TY - JOUR
T1 - Adaptive evolution strategy sample consensus for 3D reconstruction from two cameras
AU - Toda, Yuichiro
AU - Yz, Hsu Horng
AU - Matsuno, Takayuki
AU - Minami, Mamoru
AU - Zhou, Dalin
N1 - Publisher Copyright:
© 2020, International Society of Artificial Life and Robotics (ISAROB).
PY - 2020/8/1
Y1 - 2020/8/1
N2 - RANdom SAmple Consensus (RANSAC) has been applied to many 3D image processing problems such as homography matrix estimation problems and shape detection from 3D point clouds, and is one of the most popular robust estimator methods. However, RANSAC has a problem related to the trade-off between computational cost and stability of search because RANSAC is based on random sampling. In our previous work, we proposed Adaptive Evolution Strategy SAmple Consensus (A-ESSAC) as a new robust estimator, and we applied ESSAC to the homography matrix estimation for 3D SLAM using RGB-D camera. A-ESSAC is based on Evolution Strategy to maintain the genetic diversity. Furthermore, ESSAC has two heuristic searches. One is a search range control for reducing the computational cost of RANSAC. The other is adaptive/self-adaptive mutation for changing the search strategy of A-ESSAC according to the best fitness value. In this paper, we apply A-ESSAC to 3D reconstruction method using two cameras, and we show an experimental result, and discuss the effectiveness of the proposed method.
AB - RANdom SAmple Consensus (RANSAC) has been applied to many 3D image processing problems such as homography matrix estimation problems and shape detection from 3D point clouds, and is one of the most popular robust estimator methods. However, RANSAC has a problem related to the trade-off between computational cost and stability of search because RANSAC is based on random sampling. In our previous work, we proposed Adaptive Evolution Strategy SAmple Consensus (A-ESSAC) as a new robust estimator, and we applied ESSAC to the homography matrix estimation for 3D SLAM using RGB-D camera. A-ESSAC is based on Evolution Strategy to maintain the genetic diversity. Furthermore, ESSAC has two heuristic searches. One is a search range control for reducing the computational cost of RANSAC. The other is adaptive/self-adaptive mutation for changing the search strategy of A-ESSAC according to the best fitness value. In this paper, we apply A-ESSAC to 3D reconstruction method using two cameras, and we show an experimental result, and discuss the effectiveness of the proposed method.
KW - 3D reconstruction
KW - Evolutionary computation
KW - Robust estimator
UR - http://www.scopus.com/inward/record.url?scp=85084159146&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084159146&partnerID=8YFLogxK
U2 - 10.1007/s10015-020-00603-9
DO - 10.1007/s10015-020-00603-9
M3 - Article
AN - SCOPUS:85084159146
SN - 1433-5298
VL - 25
SP - 466
EP - 474
JO - Artificial Life and Robotics
JF - Artificial Life and Robotics
IS - 3
ER -