The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
최근에는 카메라와 빛 감지 및 거리 측정(LiDAR)을 활용한 도시 디지털화에 대한 수요가 증가하고 있습니다. 그림자는 측정에 가장 큰 영향을 미치는 조건입니다. 따라서 그림자 검출 기술이 필수적이다. 본 연구에서는 다른 광원의 조사가 아니라 물체의 표면 특성에 의존하는 LiDAR 강도를 활용한 그림자 감지를 제안합니다. 기존의 LiDAR 강도 보조 그림자 감지 방법과 달리, 우리의 방법은 각 위치의 휘도와 LiDAR 강도 간의 비상관성을 최적화에 포함합니다. 각 위치의 휘도와 LiDAR 강도의 비상관관계로 정의되는 에너지는 그래프 컷 분할을 통해 그림자를 감지하여 최소화됩니다. KITTI 및 Waymo 데이터 세트에 대한 평가에서 그림자 감지 방법은 여러 평가 지표 측면에서 이전 방법보다 성능이 뛰어났습니다.
Shogo SATO
NTT Human Informatics Laboratories
Yasuhiro YAO
NTT Human Informatics Laboratories
Taiga YOSHIDA
NTT Human Informatics Laboratories
Shingo ANDO
NTT Human Informatics Laboratories
Jun SHIMAMURA
NTT Human Informatics Laboratories
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Shogo SATO, Yasuhiro YAO, Taiga YOSHIDA, Shingo ANDO, Jun SHIMAMURA, "Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 9, pp. 1556-1563, September 2023, doi: 10.1587/transinf.2023EDP7009.
Abstract: In recent years, there has been a growing demand for urban digitization using cameras and light detection and ranging (LiDAR). Shadows are a condition that affects measurement the most. Therefore, shadow detection technology is essential. In this study, we propose shadow detection utilizing the LiDAR intensity that depends on the surface properties of objects but not on irradiation from other light sources. Unlike conventional LiDAR-intensity-aided shadow detection methods, our method embeds the un-correlation between luminance and LiDAR intensity in each position into the optimization. The energy, which is defined by the un-correlation between luminance and LiDAR intensity in each position, is minimized by graph-cut segmentation to detect shadows. In evaluations on KITTI and Waymo datasets, our shadow-detection method outperformed the previous methods in terms of multiple evaluation indices.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7009/_p
부
@ARTICLE{e106-d_9_1556,
author={Shogo SATO, Yasuhiro YAO, Taiga YOSHIDA, Shingo ANDO, Jun SHIMAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation},
year={2023},
volume={E106-D},
number={9},
pages={1556-1563},
abstract={In recent years, there has been a growing demand for urban digitization using cameras and light detection and ranging (LiDAR). Shadows are a condition that affects measurement the most. Therefore, shadow detection technology is essential. In this study, we propose shadow detection utilizing the LiDAR intensity that depends on the surface properties of objects but not on irradiation from other light sources. Unlike conventional LiDAR-intensity-aided shadow detection methods, our method embeds the un-correlation between luminance and LiDAR intensity in each position into the optimization. The energy, which is defined by the un-correlation between luminance and LiDAR intensity in each position, is minimized by graph-cut segmentation to detect shadows. In evaluations on KITTI and Waymo datasets, our shadow-detection method outperformed the previous methods in terms of multiple evaluation indices.},
keywords={},
doi={10.1587/transinf.2023EDP7009},
ISSN={1745-1361},
month={September},}
부
TY - JOUR
TI - Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation
T2 - IEICE TRANSACTIONS on Information
SP - 1556
EP - 1563
AU - Shogo SATO
AU - Yasuhiro YAO
AU - Taiga YOSHIDA
AU - Shingo ANDO
AU - Jun SHIMAMURA
PY - 2023
DO - 10.1587/transinf.2023EDP7009
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2023
AB - In recent years, there has been a growing demand for urban digitization using cameras and light detection and ranging (LiDAR). Shadows are a condition that affects measurement the most. Therefore, shadow detection technology is essential. In this study, we propose shadow detection utilizing the LiDAR intensity that depends on the surface properties of objects but not on irradiation from other light sources. Unlike conventional LiDAR-intensity-aided shadow detection methods, our method embeds the un-correlation between luminance and LiDAR intensity in each position into the optimization. The energy, which is defined by the un-correlation between luminance and LiDAR intensity in each position, is minimized by graph-cut segmentation to detect shadows. In evaluations on KITTI and Waymo datasets, our shadow-detection method outperformed the previous methods in terms of multiple evaluation indices.
ER -