KR102727664B1 - System and method for road polyline object evaluation using point cloud automatic analysis results - Google Patents

Abstract

A road linear object evaluation system and method using the results of automatic point cloud analysis are disclosed. The road linear object evaluation system using the results of automatic point cloud analysis includes: a point cloud data storage unit that stores point cloud (PCL) data collected on a road; a lane extraction unit that analyzes the point cloud data to extract a lane; a parallel determination unit that determines whether a first line formed by a 0th point and a 1st point and a second line formed by a 3rd point and a 4th point extracted by the lane extraction unit are parallel; and an abnormality detection unit that determines whether there is an abnormality according to whether preset abnormality detection criteria conditions are satisfied based on whether the first and second lines are parallel.

Description

{System and method for road polyline object evaluation using point cloud automatic analysis results}

The present invention relates to a system and method for evaluating a road linear object using the results of automatic analysis of a point cloud, and more particularly, to a system and method for evaluating a road linear object using the results of automatic analysis of a point cloud, which extracts a lane using point cloud (PCL) data collected on a road, finds a plurality of reference points among the constituent points of the extracted lane linearity, extracts a plurality of straight lines, and determines whether each of the plurality of straight lines falls within a preset reference error value depending on whether they are parallel, thereby detecting whether there is an abnormality in a road linearity (road polyline).

Autonomous vehicles are vehicles that can sense their surroundings and movements with little or no human intervention or input. In order for such autonomous vehicles to be realized, various sensors that can sense the surroundings, such as lidar, radar, computer vision, GPS, odometry, and inertial measurement units, must be combined, and more specifically, the sensing actions of various physical sensors and logical road information technology pre-configured with HD-Map data authoring technology must be combined.

In particular, real-time data and transmission technology are needed to provide vehicle operation support information to autonomous vehicles so that autonomous vehicles can easily identify surrounding traffic conditions that are difficult to detect. For example, LDM (Local Dynamic Map) is a technology that links, stores, and manages standardized vehicle operation support information for autonomous cooperative driving. It should provide information to autonomous vehicles in real time by integrating road traffic and surrounding vehicle conditions (dynamic information) based on a precise electronic map (or static information) at the lane level.

Autonomous driving of vehicles (autonomous vehicles) 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.

Such 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.

In particular, recognizing lanes and driving along a designated lane can be said to be the most basic technology for safe driving with manned vehicles.

There is a method based on images acquired through a camera to recognize lanes on the road, but it has the disadvantage of low recognition accuracy when the surrounding light is insufficient. Accordingly, technology for recognizing lanes on the road using Lidar sensors is being developed recently.

A lidar sensor is a device that precisely draws the surroundings by measuring the distance to objects and the intensity of the signal that is reflected back from the medium where the pulse collided after firing a laser pulse onto the road surface. 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 utilization technology and scope of use can be seen to be different.

This lidar is one component of the Mobile Mapping System (MMS), and in addition to the lidar, the MMS also includes a camera, an inertial measurement unit (IMU), GPS, and a distance measurement indicator (DMI).

Accordingly, information acquired through MMS collection equipment (vehicle) integrating lidar sensors, image sensors, IMU, and GPS equipment can obtain specific road configuration information (signal reflection intensity of the medium, absolute position of the medium, continuity, etc.), i.e. high-precision digital map data.

In general, point cloud data collected by vehicles equipped with MMS equipment includes various information such as structures, buildings, and vehicles around the road. However, the information that is actually needed for autonomous driving in the point cloud data is the road floor data including information such as lanes, road signs, crosswalks, and stop lines. If point cloud data collected by LiDAR equipment is provided as is to autonomous vehicles, there is a problem that automatic detection results may be erroneous due to noise (missed collection sections due to weak signal collection, driving traces of vehicles driving side by side in the adjacent lane, etc.) caused by vehicles in the adjacent lane.

