Takeo Kanade

TL;DR: In this article, a system and method for servoing on a moving target within a dynamic scene is described, which includes a master variable pointing camera system and a plurality of slave variable pointing cameras positioned around the scene.

TL;DR: The problem of super-resolving a human face video by a very high (/spl times/ 16) zoom factor is considered using a graphical model that encodes, (1) spatio-temporal consistencies, and (2) image formation & degradation processes.

TL;DR: In this article, an adaptive control of a space robot system with an attitude-controlled base on which the robot is attached is proposed, where most tasks are specified in inertia space, instead of joint space, and two potential problems, unavailability of the joint trajectory (since mapping from inertia space trajectory is dynamics-dependent and subject to uncertainty), and nonlinear parameterization in inertia spaces are identified.

TL;DR: The proposed method can overcome occlusions and divergence problems, and provides fast recovery after occlusion has ended, while preventing divergence problem which frequently occurs in conventional frame-to-frame tracking methods.

TL;DR: A critical, albeit brief, overview of feature point tracking, SFM algorithms and Kalman Filtering as they apply specifically to the state estimation problem for aircraft and features of the methods that are well-suited to aircraft estimation problems are noted.