Efficient learning of linear predictors using dimensionality reduction

Authors:
Stefan Holzer;Slobodan Ilic;David Joseph Tan;Nassir Navab
Affiliations:
Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, Technische Universität München (TUM), Garching, Germany
Venue:
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Year:
2012

Citing 11
Cited 0

Efficient Region Tracking With Parametric Models of Geometry and Illumination

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Systems and Experiment Paper: Construction of Panoramic Image Mosaics with Global and Local Alignment

International Journal of Computer Vision
Hyperplane Approximation for Template Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas-Kanade 20 Years On: A Unifying Framework

International Journal of Computer Vision
Homography-based 2D Visual Tracking and Servoing

International Journal of Robotics Research
Tracking with general regression

Machine Vision and Applications
Selection of Reliable Features Subsets for Appearance-Based Tracking

SITIS '07 Proceedings of the 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System
Tracking by an Optimal Sequence of Linear Predictors

IEEE Transactions on Pattern Analysis and Machine Intelligence
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Learning efficient linear predictors for motion estimation

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using Linear Predictors for template tracking enables fast and reliable real-time processing. However, not being able to learn new templates online limits their use in applications where the scene is not known a priori and multiple templates have to be added online, such as SLAM or SfM. This especially holds for applications running on low-end hardware such as mobile devices. Previous approaches either had to learn Linear Predictors offline [1], or start with a small template and iteratively grow it over time [2]. We propose a fast and simple learning procedure which reduces the necessary training time by up to two orders of magnitude while also slightly improving the tracking robustness with respect to large motions and image noise. This is illustrated in an exhaustive evaluation where we compare our approach with state-of-the-art approaches. Additionally, we show the learning and tracking in mobile phone applications which demonstrates the efficiency of the proposed approach.