Apparatus and Method for Noise Filtering of LiDAR Sensor

The noise filtering device for LiDAR sensors addresses environmental interference by dynamically adjusting filtering thresholds based on environmental information, improving data reliability and accuracy.

KR1020260164264APending Publication Date: 2026-11-17HL KLEMOVE CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
KR1020250060374
Authority / Receiving Office
KR · KR
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-05-09
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

LiDAR sensors face challenges in maintaining accurate distance and object detection due to environmental factors affecting signal strength, leading to deteriorated performance in varying conditions.

Method used

A noise filtering device and method that dynamically adjusts the filtering threshold based on environmental information recognized by the LiDAR sensor, using a processor to calculate a correlation coefficient from intensity and ambient values in the sensing data to set optimal noise removal parameters.

Benefits of technology

Improves the reliability of sensing data by effectively removing noise based on environmental conditions, enhancing the accuracy and consistency of LiDAR sensor performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure PAT00009_ABST
    Figure PAT00009_ABST
Patent Text Reader

Abstract

The present invention relates to a noise filtering device and method for a LiDAR sensor, comprising a device having one or more processors and a memory for storing one or more programs executed by the one or more processors, wherein the processor identifies environmental information of the location where the LiDAR sensor is located using sensing data acquired from the LiDAR sensor, and dynamically sets a filtering threshold for removing noise from the sensing data based on the identified environmental information, and may be applied to other embodiments.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to a noise filtering device and method for a lidar sensor. Background Technology

[0002] A LiDAR (light detection and ranging) sensor detects an object by emitting light and receiving the signal reflected from the object, and calculates the distance to the object by measuring the time between the transmitted and received signals. Because these LiDAR sensors can acquire point clouds based on accurate distance information compared to cameras, they are utilized as essential sensors, particularly in vehicles and autonomous robots.

[0003] LiDAR sensors are primarily mounted on the front of vehicles or autonomous robots and exposed to the outside to enhance detection performance. LiDAR sensors offer relatively higher object detection probabilities and distance accuracy compared to cameras. However, since the strength of received signals decreases when affected by external environmental factors such as weather and lighting, a problem can arise where the distance and object detection accuracy of the LiDAR sensor deteriorates depending on environmental conditions.

[0004] Therefore, there is a growing need for technology that can recognize the environment being detected by the LiDAR sensor and improve the detection accuracy of the LiDAR sensor according to the environment. The problem to be solved

[0005] Embodiments of the present invention for solving these conventional problems provide a noise filtering device and method for a lidar sensor that can recognize environmental information in which the lidar sensor operates and dynamically set a noise filtering threshold of the lidar sensor based on the recognized environmental information. means of solving the problem

[0006] A noise filtering device for a lidar sensor according to an embodiment of the present invention is a device having one or more processors and a memory for storing one or more programs executed by said one or more processors, wherein the processor can identify environmental information of a location where said lidar sensor is located using sensing data acquired from the lidar sensor, and dynamically set a filtering threshold for removing noise from said sensing data based on said environmental information.

[0007] In addition, the processor can check the intensity value and ambient value in the sensing data.

[0008] In addition, the processor can determine the intensity value in the sensing data based on the wavelength of the irradiated light irradiated by the lidar sensor.

[0009] In addition, the processor can determine the ambient value in the sensing data based on the wavelength of light excluding the wavelength of the illumination light in the sensing data.

[0010] In addition, the processor can check the environment information by calculating a correlation coefficient between 0 and 1 based on the intensity value and the ambient value.

[0011] In addition, the processor may set the filtering threshold to be greater than the reference filtering threshold if the correlation coefficient is 0.5 or higher.

[0012] In addition, the processor can set the filtering threshold by gradually increasing it as the correlation coefficient approaches 1.

[0013] Additionally, if the correlation coefficient is less than 0.5, the processor may set the filtering threshold to be equal to or smaller than the reference filtering threshold.

[0014] In addition, the processor can set the filtering threshold by gradually decreasing it as the correlation coefficient approaches zero.

[0015] In addition, the processor can remove the noise by deleting intensity values ​​below the dynamically set filtering threshold from the sensing data.

[0016] In addition, a noise filtering method for a lidar sensor according to an embodiment of the present invention is a method performed by a device having one or more processors and a memory storing one or more programs executed by said one or more processors, and may include the steps of confirming environmental information of a location where said lidar sensor is located using sensing data acquired from the lidar sensor, and dynamically setting a filtering threshold for removing noise from said sensing data based on said confirmed environmental information.

[0017] In addition, it may include a step of checking intensity values ​​and ambient values ​​in the sensing data.

[0018] Additionally, the step of checking the ambient value may be a step of checking the intensity value in the sensing data based on the wavelength of the illumination light emitted by the lidar sensor.

[0019] Additionally, the step of checking the ambient value may be a step of checking the ambient value in the sensing data based on the wavelength of light excluding the wavelength of the illumination light in the sensing data.

[0020] In addition, the step of checking environmental information may be a step of checking environmental information by calculating a correlation coefficient between 0 and 1 based on the intensity value and ambient value.

[0021] In addition, if the correlation coefficient is 0.5 or higher, the step of setting the filtering threshold to be greater than the reference filtering threshold may be further included.

[0022] In addition, the step of setting the filtering threshold to be greater than the reference filtering threshold may be a step of gradually increasing the filtering threshold as the correlation coefficient approaches 1.

[0023] In addition, if the correlation coefficient is less than 0.5, the step of setting the filtering threshold to be smaller than the reference filtering threshold may be further included.

[0024] In addition, the step of setting it smaller than the reference filtering threshold may be a step of gradually decreasing the filtering threshold as the correlation coefficient approaches 0.

[0025] In addition, the method may further include a step of removing the noise by deleting intensity values ​​below the dynamically set filtering threshold from the sensing data. Effects of the invention

[0026] As described above, the noise filtering device and method for a lidar sensor according to the present invention have the effect of improving the reliability of sensing data acquired from a lidar sensor by recognizing environmental information in which the lidar sensor operates and dynamically setting the noise filtering threshold of the lidar sensor based on the recognized environmental information. Brief explanation of the drawing

[0027] FIG. 1 is a block diagram schematically showing the main configuration of a noise filtering device according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating a noise filtering method according to an embodiment of the present invention. FIG. 3 is a screen example diagram illustrating a method for classifying environments using correlation coefficients according to an embodiment of the present invention. FIG. 4 is a screen example diagram illustrating a method for dynamically setting a filtering threshold according to a classified environment according to an embodiment of the present invention. Specific details for implementing the invention

[0028] Hereinafter, specific embodiments according to the embodiments of the present disclosure will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely illustrative and the present invention is not limited thereto.

[0029] In describing the embodiments of the present disclosure, if it is determined that a detailed description of known technology related to the present invention may unnecessarily obscure the essence of the embodiments, such detailed description will be omitted. Furthermore, terms used below are defined in consideration of their functions in the present invention, and these may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. Terms used in the detailed description are intended merely to describe specific embodiments and should not be limiting. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form. In this description, expressions such as "include" or "comprise" are intended to refer to certain characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof other than those described. Additionally, terms such as “part,” “unit,” “module,” and “block” described in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software.

[0031] FIG. 1 is a block diagram schematically showing the main configuration of a noise filtering device according to an embodiment of the present invention.

[0032] Referring to FIG. 1, the device (10) according to the present invention may be a computing device, such as an electronic device, capable of dynamically setting a filtering threshold for filtering noise from sensing data acquired from a LiDAR sensor, and the device (10) may include a processor (1), a computer-readable storage medium (2), a program (3), a communication bus (4), an input / output interface (5), and a communication interface (6). The device (10) may include one or more input / output devices (7) connected through the input / output interface (5).

[0033] The processor (1) can cause the device (10) to operate according to an exemplary embodiment to be described below. For example, the processor (1) can execute one or more programs (3) stored in a computer-readable storage medium (2). One or more programs (3) may include one or more computer-executable instructions, and the computer-executable instructions may be configured to cause the device (10) to perform operations according to an exemplary embodiment when executed by the processor (1).

[0034] The communication bus (4) interconnects various components of the device (10), including a processor (1), a computer-readable storage medium (2), an input / output interface (5), and a communication interface (6).

