# US 2021/0239809 A1 · Lidar noise removal apparatus and lidar noise removal method thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0239809 A1 - Document ID: US20210239809A1 - Status: Published application - Kind: A1 - Application number: 16/860,346 - Filed: 2020-04-28 - Published: 2021-08-05 - Earliest claimed: 2020-01-30 - Assignees: Hyundai Motor Company; Kia Motors Corporation - Applicants: Hyundai Motor Company; Kia Motors Corporation - Inventors: Yoon Ho Jang; Soo Kyung Ryu - Web page: https://patentgrep.com/patent/US20210239809A1 ## CPC - G01S 7/497: Means for monitoring or calibrating - G01S 7/4876: {by removing unwanted signals (G01S7/495 takes precedence)} - G01S 17/02: Systems using the reflection of electromagnetic waves other than radio waves (G01S17/66 takes precedence) - G01S 17/931: of land vehicles - G06V 10/30: Noise filtering - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A LIDAR noise removal apparatus and a LIDAR noise removal method thereof are provided. The apparatus includes a LIDAR detection information processor that processes LIDAR detection information received from a LIDAR of a vehicle. A sun position acquirer acquires an azimuth angle and elevation angle of the sun relative to a traveling direction of the vehicle. An ROI selector selects an ROI corresponding to the sun from a front image of the vehicle based on the azimuth angle and elevation angle and compares a brightness of the selected ROI with a threshold value. A noise region selector selects a noise region corresponding to the ROI from the LIDAR detection information based on the azimuth angle and elevation angle when the brightness of the ROI exceeds the threshold value, and a noise remover removes noise points in the selected noise region. ## Claims ### Claim 1 A LIDAR noise removal apparatus, comprising: a LIDAR detection information processor configured to process LIDAR detection information received from a LIDAR of a vehicle; a sun position acquirer configured to acquire an azimuth angle and elevation angle of the sun relative to a traveling direction of the vehicle; a Region Of Interest (ROI) selector configured to select an ROI that corresponds to the sun from a front image of the vehicle based on the acquired azimuth angle and elevation angle of the sun and compare a brightness of the selected ROI with a threshold value to determine whether the brightness of the ROI exceeds the threshold value; a noise region selector configured to select a noise region that corresponds to the ROI from the LIDAR detection information based on the azimuth angle and elevation angle of the sun when the brightness of the ROI exceeds the threshold value; and a noise remover configured to remove noise points in the selected noise region. ### Claim 2 (depends on 1) The LIDAR noise removal apparatus according to claim 1, wherein the LIDAR detection information processor is configured to receive the LIDAR detection information from the LIDAR of the vehicle and parse the received LIDAR detection information to process the same. ### Claim 3 (depends on 1) The LIDAR noise removal apparatus according to claim 1, wherein the sun position acquirer is configured to acquire position information, heading information and time information of the vehicle and extracts the azimuth angle and elevation angle of the sun relative to the traveling direction of the vehicle based on the acquired position information, heading information and time information of the vehicle. ### Claim 4 (depends on 1) The LIDAR noise removal apparatus according to claim 1, wherein the ROI selector is configured to acquire the front image of the vehicle, convert the azimuth angle and elevation angle of the sun into coordinates of the LIDAR and coordinate of the front image and select the ROI that corresponds to the sun from the front image. ### Claim 5 (depends on 1) The LIDAR noise removal apparatus according to claim 1, wherein the noise region selector is configured to recognize that sunlight is irradiated to the vehicle, when the brightness of the ROI exceeds the threshold value. ### Claim 6 (depends on 1) The LIDAR noise removal apparatus according to claim 1, wherein the noise region selector is configured to extract a layer of the LIDAR that corresponds to an elevation of the sun, an angle that corresponds to an azimuth of the sun and a filter value when the brightness of the ROI exceeds the threshold value and selects the noise region that corresponds to the ROI from the LIDAR detection information based on the extracted layer, angle and filter value. ### Claim 7 (depends on 1) The LIDAR noise removal apparatus according to claim 1, further comprising an object recognizer configured to recognize an object from the LIDAR detection information. ### Claim 8 (depends on 7) The LIDAR noise removal apparatus according to claim 7, wherein the object recognizer is configured to assign object point flags to all points in the noise region that correspond to the ROI when the brightness of the ROI is less than or equal to the threshold value and modify a labeling parameter for the noise region that corresponds to the ROI. ### Claim 9 (depends on 8) The LIDAR noise removal apparatus according to claim 8, wherein the object recognizer is configured to modify the labeling parameter to decrease a distance threshold value for a distance between points in the noise region corresponding to the ROI. ### Claim 10 (depends on 7) The LIDAR noise removal apparatus according to