3D Non-rigid Registration of Deformable Object Using GPU

被引:0
作者
Lee, Junesuk [1 ]
Kim, Eung-su [1 ]
Park, Soon-Yong [2 ]
机构
[1] Kyungpook Natl Univ, Sch Comp Sci & Engn, Daegu, South Korea
[2] Kyungpook Natl Univ, Sch Elect Engn, Daegu, South Korea
来源
PATTERN RECOGNITION AND IMAGE ANALYSIS, PT I | 2020年 / 11867卷
关键词
3D reconstruction; Non-rigid registration; Non-rigid ICP; Deformable registration; GPU; GAUSS-NEWTON;
D O I
10.1007/978-3-030-31332-6_53
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a method to quickly process non-rigid registration between 3D deformable data using a GPU-based non-rigid ICP(Iterative Closest Point) algorithm. In this paper, we sequentially acquire whole-body model data of a person moving dynamically from a single RGBD camera. We use Dense Optical Flow algorithm to find the corresponding pixels between two consecutive frames. Next, we select nodes to estimate 3D deformation matrices by uniform sampling algorithm. We use a GPU-based non-rigid ICP algorithm to estimate the 3D transformation matrices of each node at high speed. We use non-linear optimization algorithm methods in the non-rigid ICP algorithm. We define energy functions for an estimate the exact 3D transformation matrices. We use a proposed GPU-based method because it takes a lot of computation time to calculate the 3D transformation matrices of all nodes. We apply a 3D transformation to all points with a weight-based affine transformation algorithm. We demonstrate the high accuracy of non-rigid registration and the fast runtime of the non-rigid ICP algorithm through experimental results.
引用
收藏
页码:610 / 619
页数:10
相关论文
共 50 条
[41]   Non-Rigid Graph Registration Using Active Testing Search [J].
Serradell, Eduard ;
Pinheiro, Miguel Amavel ;
Sznitman, Raphael ;
Kybic, Jan ;
Moreno-Noguer, Francesc ;
Fua, Pascal .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (03) :625-638
[42]   Comparison Study of Extraction Accuracy of 3D Facial Anatomical Landmarks Based on Non-Rigid Registration of Face Template [J].
Wen, Aonan ;
Zhu, Yujia ;
Xiao, Ning ;
Gao, Zixiang ;
Zhang, Yun ;
Wang, Yong ;
Wang, Shengjin ;
Zhao, Yijiao .
DIAGNOSTICS, 2023, 13 (06)
[43]   Optimized GPU implementation of learning-based non-rigid multi-modal registration [J].
Fan, Zhe ;
Vetter, Christoph ;
Guetter, Christoph ;
Yu, Daphne ;
Westermann, Ruediger ;
Kaufman, Arie ;
Xu, Chenyang .
MEDICAL IMAGING 2008: IMAGE PROCESSING, PTS 1-3, 2008, 6914
[44]   Biomechanically constrained non-rigid MR-TRUS prostate registration using deep learning based 3D point cloud matching [J].
Fu, Yabo ;
Lei, Yang ;
Wang, Tonghe ;
Patel, Pretesh ;
Jani, Ashesh B. ;
Mao, Hui ;
Curran, Walter J. ;
Liu, Tian ;
Yang, Xiaofeng .
MEDICAL IMAGE ANALYSIS, 2021, 67
[45]   GPU parallel implementation of B-spline non-rigid grid registration using free-form deformations [J].
Yadav, Kuldeep ;
Srivastava, Avi ;
Mittal, Ankush ;
Ansari, M. A. .
INTERNATIONAL JOURNAL OF BIOMEDICAL ENGINEERING AND TECHNOLOGY, 2013, 11 (02) :124-135
[46]   Non-rigid temporal registration of 2D and 3D multi-channel microscopy image sequences of human cells [J].
Kim, I. ;
Yang, S. ;
Le Baccon, P. ;
Heard, E. ;
Chen, Y. -C. ;
Spector, D. ;
Kappell, C. ;
Eils, R. ;
Rohr, K. .
2007 4TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING : MACRO TO NANO, VOLS 1-3, 2007, :1328-+
[47]   Efficacy of non-rigid registration technique for misregistration in 3D-CTA fusion imaging [J].
Yoshiya Ohashi ;
Hiroyuki Takashima ;
Goh Ohmori ;
Kohei Harada ;
Ayaka Chiba ;
Kanako Numasawa ;
Tatsuya Imai ;
Shun Hayasaka ;
Aya Itoh .
La radiologia medica, 2020, 125 :618-624
[48]   Efficacy of non-rigid registration technique for misregistration in 3D-CTA fusion imaging [J].
Ohashi, Yoshiya ;
Takashima, Hiroyuki ;
Ohmori, Goh ;
Harada, Kohei ;
Chiba, Ayaka ;
Numasawa, Kanako ;
Imai, Tatsuya ;
Hayasaka, Shun ;
Itoh, Aya .
RADIOLOGIA MEDICA, 2020, 125 (07) :618-624
[49]   Strain Analysis by Regularized Non-Rigid Registration [J].
Badshah, Amir ;
O'Leary, Paul ;
Harker, Matthew ;
Tscharnuter, Daniel .
IMAGE PROCESSING: MACHINE VISION APPLICATIONS V, 2012, 8300
[50]   NON-RIGID REGISTRATION GUIDED BY LANDMARKS AND LEARNING [J].
Eckl, Jutta ;
Daum, Volker ;
Hornegger, Joachim ;
Pohl, Kilian M. .
2012 9TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2012, :704-707