Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Abstract

Infrared moving target tracking plays a fundamental role in many burgeoning research areas of Smart City. Challenges in developing a suitable tracker for infrared images are particularly caused by pose variation, occlusion, and noise. In order to overcome these adverse interferences, a total variation regularization term-based low-rank and sparse matrix representation (TV-LRSMR) model is designed in order to exploit a robust infrared moving target tracker in this paper. First of all, the observation matrix that is derived from the infrared sequence is decomposed into a low-rank target matrix and a sparse occlusion matrix. For the purpose of preventing the noise pixel from being separated into the occlusion term, a total variation regularization term is proposed to further constrain the occlusion matrix. Then an alternating algorithm combing principal component analysis and accelerated proximal gradient methods is employed to separately optimize the two matrices. For long-term tracking, the presented algorithm is implemented using a Bayesien state inference under the particle filtering framework along with a dynamic model update mechanism. Both qualitative and quantitative experiments that were examined on real infrared video sequences verify that our algorithm outperforms other state-of-the-art methods in terms of precision rate and success rate.

Infrared Small Target Detection with Total Variation and Reweighted ℓ1 Regularization

“…e proposed model contains an optimization problem: the objective function includes the nuclear norm, ℓ 1 norm, and total variation norm and is solved by ADMM. For the proposed method, the computational complexities of updating the variables Z 1 , Z 2 , Z 3x , Z 3y , B, and T in (12), (15), (19), (20), (22), and (24) for each iteration are O(mn 2 ), O(mn), O(mn), O(mn), O(mn), and O(mn), respectively. erefore, the total cost of each iteration for the proposed method is O(mn 2 ) operations.…”

“…A large number of methods have been developed to address the issues of small target detection. ese methods can be roughly classified into two categories: single-frame detection [5][6][7][8][9][10][11][12][13][14][15][16] and sequential multiframe detection [17][18][19]. Recently, Gao et al [17] employed the mixture of the Gaussians model [20] with the Markov random field to model the complex noise of which the target is assumed as a component.…”

Fabric defect detection based on deep-feature and low-rank decomposition

“…Low-rank decomposition (LRD) techniques 30 can divide an image matrix into two parts: low-rank matrix and sparse matrix, where the low-rank matrix indicates a smooth background and the sparse matrix indicates the salient regions. It has been successfully used in a variety of applications, such as subspace segmentation, 31 visual tracking, 32,33 image clustering, 34 and video backgroundforeground separation. 35,36 Shen and Wu 37 provided a unified framework for integrating high-level knowledge and low-level features, which is based on the assumption that an image could be represented as the sum of the background being low rank and the salient regions being sparse.…”

A Hierarchical Association Framework for Multi-Object Tracking in Airborne Videos

“…The goal of Multi-Object Tracking (MOT) in airborne videos is to estimate the state of multiple objects and conserving their identities given variations in appearance and motion over time [1][2][3][4]. MOT is challenging due to the uncertain motion of airborne vehicles, the vibration of non-stationary cameras and the partial occlusions of objects [5].…”