[0035] The device (10) may include one or more input / output interfaces (5) and one or more communication interfaces (6) that provide an interface for one or more input / output devices (7). The input / output interfaces (5) and the communication interfaces (6) are connected to a communication bus (4). The input / output devices (7) may be connected to other components of the device (10) through the input / output interfaces (5). Exemplary input / output devices (7) may include input devices such as a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touchscreen), a voice or sound input device, various types of sensors including a LiDAR sensor and / or a camera, and output devices such as a display device, a speaker, a light, etc. The input / output devices (7) may be included inside the device (10) as a component constituting the device (10), or may be connected to a device separate from the device (10).

[0036] More specifically, the processor (1) can receive as sensing data reflected light obtained by reflecting light from an object that is irradiated by a LiDAR sensor, natural light, or reflected light obtained by reflecting natural light that is reflected by an object. At this time, the sensing data may include various forms of feature data including intensity and ambient. The processor (1) checks the intensity value and ambient value in the received sensing data.

[0037] The processor (1) identifies the wavelength of the irradiating light emitted from the lidar sensor. The processor (1) identifies the data having a wavelength corresponding to the wavelength of the irradiating light in the sensing data as an intensity value. The processor (1) identifies the data having a wavelength corresponding to natural light, excluding the wavelength of the irradiating light in the sensing data, as an ambient value.

[0038] The processor (1) calculates a correlation coefficient between 0 and 1 based on the identified intensity value and ambient value. To do this, the processor (1) calculates the standard deviation of the ambient value and the intensity value, and the covariance of the ambient value and the intensity value, and calculates the correlation coefficient using the standard deviation and the covariance.

[0039] The processor (1) can determine that the environment is outdoors or daytime if the calculated correlation coefficient is close to 1, and that the environment is indoors or nighttime if the correlation coefficient is close to 0.

[0040] The processor (1) sets a filtering threshold for removing noise from the sensing data. The processor (1) may set the filtering threshold to be greater than a preset reference filtering threshold if the calculated correlation coefficient is greater than a threshold, for example, 0.5, and may gradually increase the filtering threshold as the correlation coefficient approaches 1. At this time, 0.5 is a value set for convenience of explanation and is not necessarily limited to this, and the reference filtering threshold may be a preset value based on the LiDAR sensor.

[0041] Additionally, if the calculated correlation coefficient is less than 0.5, the processor (1) can set the filtering threshold to be equal to the reference filtering threshold or smaller than the reference filtering threshold. The processor (1) can set the filtering threshold by gradually decreasing it as the correlation coefficient approaches 0.

[0042] In addition, the processor (1) can set the average value of the intensity value identified in the sensing data as a reference filtering threshold. The processor (1) can set the filtering threshold to a value greater than the reference filtering threshold if the correlation coefficient is 0.5 or higher, and can set the filtering threshold to a value smaller than the reference filtering threshold if the correlation coefficient is less than 0.5. Furthermore, the processor (1) can set the filtering threshold to gradually increase relative to the reference filtering threshold as the correlation coefficient approaches 1, and can set the filtering threshold to gradually decrease relative to the reference filtering threshold as the correlation coefficient approaches 0.

[0043] The processor (1) applies a filtering threshold, which is dynamically set according to the correlation coefficient, to the sensing data and determines that an intensity value in the sensing data that is smaller than the filtering threshold is noise, thereby removing noise from the sensing data. The processor (1) can analyze the noise-removed sensing data to identify objects, etc., detected by the LiDAR sensor.

[0045] FIG. 2 is a flowchart illustrating a noise filtering method according to an embodiment of the present invention.

[0046] Referring to FIG. 2, the processor (1) receives sensing data obtained from a LiDAR sensor included in an input / output device (7) (21). The processor (1) checks the intensity value and ambient value in the received sensing data (22).

[0047] More specifically, the processor (1) identifies the wavelength of the irradiation light emitted from the lidar sensor. The processor (1) identifies the data having a wavelength corresponding to the wavelength of the irradiation light in the sensing data as an intensity value. The processor (1) identifies the data having a wavelength excluding the wavelength of the irradiation light in the sensing data as an ambient value.

[0048] The processor (1) calculates a correlation coefficient between 0 and 1 using the following mathematical formula 1 based on the confirmed intensity value and ambient value (23). The processor (1) checks the environmental information of the location where the lidar sensor is located based on the calculated correlation coefficient (24).

