Abstract:
The problem considered here is how to select the feature points (in practice small image patches are used) in an image from an image sequence, such that they can be tracked well further through the sequence. Usually, tracking is performed by some sort of local search methods searching for a similar patch in the next image from the sequence. Therefore, it would be useful if we could estimate ’the size of the convergence region ’ for each image patch. It is less likely to erroneously calculate the displacement for an image patch with a large convergence region than for an image patch with a small convergence region. Consequently, the size of the convergence region can be used as a proper goodness measure for a feature point. For the standard Kanade-Lucas-Tomasi (KLT) tracking method we propose a simple and fast method to approximate the convergence region for an image patch. In the experimental part we test our hypothesis on a large set of real data.
Citations
|
1235
|
Multiple view geometry in computer vision
– Hartley, Zisserman
- 2003
|
|
964
|
An iterative image registration technique with an application to stereo vision
– Lucas, Kanade
- 1981
|
|
792
|
A combined corner and edge detector
– Harris, Stephens
- 1988
|
|
669
|
Good features to track
– Shi, Tomasi
- 1994
|
|
658
|
Practical methods of optimization
– Fletcher
- 1987
|
|
639
|
Shape and motion from image streams under ortography: a factorization approach
– Tomasi, Kanade
- 1992
|
|
256
|
Efficient region tracking with parametric models of geometry and illumination
– Hager, Belhumeur
- 1998
|
|
220
|
Feature Detection with Automatic Scale Selection
– Lindeberg
- 1996
|
|
203
|
The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms
– Bradley
- 1997
|
|
200
|
Detection and tracking of point features
– Tomasi, Kanade
- 1991
|
|
198
|
Recursive estimation of motion, structure, and focal length
– Azarbayejani, Pentland
- 1995
|
|
133
|
Evaluation of Interest Point Detectors
– Schmid, Mohr, et al.
- 2000
|
|
110
|
The computation of optical flow
– Beauchemin, Barron
- 1995
|
|
67
|
A Real-Time Computer Vision System for Measuring Traffic Parameters
– Beymer, McLauchlan, et al.
- 1997
|
|
40
|
Real-time feature tracking and outlier rejection with changes
– Jin, Favaro, et al.
- 2001
|
|
31
|
Generalized Image Matching by the Method of Differences
– Lucas
- 1984
|
|
30
|
Unsupervised learning of human motion
– Song, Goncalves, et al.
|
|
25
|
a new approach to low-level image processing
– “SUSAN
- 1997
|
|
22
|
Improving feature tracking with robust statistics
– Fusiello, Trucco, et al.
- 1999
|
|
18
|
Nonlinear Systems Analysis (Prentice-Hall
– Vidyasagar
- 1993
|
|
14
|
Determining optical flow: a retrospective
– Horn, Schunck
- 1993
|
|
14
|
Fast corner detection
– Trajkovic, Hedley
- 1998
|
|
12
|
Estimation of Optical Flow Based on Higher-Order Spatiotemporal Derivatives in Interlaced and Non-Interlaced Image Sequences
– Otte, Nagel
- 1995
|
|
4
|
Understanding and modeling the evolution of critical points under gaussian blurring
– Kuijper, Florack
- 2002
|
