Covariance Tracking using Model Update Based on Lie Algebra

By Fatih Murat Porikli, Oncel Tuzel, Peter Meer. Computer Vision and Pattern Recognition, 2006

635 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/221c25297e149efe4934455550369b4a50326efb

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Pedestrian Detection via Classification on Riemannian Manifolds (2008, neutral): “Ç”
Online Object Tracking: A Benchmark (2013, methodology): “In addition to template, many other visual features have been adopted in tracking algorithms, such as color histograms [16], histograms of oriented gradients (HOG) [17, 52], covariance region descriptor [53, 46, 56] and Haar-like features [54, 22].”
Robust tracking using local sparse appearance model and K-selection (2011, methodology): “The generative models formulate the tracking problem as searching for the regions with the highest likelihood [5] [7] [16] [18] [19] [25] [28] [15], either using a single appearance model or multiple appearance models [27].”
Object Tracking Benchmark (2015, methodology): “In addition to template, many other visual features have been adopted in tracking algorithms, such as color histograms [16], histograms of oriented gradients (HOG) [17, 52], covariance region descriptor [53, 46, 56] and Haar-like features [54, 22].”
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition (2014, background): “[17] first introduced them for texture classification and later on extended them to tracking problems [11].”
Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices (2015, background): “The superiority of region covariance descriptor is firstly shown on object detection and texture classification [22] and then on object tracking [18].”
Minimum error bounded efficient ℓ1 tracker with occlusion detection (2011, methodology): “Examples of generative tracking methods are eigentracker [3], mean shift tracker [7], incremental tracker [20], and covariance tracker [19].”
Human Detection via Classification on Riemannian Manifolds (2007, methodology): “Covariance features were introduced in [21] for matching and texture classification problems, and later were extended to tracking [18].”
Visual Tracking: an Experimental Survey (2013, neutral): “A common way of updating is to substitute the old template with the last seen template, improved with partial updating [103], [104], with leaking [61], or with occasional target rebooting from scratch [105].”
Robust visual tracking using ℓ1 minimization (2009, methodology): “The Covariance tracker [27] was proposed to successfully track nonrigid objects using a covariance based object description that fuses different types of features and modalities.”
Real time robust L1 tracker using accelerated proximal gradient approach (2012, background): “eigentracker [3], mean shift tracker [6], incremental tracker [18] and covariance tracker [17].”
Scene-Level Geographic Image Classification Based on a Covariance Descriptor Using Supervised Collaborative Kernel Coding (2016, neutral): “, texture discrimination [18], visual saliency estimation [19], object detection [18,20] and object tracking [21].”
Multiple object tracking: A literature review (2014, background): “Region covariance matrix [82], [83] which computes up-to-second-order discrepancy belongs to this set.”
Robust Visual Tracking using 1 Minimization (2009, methodology): “The Covariance tracker [27] was proposed to successfully track nonrigid objects using a covariance based object description that fuses different types of features and modalities.”