). Through the process of FIGS. 4 and 5, the point cloud road floor extraction system (100) according to one embodiment of the present invention can generate a minimum z grid table (Min-z Grid Table) for filtering floor data from point cloud data.

[0079]

[0080] Returning to FIG. 1, the filtering module (142) filters point cloud data existing under a plurality of cells. In one embodiment, the filtering module (142) may filter point cloud data using the minimum z grid table generated through the processes of FIGS. 4 and 5. Generating the minimum z grid table in this way and filtering point cloud data using the same may be referred to as a minimum z grid filter (Min-z Grid Filter). Hereinafter, with reference to FIG. 6, the process of the filtering module (142) of the floor data extraction unit (140) of the point cloud road floor extraction system (100) according to one embodiment of the present invention filtering point cloud data will be described in detail.

[0081]

[0082] FIG. 6 is a diagram illustrating a process in which a filtering module of a floor data extraction unit of a point cloud road floor extraction system according to one embodiment of the present invention filters point cloud data.

[0083] Referring to FIG. 6, the filtering module (142) can filter the point cloud data by determining whether a point (c) of the point cloud data is located below two points (a, b) included in the cell using the Counter ClockWise (CCW) algorithm. The CCW algorithm is a geometric algorithm used when there are three points and you want to know the direction of the straight line connecting these three points. In FIG. 6, if the direction of a->b->c is determined to be clockwise, it can be determined that c is located below the cell including a and b. The filtering module (142) can extract the floor data by extracting the points located below the cell for the point cloud data matching the area of ​​each cell using the CCW algorithm.

[0084]

[0085] Figure 7 is a flowchart for explaining a point cloud road floor surface extraction method according to one embodiment of the present invention.

[0086] As illustrated in FIG. 7, a point cloud road lane extraction method according to one embodiment of the present invention may include steps S410 to S440.

[0087] Step S410 is a step of storing point cloud (PCL) data collected on the road in the point cloud data storage unit (110).

[0088] Step S420 is a step of filtering the stored point cloud data in the data filtering unit (120). In one embodiment, the data filtering unit (120) may perform filtering by batch-shifting the signal intensity values ​​of the stored point cloud data and amplifying and trimming the deviation between the signal intensity values. In another embodiment, the data filtering unit (120) may perform a drive near filter that extracts only the point cloud data within a predetermined distance based on a driving line that is converted into a line by gathering the left and right points of time when the stored point cloud data is collected on the road.

[0089] Step S430 is a step of generating a grid including a plurality of cells using the x-coordinate and the y-coordinate, while ignoring the z-coordinate of the point cloud data in the grid generation unit (130). In one embodiment, step S430 may include a step of generating a driving interval point using only the x-coordinate and the y-coordinate, while ignoring the z-coordinate value of the point cloud data along the driving direction based on the driving line on the road; and a step of generating a grid using the x-coordinate and the y-coordinate before and after the driving interval point using the driving interval point.

[0090] Step S440 is a step of extracting road floor data by using the minimum z-coordinate value of point cloud data included in each cell of the grid in the floor data extraction unit (140) to set the z-coordinate value of each cell, and filtering the point cloud data using a plurality of cells. In one embodiment, step S440 may include a step of setting the minimum z-coordinate value of point cloud data included in each cell of the grid as the z-coordinate value of each cell; and a step of filtering point cloud data existing under the plurality of cells.

[0091]

[0092] The point cloud road floor extraction method according to one embodiment of the present invention described above has been described with reference to the flowchart presented in the drawings. For simplicity, the method has been depicted and described as a series of blocks. However, the present invention is not limited to the order of the blocks. Some blocks may occur in a different order or simultaneously with other blocks than depicted and described herein, and various other branches, flow paths, and block orders that achieve the same or similar results may be implemented. Furthermore, not all depicted blocks may be required to implement the method described herein.

[0093]

[0094] In the description with reference to FIG. 7, each step may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Furthermore, some steps may be omitted as needed, and the order of the steps may be changed. Furthermore, even if other omitted content is included, the content of FIGS. 1 through 6 may be applied to the content of FIG. 7. Furthermore, the content of FIG. 7 may be applied to the content of FIGS. 1 through 6.

[0095]

[0096] FIG. 8 is a block diagram illustrating a computer system for implementing a point cloud road floor surface extraction method according to one embodiment of the present invention.

[0097] Referring to FIG. 8, a computer system (1000) may include at least one of a processor (1010), a memory (1030), an input interface device (1050), an output interface device (1060), and a storage device (1040) that communicate via a bus (1070). The computer system (1000) may further include a communication device (1020) coupled to a network. The processor (1010) may be a central processing unit (CPU), or a semiconductor device that executes instructions stored in the memory (1030) or the storage device (1040). The memory (1030) and the storage device (1040) may include various forms of volatile or non-volatile storage media. For example, the memory may include a read-only memory (ROM) and a random access memory (RAM). In embodiments of the present disclosure, the memory may be located internally or externally to the processor, and the memory may be connected to the processor via various known means. Memory is a variety of volatile or non-volatile storage media, and may include, for example, read-only memory (ROM) or random access memory (RAM).

[0098] Accordingly, embodiments of the present invention may be implemented as a computer-implemented method or as a non-transitory computer-readable medium storing computer-executable instructions. In one embodiment, when executed by a processor, the computer-readable instructions may perform a method according to at least one aspect of the present disclosure.

[0099] The communication device (1020) can transmit or receive wired or wireless signals.

[0100] In addition, the method according to the embodiment of the present invention may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium.