claim 7, wherein the object recognizer is configured to check the number of object points of a labeled object in the noise region that corresponds to the ROI and perform filtering based on the number of the object points of the labeled object to recognize the object. ### Claim 11 A LIDAR noise removal method of a LIDAR noise removal apparatus, the LIDAR noise removal apparatus receiving LIDAR detection information from a LIDAR of a vehicle, the method comprising: processing, by a processor, the LIDAR detection information received from the LIDAR of the vehicle; acquiring, by the processor, an azimuth angle and elevation angle of the sun relative to a traveling direction of the vehicle; selecting, by the processor, a Region Of Interest (ROI) that corresponds to the sun from a front image of the vehicle based on the acquired azimuth angle and elevation angle of the sun; comparing, by the processor, a brightness of the selected ROI with a threshold value to determine whether the brightness of the ROI exceeds the threshold value; selecting, by the processor, a noise region that corresponds to the ROI from the LIDAR detection information based on the azimuth angle and elevation angle of the sun when the brightness of the ROI exceeds the threshold value; and removing, by the processor, noise points in the selected noise region. ### Claim 12 (depends on 11) The LIDAR noise removal method according to claim 11, wherein the processing the LIDAR detection information includes: receiving, by the processor, the LIDAR detection information from the LIDAR of the vehicle; and parsing, by the processor, the received LIDAR detection information to process the same. ### Claim 13 (depends on 11) The LIDAR noise removal method according to claim 11, wherein acquiring an azimuth angle and elevation angle of the sun includes: acquiring, by the processor, position information, heading information and time information of the vehicle; and extracting, by the processor, the azimuth angle and elevation angle of the sun relative to the traveling direction of the vehicle based on the acquired position information, heading information and time information of the vehicle. ### Claim 14 (depends on 11) The LIDAR noise removal method according to claim 11, wherein selecting an ROI includes: acquiring, by the processor, the front image of the vehicle; converting, by the processor, the azimuth angle and elevation angle of the sun into coordinates of the LIDAR and coordinates of the front image; and selecting, by the processor, the ROI that corresponds to the sun from the front image based on the converted azimuth angle and elevation angle of the sun. ### Claim 15 (depends on 11) The LIDAR noise removal method according to claim 11, wherein selecting a noise region corresponding to the ROI includes recognizing that sunlight is irradiated to the vehicle, when the brightness of the ROI exceeds the threshold value. ### Claim 16 (depends on 11) The LIDAR noise removal method according to claim 11, further comprising: assigning, by the processor, object point flags to all points in the noise region that correspond to the ROI when the brightness of the ROI is less than or equal to the threshold value and modifying a labeling parameter for the noise region corresponding to the ROI; and recognizing, by the processor, an object from the LIDAR detection information. ### Claim 17 (depends on 16) The LIDAR noise removal method according to claim 16, wherein modifying a labeling parameter for the noise region corresponding to the ROI includes modifying the labeling parameter to decrease a distance threshold value for a distance between points in the noise region that corresponds to the ROI. ### Claim 18 (depends on 16) The LIDAR noise removal method according to claim 16, wherein recognizing an object from the LIDAR detection information includes checking the number of object points of a labeled object in the noise region that corresponds to the ROI and performing filtering based on the number of the object points of the labeled object to recognize the object. ### Claim 19 (depends on 11) A non-transitory computer-readable recording medium for storing a program for executing the method according to claim 11. ### Claim 20 A vehicle, comprising: a LIDAR configured to sense surrounding object information of the vehicle; a camera configured to acquire a front image of the vehicle; and a LIDAR noise removal apparatus configured to remove noise points that correspond to sunlight incident on the LIDAR, wherein the LIDAR noise removal apparatus includes: a LIDAR detection information processor configured to process LIDAR detection information received from the LIDAR; a sun position acquirer configured to acquire an azimuth angle and elevation angle of the sun relative to a traveling direction of the vehicle; a Region Of Interest (ROI) selector configured to select an ROI that corresponds to the sun from the front image of the vehicle based on the acquired azimuth angle and elevation angle of the sun and compare a brightness of the selected ROI with a threshold value to determine whether the brightness of the ROI exceeds the threshold value; a noise region selector configured to select a noise region that corresponds to the ROI from the LIDAR detection information based on the azimuth angle and elevation angle of the sun when the brightness of the ROI exceeds the threshold value; and a noise remover configured to remove noise points in the selected noise region.