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
User-Powered "Content-Free" Approach to Image Retrieval
Takeo Kanade,Shingo Uchihashi +1 more
TL;DR: The results indicate that the performance of CFIR improves with the number of accumulated feedbacks, outperforming a basic but typical conventional CBIR system and being dubbed by a term “content-free” image retrieval (CFIR).
Proceedings ArticleDOI
Development of a 5-DOF walking robot for Space Station application: overview
TL;DR: An overview of the development of a robot walker for use on the NASA Space Station is presented, designed to perform such tasks as inspection, transport of parts, and simple manipulation.
Sensory Attention: Computational Sensor Paradigm for Low-Latency Adaptive Vision
Vladimir Brajovic,Takeo Kanade +1 more
TL;DR: A tracking computational sensor — a VLSI implementation of a sensory attention that reliably tracks features of interest while it suppresses other irrelevant features that may interfere with the task at hand.
Journal ArticleDOI
New technologies and applications in robotics
TL;DR: Material transfer robots first appeared in the mid-1960s for use in traditional industrial applications but by the 1980s, robots found use in more demanding industrial applications such as welding, assembly, and inspection, with the help of vision and other sensors.
Proceedings ArticleDOI
Coherent Object Detection with 3D Geometric Context from a Single Image
Jiyan Pan,Takeo Kanade +1 more
TL;DR: A novel generalized RANSAC algorithm is proposed to generate global 3D geometry hypotheses from local entities such that outlier suppression and noise reduction is achieved simultaneously and results show that this approach compares favorably with the state of the art.