[0049]

[0050] At this time, represents the correlation coefficient calculated from the ambient value (A) and the intensity value (I), and represents the standard deviation of the ambient value (A) and intensity value (I), and represents the covariance of the ambient value (A) and the intensity value (I).

[0051] The processor (1) can determine the environment information as being outdoors or daytime if the calculated correlation coefficient is close to 1, and determine the environment information as being indoors or nighttime if the correlation coefficient is close to 0.

[0052] The processor (1) sets a filtering threshold for removing noise from the sensing data (25). More specifically, the processor (1) can set the filtering threshold to be greater than the reference filtering threshold when the calculated correlation coefficient is 0.5 or higher, and can gradually increase the filtering threshold as the correlation coefficient approaches 1.

[0053] Additionally, if the calculated correlation coefficient is less than 0.5, the processor (1) may set the filtering threshold to be equal to the reference filtering threshold or smaller than the reference filtering threshold. The processor (1) may set the filtering threshold by gradually decreasing it as the correlation coefficient approaches 0. At this time, the reference filtering threshold may be a preset value based on the LiDAR sensor.

[0054] In addition, the processor (1) can set the average value of the intensity value identified in the sensing data as a reference filtering threshold. The processor (1) can set the filtering threshold to a value greater than the reference filtering threshold if the correlation coefficient is 0.5 or higher, and can set the filtering threshold to a value smaller than the reference filtering threshold if the correlation coefficient is less than 0.5. Furthermore, the processor (1) can set the filtering threshold to gradually increase relative to the reference filtering threshold as the correlation coefficient approaches 1, and can set the filtering threshold to gradually decrease relative to the reference filtering threshold as the correlation coefficient approaches 0.

[0055] The processor (1) applies a filtering threshold, which is dynamically set according to the correlation coefficient, to the sensing data and determines that an intensity value in the sensing data that is smaller than the filtering threshold is noise, thereby removing noise from the sensing data (26). The processor (1) can analyze the noise-removed sensing data (27) to identify objects, etc., detected by the LiDAR sensor.

[0057] FIG. 3 is a screen example diagram illustrating a method for classifying environments using correlation coefficients according to an embodiment of the present invention.

[0058] Referring to FIG. 3, FIG. 3(a) and FIG. 3(b) show intensity values ​​and ambient values ​​identified based on sensing data acquired by a lidar sensor in different environments. The processor (1) calculates the standard deviation and covariance of the intensity values ​​and ambient values ​​of FIG. 3(a) and FIG. 3(b) and calculates the correlation coefficient based on Equation 1.

[0059] As a result of the calculation, the processor (1) can confirm that the correlation coefficient in the case of FIG. 3(a) is calculated to be 0.75 and the correlation coefficient in the case of FIG. 3(b) is calculated to be 0.12. Therefore, since the correlation coefficient in FIG. 3(a) is 0.75, which is 0.5 or higher, the processor (1) can confirm that the environmental condition of the lidar sensor is outdoors or that the time when the lidar sensor acquired sensing data is daytime. In addition, since the correlation coefficient in FIG. 3(b) is 0.12, which is less than 0.5, the processor (1) can confirm that the environmental condition of the lidar sensor is indoors or that the time when the lidar sensor acquired sensing data is nighttime.

[0061] FIG. 4 is a screen example diagram illustrating a method for dynamically setting a filtering threshold according to a classified environment according to an embodiment of the present invention.

[0062] Referring to FIG. 4, FIG. 4(a) and FIG. 4(b) are graphs corresponding to FIG. 3(a) and FIG. 3(b), respectively, and may be graphs illustrating the intensity values ​​of sensing data received at a specific time from a lidar sensor. The x-axis of the graph may represent time, and the y-axis may represent the intensity values.

[0063] The processor (1) has a reference filtering threshold (as shown in FIG. 4(a) and FIG. 4(b) It can be confirmed that ) is 50. The processor (1) confirmed that the correlation coefficient calculated in the environment of FIG. 3(a) is 0.75 and the correlation coefficient calculated in the environment of FIG. 3(b) is 0.12.

