Joint Anisotropic Mean Shift and Consensus Point Feature Correspondences for Object Tracking in Video
Paper in proceeding, 2009

We propose a novel tracking scheme that jointly employs point feature correspondences and object appearance similarity. For selecting point correspondences, we use a subset of scale-invariant point features from SIFT that agree with a pre-defined affine transformation. The selected consensus points are then used for pre-selecting candidate regions. For appearance similarity based tracking, we employ an existing anisotropic mean shift, from which the formula for estimating bounding box parameters (width, height, orientation and center) are derived. A switching criterion is utilized to handle the situation where only a small number of point correspondences is found. Experiments and evaluation are performed on tracking moving objects on videos where objects may contain partial occlusions, intersection, deformation and pose changes among other transforms. Our comparisons with two existing methods have shown that the proposed scheme has yielded marked improvement, especially in terms of reducing tracking drifts, of robustness to occlusions, and of tightness and accuracy of tracked bounding box.

anisotropic mean shift

SIFT

point feature correspondences

RANSAC

appearance model.

Video object tracking

Author

Zulfiqar Hasan Khan

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Irene Yu-Hua Gu

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Tiesheng Wang

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Andrew Backhouse

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

Proc. of IEEE International conf. on Multimedia and Expo. (ICME '09)

1270-1273

Subject Categories

Computer Engineering

Signal Processing

Computer Vision and Robotics (Autonomous Systems)

More information

Created

10/6/2017