The purpose of the present invention is to provide a system and method for evaluating a road linearity object using the results of an automatic analysis of a point cloud, which evaluates the continuity and consistency of a road surface linearity (lane, center line, curb, etc.) cartographed with HD map data, extracts a lane using point cloud (PCL) data collected on a road, finds a plurality of reference points among the constituent points of the extracted lane linearity, extracts a plurality of straight lines, and determines whether each of the plurality of straight lines falls within a preset reference error value depending on whether they are parallel, thereby detecting an abnormality in the road linearity (Road Polyline), as well as providing a method for examining the suitability of an entire road linearity created for the purpose of constructing an HD-MAP.

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.

According to one embodiment of the present invention, a road linear object evaluation system using a point cloud automatic analysis result comprises: a point cloud data storage unit that stores point cloud (PCL) data collected on a road; a lane extraction unit that analyzes the point cloud data to extract a lane; a parallel judgment unit that determines whether a first line formed by a 0th point and a 1st point and a second line formed by a 3rd point and a 4th point extracted by the lane extraction unit are parallel; and an abnormality detection unit that determines whether there is an abnormality depending on whether preset abnormality detection criteria conditions are satisfied based on whether the first and second lines are parallel.

The above-mentioned abnormality detection unit may store a first vertical distance calculated as a vertical distance between the second point and a third line connecting the first point and the third point, as a first error value, if it is determined that the first line and the second line are parallel.

The above-described anomaly detection unit, if it is determined that the first line and the second line are not parallel, calculates an extended intersection point (pK) of the first line and the second line, and can generate a Bezier curve connecting the first point and the third point using the first point, the third point, and the extended intersection point.

The above-mentioned abnormality detection unit can store a second vertical distance calculated as a vertical distance between the Bezier curve and the second point as a second error value.

The road linear object evaluation system using the above point cloud automatic analysis results is configured to further include an error range verification unit that verifies whether the first error value and the second error value detected by the above anomaly detection unit are within a preset error range.

According to one embodiment of the present invention, a road linear object evaluation method using a point cloud automatic analysis result is configured to include a point cloud data storage step, which is performed in a point cloud data storage unit and stores point cloud (PCL) data collected on a road; a lane extraction step, which is performed in a lane extraction unit and analyzes the point cloud data to extract a lane; a parallel determination step, which is performed in a parallel determination unit and determines whether a first line composed of a 0th point and a first point, and a second line composed of a third point and a fourth point extracted from the lane extraction unit are parallel; and an abnormality detection step, which is performed in an abnormality detection unit and determines whether there is an abnormality depending on whether preset abnormality detection criteria conditions are satisfied based on whether the first line and the second line are parallel.

The above-described abnormality detection step may include a step of storing a first vertical distance calculated as a vertical distance between a third line connecting the first point and the third point and the second point as a first error value, if it is determined that the first line and the second line are parallel.

The above-described abnormality detection step may include a step of calculating an extended intersection point (pK) of the first line and the second line, if it is determined that the first line and the second line are not parallel, and generating a Bezier curve connecting the first point and the third point using the first point, the third point, and the extended intersection point.

The above-mentioned abnormality detection step may include a step of storing a second vertical distance calculated as a vertical distance between the Bezier curve and the second point as a second error value.

The road linear object evaluation method using the above point cloud automatic analysis results is performed in an error range verification unit, and may further include an error range verification step for verifying whether the first error value and the second error value detected in the above abnormality detection step are within a preset error range.

According to one aspect of the present invention, the present invention relates to a system and method for evaluating a road linear object using a result of automatic analysis of a point cloud, wherein the system and method extract a lane using point cloud (PCL) data collected on a road, finds a plurality of reference points among constituent points of the extracted lane linearity, extracts a plurality of straight lines, and determines whether each of the plurality of straight lines falls within a preset reference error value depending on whether they are parallel, thereby detecting whether an abnormality in a road linearity (Road Polyline) is present.

In addition, the system and method for evaluating road linear objects using the results of automatic point cloud analysis according to one embodiment of the present invention interpolates errors in the results of automatic detection caused by noise (missed collection sections due to weak signal collection, driving traces of vehicles driving side by side in the adjacent lane, etc.) due to vehicles in the adjacent lane into an appropriate linear interpolation result, thereby detecting and removing road linear error points, and extracting more accurate lanes.

The effects obtainable from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below.

Figure 1 is a drawing illustrating an example of an automatic analysis evaluation method using a road linear object evaluation system and method using the results of automatic point cloud analysis.
FIG. 2 is a drawing illustrating a road linear object evaluation system (200) using the results of automatic point cloud analysis.
FIG. 3 is a drawing illustrating an example of determining whether a first line and a second line are parallel when they are parallel from a parallel detection unit by a road linear object evaluation system and method using a point cloud automatic analysis result according to one embodiment of the present invention.
FIG. 4 is a diagram schematically illustrating a process of calculating a second point and performing interpolation when a first line and a second line are parallel according to one embodiment of the present invention.
FIG. 5 is a drawing illustrating an example of determining whether a first line and a second line from a parallel detection unit are parallel when they are not parallel by a road linear object evaluation system and method using a point cloud automatic analysis result according to one embodiment of the present invention.
FIG. 6 is a diagram schematically illustrating a process of calculating a second point and performing interpolation when the first line and the second line are not parallel according to one embodiment of the present invention.
FIG. 7 is a block diagram showing a computer system for implementing a road linear object evaluation method using point cloud automatic analysis results according to one embodiment of the present invention.
FIG. 8 is a block diagram showing a computer system for implementing a road linear object evaluation method using point cloud automatic analysis results according to one embodiment of the present invention.

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 only these embodiments are provided to make the disclosure of the present invention complete, and to fully inform a person having ordinary skill in the art to which the present invention belongs 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.

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.

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

Figure 1 is a drawing illustrating an example of an automatic analysis evaluation method using a road linear object evaluation system and method using the results of automatic point cloud analysis.

Referring to FIG. 1, according to the system and method for evaluating road linear objects using the automatic analysis results of a point cloud according to an embodiment of the present invention, only data including lane information, which is information practically necessary 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 system and method for evaluating road linear objects using the automatic analysis results of a point cloud according to an embodiment of the present invention interpolates automatic detection result errors caused by noise (missed collection sections, weak signal strength) due to vehicles in adjacent lanes, etc. into an appropriate linear interpolation, thereby detecting and removing road linear error points, thereby enabling more accurate lane extraction.

FIG. 2 is a drawing illustrating a road linear object evaluation system (200) using the results of automatic point cloud analysis.

Referring to FIG. 2, a road linear object evaluation system (200) using a cloud automatic analysis result is configured to include a point cloud data storage unit (210), a lane extraction unit (220), a parallel determination unit (230), an anomaly detection unit (240), and an error range confirmation unit (250). The road linear object evaluation system (200) using a cloud automatic analysis result illustrated in FIG. 2 is according to one embodiment, and the components of the road linear object evaluation system (200) using a cloud automatic analysis result according to the present invention are not limited to the embodiment illustrated in FIG. 2, and may be added, changed, or deleted as needed.

The point cloud data storage unit (210) stores point cloud (PCL) data collected on the road. The point cloud data is data collected by a Lidar sensor, an RGB-D sensor, etc. These sensors send light/signal to an object and record the time it takes for it to return, calculate distance information for each light/signal, and generate one point. The point cloud data refers to a set cloud of multiple points spread over a three-dimensional space collected from these sensors. In one embodiment, the point cloud data stored in the point cloud data storage unit (210) may be data collected from a Lidar sensor equipped in the MMS.

In one embodiment, point cloud data may be stored in the point cloud data storage unit (210) in the las file format. Due to the characteristics of the las file format, when point cloud data is collected on the road via 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 the road, the lane (driving line) that is converted into a line by gathering the time points divided into left and right as points can be expressed on the point cloud data.

The lane extraction unit (220) can extract lanes by analyzing information collected from the point cloud data storage unit (210). The lane extraction unit (220) can connect points and express them as lines based on data collected repeatedly along the driving direction from the point cloud data storage unit (210).

