Simultaneous Video Stabilization and Moving Object Detection in Turbulence

Abstract

Abstract-Turbulence mitigation refers to the stabilization of videos with non-uniform deformations due to the influence of optical turbulence. Typical approaches for turbulence mitigation follow averaging or de-warping techniques. Although these methods can reduce the turbulence, they distort the independently moving objects which can often be of great interest. In this paper, we address the novel problem of simultaneous turbulence mitigation and moving object detection. We propose a novel threeterm low-rank matrix decomposition approach in which we decompose the turbulence sequence into three components: the background, the turbulence, and the object. We simplify this extremely difficult problem into a minimization of nuclear norm, Frobenius norm, and 1 norm. Our method is based on two observations: First, the turbulence causes dense and Gaussian noise, and therefore can be captured by Frobenius norm, while the moving objects are sparse and thus can be captured by 1 norm. Second, since the object's motion is linear and intrinsically different than the Gaussian-like turbulence, a Gaussian-based turbulence model can be employed to enforce an additional constraint on the search space of the minimization. We demonstrate the robustness of our approach on challenging sequences which are significantly distorted with atmospheric turbulence and include extremely tiny moving objects.

Object detection oriented video reconstruction using compressed sensing

“…In real-world video surveillance, movement turbulence is repetitive and locally centered [20,21], which can be modeled by Gaussian distribution [22,23]. In this paper, we utilize the following mixed Gaussian model to estimate the intensity distribution of a pixel undergoing movement turbulence [22].…”

“…In this paper, we utilize the following mixed Gaussian model to estimate the intensity distribution of a pixel undergoing movement turbulence [22].…”

“…where f(x ij ) represents the probability density of a pixel x ij at jth element in the ith column ofX, ω is the weight of the two Gaussian models, μ x and σ x are the mean and the standard deviation, which are estimated by the EM algorithm, and μ p and Σ p are the mean and the covariance matrix, which are estimated from the particle trajectory of x ij [22]. Particle trajectory aims to capture the deformation caused by movement turbulence, which can be obtained by using Lagrangian particle trajectory advection approach [24,25].…”

Focus-of-attention for human activity recognition from UAVs

“…Simple methods such as estimation of the homography by RANSAC [12] have proven to be effective if parallax effects are not severe. For complex scenes that generate complicating artefacts, advanced methods have been proposed [13]. The scenes that will be considered in this paper are not very complex and therefore a simple method suffices.…”

Improved visual background extractor using an adaptive distance threshold

“…Therefore, moving object detection which extracts foreground objects from the background has become a hot issue, [1][2][3][4][5][6][7] and has been widely applied to areas such as smart video surveillance, intelligent transportation, and humancomputer interaction.…”