LANE RECOGNITON DEVICE AND METHOD BASED ON LIDAR FOR VEHICLE

• Main Authors: LEE NAM HYUNG, JANG SUNG MOON
• Format: Patent
• Language: English; Korean
• Published: 21.11.2022
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; HANDLING RECORD CARRIERS; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PERFORMING OPERATIONS; PHYSICS; PRESENTATION OF DATA; RADIO DIRECTION-FINDING; RADIO NAVIGATION; RECOGNITION OF DATA; RECORD CARRIERS; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT; TESTING; TRANSPORTING; VEHICLES IN GENERAL

The present invention relates to an apparatus for recognizing a lane based on a lidar of a vehicle, and a method thereof. The apparatus for recognizing the lane based on the lidar of the vehicle of the present invention may comprise: a pre-processing unit which detects a lane point candidate group based on information detected from the lidar; a deep learning unit learning the lane point candidate group and generating lane recognition information; and a post-processing unit which converts the lane recognition information into lane information through a lane curve fitting algorithm. Provided are the apparatus for recognizing the lane based on the lidar capable of recognizing the lane regardless of illumination change, and the method thereof. 본 발명은 차량의 라이다 기반 차선 인식 장치 및 방법에 관한 것으로, 라이다로부터 검출된 정보에 기초하여 차선 포인트 후보군을 검출하는 전처리부, 상기 차선 포인트 후보군을 학습하여 차선 인식 정보를 생성하는 딥러닝부, 및 차선 곡선 피팅 알고리즘을 통해 상기 차선 인식 정보를 차선 정보로 변환하는 후처리부를 포함할 수 있다.