The parallel judgment unit (230) can determine whether the first line formed by the 0th point (p0) and the first point (p1) extracted from the lane extraction unit (220) and the second line formed by the third point (p3) and the fourth point (p4) are parallel. The first line and the second line mean lines formed by the same distance, and the first and second lines can be determined to be parallel if they are formed horizontally in the driving direction (forward direction). In addition, the first line and the second line can be determined to be not parallel if they are not formed horizontally in the driving direction (forward direction).

The abnormality detection unit (240) can determine whether there is an abnormality based on whether the first and second lines are parallel and whether the preset abnormality detection criteria are satisfied. Here, when each preset abnormality detection criteria is satisfied, it is determined to be normal, and when the abnormality detection criteria are not satisfied, it is determined to be abnormal.

If the abnormality detection unit (240) determines that the first line and the second line are parallel, it can store the first vertical distance calculated as the vertical distance between the second point and the third line connecting the first point and the third point as the first error value.

If the anomaly detection unit (240) determines that the first line and the second line are not parallel, it can calculate the extended intersection point (pK) of the first line and the second line, and generate a Bezier curve connecting the first point and the third point using the first point, the third point, and the extended intersection point (pK), and store the second vertical distance calculated as the vertical distance between the Bezier curve and the second point as a second error value.

The error range verification unit (250) can verify whether the first error value and the second error value detected by the abnormality detection unit are within a preset error range.

In addition, according to one embodiment, a road linear object correction system (200) using the results of automatic point cloud analysis can evaluate the continuity and consistency of linearity (lanes, center lines, curbs, etc.) of a road surface cartographed with HD Map data.

FIG. 3 is a drawing illustrating an example of determining whether a first line and a second line are parallel when they are parallel from a parallel detection unit by a road linear object evaluation system and method using a point cloud automatic analysis result according to one embodiment of the present invention.

FIG. 4 is a diagram schematically illustrating a process of calculating a second point and performing interpolation when a first line and a second line are parallel according to one embodiment of the present invention.

Referring to FIGS. 3 and 4, in one embodiment, the point cloud data storage unit (210) repeatedly collects point cloud data (point cloud data of p0, p1, p2, p3, and p4), the lane extraction unit (220) extracts a first line by connecting p0 and p1, and a second line by connecting p3 and p4, so that the parallel determination unit (230) can determine whether the first line and the second line are parallel. When the parallel determination unit (230) determines that the first line and the second line are parallel, the vertical distance between the line connecting p1 and p3 and p2 is calculated, and if it is within a preset reference range, it can be determined as normal data. Here, the preset reference range may be an error range, and the preset reference range may be changed as necessary. In addition, the vertical distance from p2 may be repeatedly stored as an error value.

FIG. 5 is a drawing illustrating an example of determining whether a first line and a second line from a parallel detection unit are parallel when they are not parallel by a road linear object evaluation system and method using a point cloud automatic analysis result according to one embodiment of the present invention.

FIG. 6 is a diagram schematically illustrating a process of calculating a second point and performing interpolation when the first line and the second line are not parallel according to one embodiment of the present invention.

Referring to FIGS. 5 and 6, in one embodiment, the point cloud data storage unit (210) repeatedly collects point cloud data (point cloud data of p3, p4, p5, p6, and p7), the lane extraction unit (220) extracts a first line by connecting p3 and p4, and a second line by connecting p6 and p7, so that the parallel determination unit (230) can determine whether the first line and the second line are parallel. If the parallel determination unit (230) determines that the first line and the second line are not parallel, the extended intersection point (pK) with the first line and the second line is calculated, a Bezier curve connecting p4 and p5 is generated using pK, and the vertical distance between the generated Bezier curve and p2 is calculated, and if it is within a preset reference range, it can be determined as normal data. Here, the preset reference range may be an error range, and the preset reference range may be changed as needed. Additionally, the vertical distance from p2 can be repeatedly stored as an error value.

A Bezier curve is a mathematical representation of a curve used in computer graphics and animation. To draw a quadratic Bezier curve, use three points (x0, x1, x2) to draw two imaginary lines, one from x0 to x1 and the other from x1 to x2. As the start point of the first imaginary line and the end point of the second imaginary line move steadily, a third imaginary line is drawn. On this imaginary line, a point that moves steadily from the start point to the end point is drawn to form a curve.

