TY - JOUR
T1 - Learning geometric and photometric features from panoramic LiDAR scans for outdoor place categorization
AU - Nakashima, Kazuto
AU - Jung, Hojung
AU - Oto, Yuki
AU - Iwashita, Yumi
AU - Kurazume, Ryo
AU - Mozos, Oscar Martinez
N1 - Publisher Copyright:
© 2018, © 2018 Taylor & Francis and The Robotics Society of Japan.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Semantic place categorization, which is one of the essential tasks for autonomous robots and vehicles, allows them to have capabilities of self-decision and navigation in unfamiliar environments. In particular, outdoor places are more difficult targets than indoor ones due to perceptual variations, such as dynamic illuminance over 24 hours and occlusions by cars and pedestrians. This paper presents a novel method of categorizing outdoor places using convolutional neural networks (CNNs), which take omnidirectional depth/reflectance images obtained by 3D LiDARs as the inputs. First, we construct a large-scale outdoor place dataset named Multi-modal Panoramic 3D Outdoor (MPO) comprising two types of point clouds captured by two different LiDARs. They are labeled with six outdoor place categories: coast, forest, indoor/outdoor parking, residential area, and urban area. Second, we provide CNNs for LiDAR-based outdoor place categorization and evaluate our approach with the MPO dataset. Our results on the MPO dataset outperform traditional approaches and show the effectiveness in which we use both depth and reflectance modalities. To analyze our trained deep networks, we visualize the learned features.
AB - Semantic place categorization, which is one of the essential tasks for autonomous robots and vehicles, allows them to have capabilities of self-decision and navigation in unfamiliar environments. In particular, outdoor places are more difficult targets than indoor ones due to perceptual variations, such as dynamic illuminance over 24 hours and occlusions by cars and pedestrians. This paper presents a novel method of categorizing outdoor places using convolutional neural networks (CNNs), which take omnidirectional depth/reflectance images obtained by 3D LiDARs as the inputs. First, we construct a large-scale outdoor place dataset named Multi-modal Panoramic 3D Outdoor (MPO) comprising two types of point clouds captured by two different LiDARs. They are labeled with six outdoor place categories: coast, forest, indoor/outdoor parking, residential area, and urban area. Second, we provide CNNs for LiDAR-based outdoor place categorization and evaluate our approach with the MPO dataset. Our results on the MPO dataset outperform traditional approaches and show the effectiveness in which we use both depth and reflectance modalities. To analyze our trained deep networks, we visualize the learned features.
UR - http://www.scopus.com/inward/record.url?scp=85051145962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051145962&partnerID=8YFLogxK
U2 - 10.1080/01691864.2018.1501279
DO - 10.1080/01691864.2018.1501279
M3 - Article
AN - SCOPUS:85051145962
SN - 0169-1864
VL - 32
SP - 750
EP - 765
JO - Advanced Robotics
JF - Advanced Robotics
IS - 14
ER -