TY - GEN
T1 - Voting-based pose estimation for robotic assembly using a 3D sensor
AU - Choi, Changhyun
AU - Taguchi, Yuichi
AU - Tuzel, Oncel
AU - Liu, Ming Yu
AU - Ramalingam, Srikumar
PY - 2012
Y1 - 2012
N2 - We propose a voting-based pose estimation algorithm applicable to 3D sensors, which are fast replacing their 2D counterparts in many robotics, computer vision, and gaming applications. It was recently shown that a pair of oriented 3D points, which are points on the object surface with normals, in a voting framework enables fast and robust pose estimation. Although oriented surface points are discriminative for objects with sufficient curvature changes, they are not compact and discriminative enough for many industrial and real-world objects that are mostly planar. As edges play the key role in 2D registration, depth discontinuities are crucial in 3D. In this paper, we investigate and develop a family of pose estimation algorithms that better exploit this boundary information. In addition to oriented surface points, we use two other primitives: boundary points with directions and boundary line segments. Our experiments show that these carefully chosen primitives encode more information compactly and thereby provide higher accuracy for a wide class of industrial parts and enable faster computation. We demonstrate a practical robotic bin-picking system using the proposed algorithm and a 3D sensor.
AB - We propose a voting-based pose estimation algorithm applicable to 3D sensors, which are fast replacing their 2D counterparts in many robotics, computer vision, and gaming applications. It was recently shown that a pair of oriented 3D points, which are points on the object surface with normals, in a voting framework enables fast and robust pose estimation. Although oriented surface points are discriminative for objects with sufficient curvature changes, they are not compact and discriminative enough for many industrial and real-world objects that are mostly planar. As edges play the key role in 2D registration, depth discontinuities are crucial in 3D. In this paper, we investigate and develop a family of pose estimation algorithms that better exploit this boundary information. In addition to oriented surface points, we use two other primitives: boundary points with directions and boundary line segments. Our experiments show that these carefully chosen primitives encode more information compactly and thereby provide higher accuracy for a wide class of industrial parts and enable faster computation. We demonstrate a practical robotic bin-picking system using the proposed algorithm and a 3D sensor.
UR - http://www.scopus.com/inward/record.url?scp=84864490447&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864490447&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2012.6225371
DO - 10.1109/ICRA.2012.6225371
M3 - Conference contribution
AN - SCOPUS:84864490447
SN - 9781467314039
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 1724
EP - 1731
BT - 2012 IEEE International Conference on Robotics and Automation, ICRA 2012
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2012 IEEE International Conference on Robotics and Automation, ICRA 2012
Y2 - 14 May 2012 through 18 May 2012
ER -