[0064] Accordingly, the processor (1) can increase the filtering threshold (41) to 120 based on the environment information of FIG. 3(a) and maintain the filtering threshold (42) at 50 based on the environment information of FIG. 3(b). In addition, in FIG. 4(b), the filtering threshold (42) is a reference filtering threshold ( Although it is explained as an example of setting it to be the same as ), it is not necessarily limited to this, and the filtering threshold (42) is a reference filtering threshold ( It can be set smaller than ).

[0065] After setting the filtering threshold (41, 42), the processor (1) determines an intensity value smaller than the filtering threshold (41, 42) as noise and removes it from the sensing data, and can identify an object detected by the lidar sensor using the remaining intensity value.

[0066] In this way, the present invention has the effect of improving data reliability by dynamically setting a filtering threshold based on environmental information at the time of acquiring sensing data from a LiDAR sensor, thereby effectively removing noise that may occur depending on the environmental information.

[0068] Although the present invention has been described in detail above through representative embodiments, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the present invention should be determined by the technical concept of the appended claims.

Claims

Claim 1 A device comprising one or more processors; and a memory for storing one or more programs executed by the one or more processors, wherein the processors identify environmental information of the location where the lidar sensor is located using sensing data acquired from the lidar sensor, and dynamically set a filtering threshold for removing noise from the sensing data based on the identified environmental information. Claim 2 In claim 1, the processor is a device for verifying intensity values ​​and ambient values ​​in the sensing data. Claim 3 In paragraph 2, the processor is a device for verifying the intensity value in the sensing data based on the wavelength of the irradiation light irradiated by the lidar sensor. Claim 4 In paragraph 3, the processor is a device for verifying the ambient value in the sensing data based on the wavelength of light excluding the wavelength of the illumination light in the sensing data. Claim 5 In paragraph 4, the processor is a device for verifying environment information by calculating a correlation coefficient between 0 and 1 based on the intensity value and the ambient value. Claim 6 In claim 5, the processor is a device that sets the filtering threshold to be greater than the reference filtering threshold when the correlation coefficient is 0.5 or higher. Claim 7 In claim 6, the processor is a device that sets the filtering threshold by gradually increasing it as the correlation coefficient approaches 1. Claim 8 In paragraph 5, the processor is a device that sets the filtering threshold to be equal to or smaller than the reference filtering threshold when the correlation coefficient is less than 0.

5. Claim 9 In claim 8, the processor is a device that sets the filtering threshold by gradually decreasing it as the correlation coefficient approaches 0. Claim 10 In claim 5, the processor is a device that removes the noise by deleting intensity values ​​below the dynamically set filtering threshold from the sensing data. Claim 11 A method performed by a device having one or more processors and a memory for storing one or more programs executed by said one or more processors, comprising: a step of identifying environmental information of a location where said lidar sensor is located using sensing data acquired from said lidar sensor; and a step of dynamically setting a filtering threshold for removing noise from said sensing data based on said identified environmental information. Claim 12 A method according to claim 11, further comprising the step of verifying intensity values ​​and ambient values ​​in the sensing data. Claim 13 In claim 12, the step of verifying the ambient value is a method in which the intensity value in the sensing data is verified based on the wavelength of the irradiation light irradiated by the lidar sensor. Claim 14 In claim 13, the step of verifying the ambient value is a method of verifying the ambient value in the sensing data based on the wavelength of light excluding the wavelength of the illumination light in the sensing data. Claim 15 In claim 14, the step of verifying the environmental information is a method in which a correlation coefficient between 0 and 1 is calculated based on the intensity value and ambient value to verify the environmental information. Claim 16 A method according to claim 15, further comprising the step of setting the filtering threshold to be greater than the reference filtering threshold if the correlation coefficient is 0.5 or higher. Claim 17 In claim 16, the step of setting the filtering threshold greater than the reference filtering threshold is a method in which the filtering threshold is gradually increased as the correlation coefficient approaches 1. Claim 18 A method according to claim 15, further comprising the step of setting the filtering threshold to be smaller than the reference filtering threshold if the correlation coefficient is less than 0.

5. Claim 19 In claim 18, the step of setting the filtering threshold smaller than the reference filtering threshold is a method in which the filtering threshold is gradually reduced as the correlation coefficient approaches 0. Claim 20 A method according to claim 15, further comprising the step of removing the noise by deleting intensity values ​​below the dynamically set filtering threshold from the sensing data.