no code implementations • CVPR 2020 • Amit Dekel, Linus Härenstam-Nielsen, Sergio Caccamo
We propose a least-squares formulation to the noisy hand-eye calibration problem using dual-quaternions, and introduce efficient algorithms to find the exact optimal solution, based on analytic properties of the problem, avoiding non-linear optimization.
no code implementations • 13 Feb 2018 • Sergio Caccamo, Esra Ataer-Cansizoglu, Yuichi Taguchi
To robustly classify the features in each frame, we fuse multiple RANSAC-based registration results obtained by registering different groups of the features to different maps, including (1) all the features to the static map, (2) all the features to each object map, and (3) subsets of the features, each forming a segment, to each object map.
no code implementations • 18 Oct 2017 • Sergio Caccamo, Ramviyas Parasuraman, Luigi Freda, Mario Gianni, Petter Ögren
Mobile robots, be it autonomous or teleoperated, require stable communication with the base station to exchange valuable information.
no code implementations • 17 Oct 2017 • Wim Abbeloos, Esra Ataer-Cansizoglu, Sergio Caccamo, Yuichi Taguchi, Yukiyasu Domae
We present a method for unsupervised 3D object discovery, reconstruction, and localization that exploits multiple instances of an identical object contained in a single RGB-D image.
no code implementations • 23 Jul 2017 • Wim Abbeloos, Sergio Caccamo, Esra Ataer-Cansizoglu, Yuichi Taguchi, Chen Feng, Teng-Yok Lee
Often multiple instances of an object occur in the same scene, for example in a warehouse.