FIG. 7 is a block diagram showing a computer system for implementing a road linear object evaluation method using point cloud automatic analysis results according to one embodiment of the present invention.

As illustrated in FIG. 7, a road linear object evaluation method using a point cloud automatic analysis result according to one embodiment of the present invention may include steps S710 to S750.

Step S710 is a step of storing point cloud (PCL) data collected on the road in the point cloud data storage unit (210).

Step S720 is a step of extracting a lane by analyzing information collected from the point cloud data storage unit (210) in the lane extraction unit (220). The lane extraction unit (220) may include a step of connecting points and expressing them as lines based on data collected repeatedly along the driving direction from the point cloud data storage unit (210).

Step S730 is performed in the parallel determination unit (230) and is a step of determining whether the first line formed by the 0th point and the 1st point extracted from the lane extraction unit (220) and the second line formed by the 3rd point and the 4th point are parallel. The first line and the second line mean lines formed at the same distance, and the step may include a step of determining that the first and second lines are parallel when they are formed horizontally in the driving direction (forward direction), and a step of determining that the first line and the second line are not parallel when they are not formed horizontally in the driving direction (forward direction).

Step S740 is performed in the abnormality detection unit (240), and includes a step of determining whether there is an abnormality depending on whether the first line and the second line are parallel and whether preset abnormality detection criteria conditions are satisfied. Here, when each preset abnormality detection criteria condition is satisfied, it is determined to be normal, and when the abnormality detection criteria condition is not satisfied, it may include a step of determining that there is an abnormality.

Step S750 is performed in the error range verification unit (250), and is a step for verifying whether the first error value and the second error value detected by the abnormality detection unit are within the preset error range.

The above-described method for evaluating a road linear object using the results of automatic point cloud analysis according to one embodiment of the present invention has been described with reference to the flow chart 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, and 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 orders of blocks that achieve the same or similar results may be implemented. Furthermore, not all of the depicted blocks may be required to implement the method described herein.

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. In addition, some steps may be omitted as needed, and the order between the steps may be changed. In addition, even if other omitted content is present, the content of FIGS. 1 to 6 may be applied to the content of FIG. 7. In addition, the content of FIG. 7 may be applied to the content of FIGS. 1 to 6.

FIG. 8 is a block diagram showing a computer system for implementing a road linear object evaluation method using point cloud automatic analysis results according to one embodiment of the present invention.

Referring to FIG. 8, the 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) communicating 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 nonvolatile 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 means known in the art. Memory is a variety of volatile or nonvolatile storage media, for example, memory may include read-only memory (ROM) or random access memory (RAM).

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

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

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 in a computer-readable medium.

The above computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the computer-readable medium may be specially designed and configured for the embodiments of the present invention, or may be known and usable to 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 media such as a hard disk, a floppy disk, and a magnetic tape, an optical media such as a CD-ROM, a DVD, a magneto-optical media such as a floptical disk, a ROM, a RAM, a flash memory, etc. The program commands may include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer through an interpreter, etc.

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 predetermined roles.

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

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.

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

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 loaded onto 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 loaded onto 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 that perform the computer or other programmable data processing equipment can also provide steps for performing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a particular logical function(s). It should also be noted that in some alternative implementation examples, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may in fact be performed substantially concurrently, or the blocks may sometimes be performed in reverse order, depending on the functionality they perform.

The term 'part' or 'module' used in this embodiment means a software or hardware component such as an FPGA or an 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 in 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, and processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, 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 the secure multimedia card.

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.

