TY - GEN
T1 - Accurate camera pose estimation for Kinect Fusion based on line segment matching by LEHF
AU - Nakayama, Yusuke
AU - Honda, Toshihiro
AU - Saito, Hideo
AU - Shimizu, Masayoshi
AU - Yamaguchi, Nobuyasu
PY - 2014/12/4
Y1 - 2014/12/4
N2 - Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.
AB - Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.
UR - http://www.scopus.com/inward/record.url?scp=84919910802&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919910802&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2014.374
DO - 10.1109/ICPR.2014.374
M3 - Conference contribution
AN - SCOPUS:84919910802
T3 - Proceedings - International Conference on Pattern Recognition
SP - 2149
EP - 2154
BT - Proceedings - International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd International Conference on Pattern Recognition, ICPR 2014
Y2 - 24 August 2014 through 28 August 2014
ER -