Visual tracking via robust multi-task multi-feature joint sparse representation

In this paper, we cast tracking as a novel multi-task learning problem and exploit various types of visual features. We use an on-line feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samp...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Yong, Luo, Xinbin, Hu, Shiqiang
Format: Conference Proceeding
Language:English
Subjects:
Alternating Direction Method of Multipliers
Electronics
Exact solutions
Feature extraction
feature selection
Filtering
Filtration
Formulations
Kalman filters
multi-task learning
Object tracking
Robustness
Sparse matrices
Target tracking
Tracking
Variance
Visual
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we cast tracking as a novel multi-task learning problem and exploit various types of visual features. We use an on-line 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. The proposed method is integrated in a particle filtering framework. We jointly consider the underlying relationship across different particles, and tackle it in a unified robust multi-task formulation. We show that the proposed formulation can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) with a small number of closed-form updates. Both the qualitative and quantitative results demonstrate the superior performance of the proposed approach compared to several state of-the-art trackers.
ISSN:2379-190X
DOI:10.1109/ICASSP.2016.7471931