T
Takeo Kanade
Researcher at Carnegie Mellon University
Publications - 800
Citations - 107709
Takeo Kanade is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Motion estimation & Image processing. The author has an hindex of 147, co-authored 799 publications receiving 103237 citations. Previous affiliations of Takeo Kanade include National Institute of Advanced Industrial Science and Technology & Hitachi.
Papers
More filters
Proceedings ArticleDOI
Interactive retrieval of targets for wide area surveillance
TL;DR: This work addresses the problem of interactive search for a target of interest in surveillance imagery by iteratively learning a distance metric for retrieval, based on user feedback, and employs rank based constraints and convex optimization to efficiently learn the distance metric.
Journal ArticleDOI
A perspective factorization method for Euclidean reconstruction with uncalibrated cameras
Mei Han,Takeo Kanade +1 more
TL;DR: A factorization-based method to recover Euclidean structure from multiple perspective views with uncalibrated cameras, and presents three normalization algorithms which enforce Euclideans constraints on camera calibration parameters to recover the scene structure and the camera calibration simultaneously, assuming zero skew cameras.
Journal ArticleDOI
Uncertainty in object pose determination with three light-stripe range measurements
K. Kemmotsu,Takeo Kanade +1 more
TL;DR: This paper presents a method for estimating the uncertainty in determining the pose of an arbitrarily positioned object with three light-stripe range finders, and demonstrates that the method provides the estimate of accuracy in pose determination.
Journal ArticleDOI
PARES: A prototyping and reverse engineering system for mechanical parts-on-demand on the national network
TL;DR: A system in which a mechanical designer, working at a CAD station in one geographic location, communicates with a CAM facility in another geographic location to obtain a fabricated part with rapid turnaround is described, which stands for prototyping and reverse engineering system.
Book ChapterDOI
Content-free image retrieval by combinations of keywords and user feedbacks
Shingo Uchihashi,Takeo Kanade +1 more
TL;DR: Experimental results show the proposed method outperforms a conventional content-based approach using support vector machine and the result was achieved by the combination of feedback data and keywords.