TY - GEN
T1 - Road edge detection on 3D point cloud data using Encoder-Decoder Convolutional Network
AU - Rachmadi, Reza Fuad
AU - Uchimura, Keiichi
AU - Koutaki, Gou
AU - Ogata, Kohichi
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/19
Y1 - 2017/12/19
N2 - The demand of High Definition Maps (HD-Maps) has been increasing, especially for autonomous vehicle application. Usually, HD-Map is created by scanning the road using LiDAR sensor and reconstructing the road on 3D world to capture all aspects of road properties. One of the important properties of a road is its edge or boundary. In this paper, we propose end-to-end 3D Encoder-Decoder Convolutional Network (3D-EDCN) for road edge detection on 3D point cloud data produced by LiDAR sensor. Our 3D-EDCN classifier consists of nine convolutional layers and three deconvolutional layers. For simplification, we use 3D voxel format as input and output of the classifier. Our proposed method was tested using our own 3D point cloud dataset which taken from LiDAR equipment and consisting of 103 3D point cloud data with their respective road edge ground truth. In the training process, we use combinations of Cross-Entropy loss function and Euclidean loss function to help our model converged. As a preliminary result, our proposed 3D-EDCN classifier achieves Mean Square Error (MSE) of 2.738×10-5, precision of 0.37262, and recall of 0.14432.
AB - The demand of High Definition Maps (HD-Maps) has been increasing, especially for autonomous vehicle application. Usually, HD-Map is created by scanning the road using LiDAR sensor and reconstructing the road on 3D world to capture all aspects of road properties. One of the important properties of a road is its edge or boundary. In this paper, we propose end-to-end 3D Encoder-Decoder Convolutional Network (3D-EDCN) for road edge detection on 3D point cloud data produced by LiDAR sensor. Our 3D-EDCN classifier consists of nine convolutional layers and three deconvolutional layers. For simplification, we use 3D voxel format as input and output of the classifier. Our proposed method was tested using our own 3D point cloud dataset which taken from LiDAR equipment and consisting of 103 3D point cloud data with their respective road edge ground truth. In the training process, we use combinations of Cross-Entropy loss function and Euclidean loss function to help our model converged. As a preliminary result, our proposed 3D-EDCN classifier achieves Mean Square Error (MSE) of 2.738×10-5, precision of 0.37262, and recall of 0.14432.
UR - http://www.scopus.com/inward/record.url?scp=85046540057&partnerID=8YFLogxK
U2 - 10.1109/KCIC.2017.8228570
DO - 10.1109/KCIC.2017.8228570
M3 - Conference contribution
AN - SCOPUS:85046540057
T3 - Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017
SP - 95
EP - 100
BT - Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017
A2 - Bagar, Fahim Nur Cahya
A2 - Zainudin, Ahmad
A2 - Al Rasyid, M. Udin Harun
A2 - Briantoro, Hendy
A2 - Akbar, Zulhaydar Fairozal
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017
Y2 - 26 September 2017 through 27 September 2017
ER -