200: Road linear object evaluation system using point cloud automatic analysis results
210: Point Cloud Data Storage
220: Lane Extraction Unit
230: Parallel Judgment Section
240: Anomaly detection unit
250: Check the margin of error

Claims (10)

A point cloud data storage unit that stores point cloud (PCL) data collected on the road;
A lane extraction unit that extracts lanes by analyzing the above point cloud data;
A parallel judgment unit that determines whether a first line composed of the 0th point and the 1st point extracted from the above-mentioned lane extraction unit and a second line composed of the 3rd point and the 4th point are parallel; and
An abnormality detection unit that determines whether there is an abnormality based on whether the preset abnormality detection criteria conditions are satisfied based on whether the first and second lines are parallel; including,
The above abnormality detection unit,
If the first line and the second line are judged to be parallel, the first error value is calculated based on the second point and the third line connecting the first point and the third point,
If it is determined that the first line and the second line are not parallel, a second error value is calculated based on a curve based on the first point and the third point and a second error value based on the second point.
Road alignment object evaluation system using point cloud automatic analysis results.
In the first paragraph,
The above abnormality detection unit,
If it is determined that the first line and the second line are parallel, the first vertical distance calculated from the vertical distance between the third line connecting the first point and the third point and the second point is stored as the first error value.
Road alignment object evaluation system using point cloud automatic analysis results.
In the second paragraph,
The above abnormality detection unit,
A road alignment object evaluation system using the results of automatic point cloud analysis, characterized in that if it is determined that the first line and the second line are not parallel, the extended intersection point (pK) of the first line and the second line is calculated, and a Bezier curve connecting the first point and the third point is generated using the first point, the third point, and the extended intersection point.
In the third paragraph,
The above abnormality detection unit,
characterized in that the second vertical distance calculated from the vertical distance between the above Bezier curve and the second point is stored as the second error value.
Road alignment object evaluation system using point cloud automatic analysis results.
In the first paragraph,
The road linear object evaluation system using the above point cloud automatic analysis results is
It is characterized by further including an error range confirmation unit that confirms whether the first error value and the second error value detected by the above-mentioned abnormality detection unit are within a preset error range.
Road alignment object evaluation system using point cloud automatic analysis results.
A point cloud data storage step that is performed in the point cloud data storage unit and stores point cloud (PCL) data collected on the road;
A lane extraction step performed in a lane extraction unit, wherein the lane is extracted by analyzing the point cloud data;
A parallel judgment step performed in a parallel judgment unit, which determines whether a first line composed of the 0th point and the 1st point extracted from the lane extraction unit and a second line composed of the 3rd point and the 4th point are parallel; and
An abnormality detection step performed in an abnormality detection unit, wherein an abnormality is determined based on whether preset abnormality detection criteria conditions are satisfied based on whether the first and second lines are parallel; including,
The above abnormality detection step is,
If it is determined that the first line and the second line are parallel, a step of calculating a first error value based on the second point and the third line connecting the first point and the third point; and
If it is determined that the first line and the second line are not parallel, a step of calculating a second error value based on a curve based on the first point and the third point and the second point.
characterized by including,
A method for evaluating road alignment objects using automatic point cloud analysis results.
In Article 6,
The step of calculating the above first error value is:
A method characterized in that it comprises the step of storing a first vertical distance calculated from the vertical distance between the third line connecting the first point and the third point and the second point as the first error value, if the first line and the second line are determined to be parallel.
A method for evaluating road alignment objects using automatic point cloud analysis results.
In Article 7,
The step of calculating the second error value is:
A method for generating a Bezier curve connecting the first point and the third point by using the first point, the third point, and the extended intersection point, characterized in that it comprises the step of calculating the extended intersection point (pK) of the first line and the second line if it is determined that the first line and the second line are not parallel.
A method for evaluating road alignment objects using automatic point cloud analysis results.
In Article 8,
The step of calculating the second error value is:
A method characterized by comprising: a step of calculating a second vertical distance between the Bezier curve and the second point and storing the second vertical distance as the second error value;
A method for evaluating road alignment objects using automatic point cloud analysis results.
In Article 6,
The road linear object evaluation method using the above point cloud automatic analysis results is as follows:
It is characterized by further including an error range verification step performed in the error range verification unit and checking whether the first error value and the second error value detected in the abnormality detection step are within a preset error range.
A method for evaluating road alignment objects using automatic point cloud analysis results.