Jacobian images of super-resolved texture maps for model-based motion estimation and tracking
- 27 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
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.Keywords
This publication has 7 references indexed in Scilit:
- Model-based car tracking integrated with a road-followerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Super-resolved texture tracking of planar surface patchesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Real-time tracking of image regions with changes in geometry and illuminationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Recursive estimation of motion, structure, and focal lengthPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Motion Analysis for Image Enhancement: Resolution, Occlusion, and TransparencyJournal of Visual Communication and Image Representation, 1993
- Improving resolution by image registrationCVGIP: Graphical Models and Image Processing, 1991
- Recursive 3-D motion estimation from a monocular image sequenceIEEE Transactions on Aerospace and Electronic Systems, 1990