[0101] The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable medium may be specially designed and configured for embodiments of the present invention, or may be known and usable by those skilled in the art of computer software. The computer-readable recording medium may include a hardware device configured to store and execute the program commands. For example, the computer-readable recording medium may be a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical medium such as a CD-ROM or a DVD, a magneto-optical medium such as a floptical disk, a ROM, a RAM, a flash memory, etc. The program commands may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer through an interpreter, etc.

[0102]

[0103] For reference, components according to embodiments of the present invention may be implemented in the form of software or hardware such as a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC), and may perform certain roles.

[0104] However, 'components' are not limited to software or hardware, and each component may be configured to reside on an addressable storage medium or configured to trigger one or more processors.

[0105] Thus, as an example, components include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

[0106] Components and the functionality provided within those components may be combined into a smaller number of components or further separated into additional components.

[0107]

[0108] Meanwhile, it will be understood that each block of the flowchart drawings and combinations of the flowchart drawings can be performed by computer program instructions. These computer program instructions can be installed on a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flowchart block(s). The computer program instructions can also be installed on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executable process, so that the instructions executed by the computer or other programmable data processing equipment can also provide steps for performing the functions described in the flowchart block(s).

[0109] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions.

[0110]

[0111] The term 'part' or 'module' used in this embodiment means a software or hardware component such as an FPGA or ASIC, and the 'part' or 'module' performs certain roles. However, the 'part' or 'module' is not limited to software or hardware. The 'part' or 'module' may be configured to be on an addressable storage medium and may be configured to play one or more processors. Thus, as an example, the 'part' or 'module' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and '~sub-parts' or '~modules' may be combined into a smaller number of components and '~sub-parts' or '~modules' or further separated into additional components and '~sub-parts' or '~modules'. In addition, the components and '~sub-parts' or '~modules' may be implemented to regenerate one or more CPUs within the device or secure multimedia card.

[0112]

[0113] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A point cloud data storage unit that stores point cloud (PCL) data collected on the road; A grid generation unit that ignores the z-coordinate of the above point cloud data and generates a grid including multiple cells using the x-coordinate and y-coordinate; and A point cloud road floor extraction system characterized by including a floor data extraction unit that sets the z-coordinate value of each cell using the minimum z-coordinate value of point cloud data included in each cell of the grid, and extracts the floor data of the road by filtering the point cloud data using the plurality of cells.

2. In paragraph 1, The above grid generation unit, A driving interval point generation module that generates a driving interval point using only the x-coordinate and y-coordinate values, ignoring the z-coordinate value of the point cloud data along the driving direction based on the driving line on the road; and A point cloud road floor extraction system characterized by including a grid generation module that generates the grid using the x-coordinate and y-coordinate before and after the driving interval point using the driving interval point.

3. In paragraph 1, The above floor surface data extraction unit is, A z-coordinate value setting module that sets the minimum z-coordinate value of point cloud data included in each cell of the above grid as the z-coordinate value of each cell; and A point cloud road surface extraction system characterized by including a filtering module for filtering point cloud data existing under the plurality of cells.

4. In paragraph 3, The above z-coordinate value setting module is, A point cloud road floor extraction system characterized in that, when there is an increase or decrease in the z-coordinate value according to the driving direction between cells located forward and backward along the driving direction among a plurality of cells within the above grid, the z-coordinate value of the indirect point portion of the cells located forward and backward is interpolated.

5. In paragraph 4, The above z-coordinate value setting module is, A point cloud road floor extraction system, characterized in that, when a z-coordinate value increases from the first cell to the second cell in the driving direction among a plurality of cells in the grid, the z-coordinate value of the second cell is set to the z-coordinate value of the first tangent line where the first cell and the second cell meet, and the z-coordinate value of the first cell is set to the z-coordinate value of the second tangent line opposite the first tangent line portion in the first cell, so that the z-coordinate value of the first cell increases as it goes from the second tangent line to the first tangent line.

6. In paragraph 4, The above z-coordinate value setting module is, A point cloud road surface extraction system, characterized in that, when the z-coordinate value decreases from the third cell to the fourth cell in the driving direction among the plurality of cells in the grid, the z-coordinate value of the third cell is set to the z-coordinate value of the third tangent line where the third cell and the fourth cell meet, the z-coordinate value of the fourth cell is set to the z-coordinate value of the fourth tangent line opposite the third tangent line portion in the fourth cell, and the z-coordinate value of the fourth cell is interpolated so that the z-coordinate value of the fourth cell decreases from the third tangent line to the fourth tangent line.

7. In paragraph 3, The above filtering module, A point cloud road surface extraction system characterized in that it filters the point cloud data by determining whether a point of the point cloud data is located below two points included in the cell using a Counter ClockWise (CCW) algorithm.

8. Point cloud data storage step for storing point cloud (PCL) data collected on the road; A grid generation step of generating a grid including multiple cells using x-coordinates and y-coordinates while ignoring the z-coordinate of the above point cloud data; and A point cloud road floor extraction method characterized by comprising a floor surface data extraction step of setting the z-coordinate value of each cell using the minimum z-coordinate value of point cloud data included in each cell of the grid, and extracting the floor surface data of the road by filtering the point cloud data using the plurality of cells.

9. In paragraph 8, The above grid generation step is, A step of generating a driving interval point using only the x-coordinate and y-coordinate values, ignoring the z-coordinate value of the point cloud data along the driving direction based on the driving line on the road; and A point cloud road floor extraction method characterized by comprising a step of generating the grid using the x-coordinate and y-coordinate before and after the driving interval point using the driving interval point.

10. In paragraph 8, The above floor surface data extraction step is: A step of setting the minimum z-coordinate value of the point cloud data included in each cell of the above grid as the z-coordinate value of each cell; and A point cloud road floor extraction method, characterized in that it comprises a step of filtering point cloud data existing under the plurality of cells.

Images