Research Article Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity Hyuncheol Kim and Joonki Paik Department of Image, Chung-Ang University, Seoul 156-756, Republic of Korea Correspondence should be addressed to Joonki Paik; paikj@cau.ac.kr Received 13 August 2014; Revised 7 November 2014; Accepted 7 November 2014; Published 23 November 2014 Academic Editor: Sergei V. Pereverzyev Copyright © 2014 H. Kim and J. Paik. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. We address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. We frst select features with low-rank representation within a number of initial frames to obtain subspace basis. Next, the features represented by the low-rank and sparse property are learned using a modifed joint sparsity-based multitask feature learning framework. Both the features and sparse errors are then optimally updated using a novel incremental alternating direction method. Te low-rank minimization problem for learning multitask features can be achieved by a few sequences of efcient closed form update process. Since the proposed method attempts to perform the feature learning problem in both multitask and low- rank manner, it can not only reduce the dimension but also improve the tracking performance without drif. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art tracking methods for tracking objects in challenging image sequences. 1. Introduction Object tracking is one of the well-known problems in computer vision with many applications including intelligent surveillance, human-computer interface, and motion analy- sis. In spite of signifcant success, designing a robust object tracking algorithm remains still challenging issue due to fac- tors from real-world scenarios such as severe occlusion, scale and illumination variations, background clutter, rotations, and fast motions. An appearance model-based tracking method, which evaluates the likelihood of an observed image patch belong- ing to object class, considers some critical factors such as object representation and representation scheme. Te object representation can be categorized by adopted features [1, 2] and description models [3, 4]. Te representation scheme can be either generative or discriminative. Te generative methods regard the appearance modeling as fnding the image observation with minimal reconstruction error [5, 6]. On the other hand, the discriminative methods focus on determining a decision region that distinguishes the object from the background [7, 8]. Various object tracking methods based on object appear- ance models can handle only moderate changes and usually fail to track when the object appearance signifcantly changes. As a result, an appearance model learning process is required for robust object tracking under challenging issues such as object deformation. Recently, sparse representation-based ℓ 1 norm minimiza- tion methods have been successfully employed for object tracking [9–13], where an object is represented as one of mul- tiple candidates in the form of sparse linear combination of a dictionary that can be updated to maintain the optimal object appearance model. Although the sparse representation-based method can robustly track an object with partial occlusion, the computational cost for the ℓ 1 norm minimization in each frame is still expensive. Bao et al. applied the accelerated proximal gradient (APG) [14] approach to efciently solve the ℓ 1 minimization problems for object tracking. Structured multitask track- ing (MTT) was proposed by mining object discriminative structure between diferent particles rather than individually learning each particle [15]. Zhang et al. address their tracking performance as a fast solution of the MTT problem using Hindawi Publishing Corporation Abstract and Applied Analysis Volume 2014, Article ID 147353, 12 pages http://dx.doi.org/10.1155/2014/147353