Y
Yuichi Taguchi
Researcher at Mitsubishi Electric Research Laboratories
Publications - 295
Citations - 5416
Yuichi Taguchi is an academic researcher from Mitsubishi Electric Research Laboratories. The author has contributed to research in topics: Computer data storage & Point cloud. The author has an hindex of 35, co-authored 294 publications receiving 5009 citations. Previous affiliations of Yuichi Taguchi include Mitsubishi & Google.
Papers
More filters
Proceedings ArticleDOI
Joint Geodesic Upsampling of Depth Images
TL;DR: A novel approximation algorithm is developed whose complexity grows linearly with the image size and achieve realtime performance and is well suited for upsampling depth images using binary edge maps, an important sensor fusion application.
Proceedings ArticleDOI
Point-plane SLAM for hand-held 3D sensors
TL;DR: This work shows that it is possible to register 3D data in two different coordinate systems using any combination of three point/plane primitives, and uses the minimal set of primitives in a RANSAC framework to robustly compute correspondences and estimate the sensor pose.
Proceedings ArticleDOI
Fast plane extraction in organized point clouds using agglomerative hierarchical clustering
TL;DR: The proposed algorithm can reliably detect all major planes in the scene at a frame rate of more than 35Hz for 640×480 point clouds, which to the best of the knowledge is much faster than state-of-the-art algorithms.
Proceedings ArticleDOI
Voting-based pose estimation for robotic assembly using a 3D sensor
TL;DR: 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, is proposed and two other primitives are used: boundary points with directions and boundary line segments.
Journal ArticleDOI
Fast object localization and pose estimation in heavy clutter for robotic bin picking
Ming-Yu Liu,Ming-Yu Liu,Oncel Tuzel,Ashok Veeraraghavan,Ashok Veeraraghavan,Yuichi Taguchi,Tim K. Marks,Rama Chellappa +7 more
TL;DR: This work presents a practical vision-based robotic bin-picking system that performs detection and three-dimensional pose estimation of objects in an unstructured bin using a novel camera design, picks up parts from the bin, and performs error detection and pose correction while the part is in the gripper.