On-line selection of discriminative tracking features

By Robert T. Collins, Yanxi Liu. Proceedings Ninth IEEE International Conference on Computer Vision, 2003

1,417 citations recorded by the source corpus.

We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. We develop an online feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. This feature selection mechanism is embedded in a tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented to illustrate how the method adapts to changing appearances of both tracked object and scene background.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f51cb4be6e22f7e2b7126c9f2e250071a2351e08

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

On-road vehicle detection: a review (2006, background): “Several efforts have even been reported to improve tracking through feature selection [ 99 ].”
Robust visual tracking using ℓ1 minimization (2009, background): “Tracking can also be considered as a classification problem and a classifier is trained to distinguish the object from the background [1] [7].”
Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, background): “In Collins and Liu (2003), a target confidence map”
P-N learning: Bootstrapping binary classifiers by structural constraints (2010, neutral): “Sequence Frames [15] [7] [2] [3] [22] P-N Tracker 1.”
Tracking by Sampling Trackers (2011, methodology): “[3] used multiple features and selected robust ones through an on-line feature-ranking mechanism to deal with changing appearances.”
Object tracking: A survey (2006, background): “Some work has been done in this area for online selection of individual features [Collins and Liu 2003; Stern and Efros 2002].”
Tracking People by Learning Their Appearance (2007, background): “Discriminative features for tracking are not new [ 47 ], but by learning”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “. We do not predict the next action, we care about understanding the underlying physics that justiﬁes future motions in still images. Tracking: Note that our approach is quite different from tracking [17,11,10] since tracking methods are not destined for single image reasoning. [33] incorporates sim”
Data fusion for visual tracking with particles (2004, background): “appearance model, such as the background [8], [24], [55], [59].”
Part-based multiple-person tracking with partial occlusion handling (2012, background): “On the other hand, discriminative tracking approaches with online learning have flourished recently [1, 2, 11, 6, 10, 8].”
Tracking via Robust Multi-task Multi-view Joint Sparse Representation (2013, background): “Tracking problems can involve data that is represented by multiple views 1 of various types of visual features including intensity [28], color [4], edge [14], wavelet [12] and texture.”
Semi-supervised On-Line Boosting for Robust Tracking (2008, background): “Collins and Liu [5] were among the ﬁrst to emphasize (and exploit) this principle in a tracker.”
Robust Visual Tracking and Vehicle Classification via Sparse Representation (2011, neutral): “Examples include [2], [10], [46], [42], [3], and [23].”