algorithms for deriving and analyzing retroreflectivity influence factors through regression analysis. METHODS : An experimental road lane was created to examine the trends of retroreflectivity and LiDAR intensity values, and a controlled indoor experiment was conducted to identify influencing factors. The optimal algorithm was developed by regression analysis of the experimental data. RESULTS : The significance probability (P-value) through SPSS linear regression analysis was 0.000 for measured height, 0.001 for perpendicular angle, 0.157 for vertical angle, and 0.000 for LiDAR intensity, indicating that measured height, vertical angle, and LiDAR intensity are significant factors because the significance probability is less than 0.05, and vertical angle is not significant. The NNR regression model performed the best, so the measurement data with height (1.2m, 2m, 2.2m) and vertical angle (11.3°, 12.3°, 13.5°) were analyzed to derive the optimal LiDAR Intensity measurement height and vertical angle. CONCLUSIONS : For each LiDAR measurement height and vertical angle, the highest correlation between LiDAR Intensity and retroreflectivity was found at a measurement height of 1.2 meters and a vertical angle of 12.3°, where the model learning accuracy (R2) was the highest.

1. 연구배경 및 목적
2. 재귀반사도 및 LiDAR Intensity 측정 원리
    2.1. 재귀반사도 측정 원리
    2.2. LiDAR 센서 기술 원리
3. 실험 방법
    3.1. 실험 샘플 제작
    3.2. 실험 샘플 재귀반사도 기준값 결정
    3.3. 실내 실험
4. LiDAR Intensity와 재귀반사도 예측 모델 구축
    4.1. 회귀분석 결과
    4.2. 학습 알고리즘 모델 구축
5. 결론
감사의 글

• 이준식(정회원 · 세종대학교 공과대학 건설환경공학과 박사과정) | Lee Jun Sik
• 김기덕(정회원 · (주)아이리스테크놀로지 신기술개발사업팀 차장 · 공학박사) | Kim Ki Deok
• 전원기(세종대학교 공과대학 건설환경공학과 석사과정) | Chun Won Kee
• 차현우(세종대학교 공과대학 건설환경공학과 석사과정) | Cha Hyun Woo
• 이현종(정회원 · 세종대학교 공과대학 건설환경공학과 교수· 공학박사) | Lee Hyun jong (Sejong University, Prof. Department Sejong University, Civil and Environment Engineering, 209 Neung Dong ro, Seoul, Korea) 교신저자