Error Bounded Foreground and Background Modeling for Moving Object Detection in Satellite Videos

Abstract

Detecting moving objects from ground-based videos is commonly achieved by using background subtraction techniques. Low-rank matrix decomposition inspires a set of state-ofthe-art approaches for this task. It is integrated with structured sparsity regularization to achieve background subtraction in the developed method of Low-rank and Structured Sparse Decomposition (LSD). However, when this method is applied to satellite videos where spatial resolution is poor and targets contrast to the background is low, its performance is limited as the data no longer fits adequately either the foreground structure or the background model. In this paper, we handle these unexplained data explicitly and address the moving target detection from space as one of the pioneer studies. We propose a new technique by extending the decomposition formulation with bounded errors, named Extended Low-rank and Structured Sparse Decomposition (E-LSD). This formulation integrates lowrank background, structured sparse foreground as well as their residuals in a matrix decomposition problem. To solve this optimization problem is challenging. We provide an effective solution by introducing an alternative treatment and adopting the direct extension of Alternating Direction Method of Multipliers (ADMM). The proposed E-LSD was validated on two satellite videos, and experimental results demonstrate the improvement in background modeling with boosted moving object detection precision over state-of-the-art methods.

Low-Rank Matrix Decomposition With Superpixel-Based Structured Sparse Regularization for Moving Object Detection in Satellite Videos

“…To verify the effectiveness of S-LSD, we compare the detection performance against three state-of-the-art approaches, which are RPCA (Candès et al, 2011), LSD (Liu et al, 2015) and E-LSD (Zhang et al, 2019a). RPCA is a low-rank matrix decomposition method without spatial constraints on the foreground,and is solved by Principal Component Pursuit.…”

“…Another set of spatial prior on the foreground is defined on the sparsity over groups of spatial neighboring pixels other than independent pixels. The structured sparsity-inducing norm (Jenatton et al, 2011) is then introduced to regularize the foreground (Liu et al, 2015;Xu et al, 2013;Zhang et al, 2019a). In satellite videos, an Extended Low-rank and Structured Sparse Matrix Decomposition (E-LSD) model is proposed for boosting the MOD performance by imposing structured sparse regularization on the foreground (Zhang et al, 2019a,b).…”

“…In this paper, we adopt the ADMM approach for solving this augmented problem in Equation. ( 6), since the sufficient guarantee on the convergence has been provided for the set of optimization problems that minimizes the sum of three functions with uncoupled variables under a three-block linear constraint (Cai et al, 2017;Zhang et al, 2019a).…”

Review on Real Time Background Extraction: Models, Applications, Environments, Challenges and Evaluation Approaches

“…Traffic surveillance includes highways and roads environments, the foreground detection can be employed to count stopped vehicles [14] Traffic surveillance is affected by different factors, for example the camera location factor where most of the time it is a stationary camera. Sometimes traffic senses are aerial videos taken by a drone [149][150] or even high-resolution videos taken by a satellite [151][152] [153]. Also, the quality of the camera is highly considered in terms of the video characteristics in traffic scenes.…”

Multitarget Detection and Tracking Method in Remote Sensing Satellite Video

“…e tracking algorithms based on deep learning are mainly divided into two categories [15,16]: one is to design tracking algorithms based on deep features and related filtering; the other is to track targets' end-to-end based on deep networks. e existing satellite video target detection and tracking algorithms basically follow the related results in traditional video processing, as shown in [17][18][19][20][21][22][23][24][25][26][27]. Aiming at the needs of satellite video moving target detection and tracking, this paper proposes a background subtraction method based on a hybrid Gaussian background model combined with a road mask.…”