An Efficient Spatiotemporal Approach for Moving Object Detection in Dynamic Scenes

An Efficient Spatiotemporal Approach for Moving Object Detection in Dynamic Scenes

Min Liu (Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, China), Yang Liu (Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, China), Cong Liu (Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, China), Juan Wang (Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, China) and Minghu Wu (Hubei Collaborative Innovation Center for High-efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, China)
DOI: 10.4018/IJITWE.2017070106
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The dynamic texture (DT) which treats the transient video process a sample from the spatiotemporal model, has shown the surprising performance for moving objects detection in the scenes with the background motions (e.g., swaying branches, falling snow, waving water). However, DT parameters estimation is based on batch-PCA, which is a computationally inefficient method for high-dimensional vectors. Besides, in the realm of DT, the dimension of state space is given or set experimentally. In this work, the authors present a new framework to address these issues. First, they introduce a two-step method, which combines batch-PCA and the increment PCA (IPCA) to estimate the DT parameters in a micro video element (MVE) group. The parameters of the first DT are learned with the batch-PCA as the basis parameters. Parameters of the remaining DTs are estimated by IPCA with the basis parameters and the arriving observation vectors. Second, inspired by the concept of “Observability” from the control theory, the authors extend an adaptive method for salient motion detection according to the increment of singular entropy (ISE). The proposed scheme is tested in various scenes. Its computational efficiency outperforms the state-of-the-art methods and the Equal Error Rate (EER) is lower than other methods.
Article Preview

1. Introduction

Moving object detection is the first step as a pre-processing task for many computer vision applications, e.g., visual surveillance (Javed, Shafique, & Shah, 2007; Huang & Chen, 2014), behavior recognition (Gowsikhaa, Abirami, & Abiram, 2014), video retrieval (Chen & Huang, 2014) and video compression (Tong et al., 2014; Hadizadeh & Bajic, 2013). The objective of this task is to obtain the accurate foreground-background segmentation as an input for the high level analysis. Despite of its key importance, most traditional approaches (Hadizadeh & Bajic, 2013; Doretto et al., 2003) fail in the dynamic scenes. In some realistic scenarios shot by the static camera, the dynamic behaviors are caused by background elements, e.g., falling snow, moving water, rain, fountain, waves and swaying trees. In this case, objects of interest are moving among the complicated scene motion. Some scenes are static, but monitored by the moving or distant camera, or the static scenes are with ego- motion. It is very challenging to detect objects of interest in these dynamic scenes for computer vision community.

Recently, it is more successful in modeling the dynamic scenes as samples from a linear dynamical system (Doretto et al., 2003; Mahadevan & Vasconcelos, 2009; Gopalakrishnan, Rajan, & Hu, 2012). These works have demonstrated that DT as a probabilistic motion model is much more powerful than the classic background models. In fact, DT has the amazed ability to account for the various complex patterns of motion and appearance, while jointly modeling the spatiotemporal characteristics of the stochastic visual processes. One major limitation is that DT parameters estimation is based on batch-PCA. The complexity of the batch PCA is dominated by taking the SVD of a high-dimensional matrix. Let the observed data matrix be the complexity of SVD of is . So, the batch-PCA is a computationally inefficient method for high-dimensional vectors.

Besides, in the realm of DT, the dimension of state space is given or set experimentally. In practice, the parameter should be inferred from the observed data. DT represents the dynamic process as the output of the linear dynamic system driven by white, zero-mean Gaussian noise. If is set high as the order of the model, much noise will be included in the useful variable components, if not, some useful components will be removed. Therefore, the suitable selection of the parameter becomes very important.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 13: 4 Issues (2018): 2 Released, 2 Forthcoming
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing