Jacobian Images of Super-Resolved Texture Maps for Model-Based Motion Estimation and Tracking

Authors:
Frank Dellaert;Sebastian Thrun;Chuck Thorpe
Affiliations:
-;-;-
Venue:
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Year:
1998

Citing 0
Cited 6

Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Active blobs: region-based, deformable appearance models

Computer Vision and Image Understanding - Special issue on nonrigid image registration
Ordinal regression based subpixel shift estimation for video super-resolution

EURASIP Journal on Advances in Signal Processing
3D Motion from structures of points, lines and planes

Image and Vision Computing
Inertially Aided Visual Odometry for Miniature Air Vehicles in GPS-denied Environments

Journal of Intelligent and Robotic Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a Kalman filter based approach to performmodel-based motion estimation and tracking. Unlike previousapproaches, the tracking process is not formulated asan SSD minimization problem, but is developed by usingtexture mapping as the measurement model in an extendedKalman filter. During tracking, a super-resolved estimateof the texture present on the object or in the scene is obtained.A key result is the notion of Jacobian images, whichcan be viewed as a generalization of traditional gradientimages, and represent the crucial computation in the trackingprocess. The approach is illustrated with three sampleapplications: full 3D tracking of planar surface patches, aprojective surface tracker for uncalibrated camera scenarios,and a fast, Kalman filtered version of mosaicking withdetection of independently moving objects.