No abstract

Conventional neural networks show a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known SOBS method and its variants based on neural networks were the leader methods on the largescale CDnet 2012 dataset during a long time. Recently, convolutional neural networks which belong to deep learning methods were employed with success for background initialization, foreground detection and deep learned features. Currently, the top current background subtraction methods in CDnet 2014 are based on deep neural networks with a large gap of performance in comparison on the conventional unsupervised approaches based on multi-features or multi-cues strategies. Furthermore, a huge amount of papers was published since 2016 when Braham and Van Droogenbroeck published their first work on CNN applied to background subtraction providing a regular gain of performance. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. For this, we first surveyed the methods used background initialization, background subtraction and deep learned features. Then, we discuss the adequacy of deep neural networks for background subtraction. Finally, experimental results are presented on the CDnet 2014 dataset.

International audienceAccurate and efficient foreground detection is an important task in video surveillance system. The task becomes more critical when the background scene shows more variations, such as water surface, waving trees, varying illumination conditions, etc. Recently, Robust Principal Components Analysis (RPCA) shows a very nice framework for moving object detection. The background sequence is modeled by a low-dimensional subspace called low-rank matrix and sparse error constitutes the foreground objects. But RPCA presents the limitations of computational complexity and memory storage due to batch optimization methods, as a result it is difficult to apply for real-time system. To handle these challenges, this paper presents a robust foreground detection algorithm via Online Robust PCA (OR-PCA) using image decomposition along with continuous constraint such as Markov Random Field (MRF). OR-PCA with good initialization scheme using image decomposition approach improves the accuracy of foreground detection and the computation time as well. Moreover, solving MRF with graph-cuts exploits structural information using spatial neighborhood system and similarities to further improve the foreground segmentation in highly dynamic backgrounds. Experimental results on challenging datasets such as Wallflower, I2R, BMC 2012 and Change Detection 2014 dataset demonstrate that our proposed scheme significantly outperforms the state of the art approaches and works effectively on a wide range of complex background scenes

Virtual reality (VR) offers new possibilities for learning, specifically for training individuals to perform physical movements such as physical therapy and exercise. The current article examines two aspects of VR that uniquely contribute to media interactivity: the ability to capture and review physical behavior and the ability to see one's avatar rendered in real time from third person points of view. In two studies, we utilized a state-of-the-art, image-based tele-immersive system, capable of tracking and rendering many degrees of freedom of human motion in real time. In Experiment 1, participants learned better in VR than in a video learning condition according to self-report measures, and the cause of the advantage was seeing one's avatar stereoscopically in the third person. In Experiment 2, we added a virtual mirror in the learning environment to further leverage the ability to see oneself from novel angles in real time. Participants learned better in VR than in video according to objective performance measures. Implications for learning via interactive digital media are discussed. Interactivity and Learning in Virtual Reality 355Historically, virtual reality (VR) learning environments have been applied to a multitude of learning scenarios, from flight simulation (Hays, Jacobs, Prince, & Salas, 1992) to medical training (Berkley, Turkiyyah, Berg, Ganter, & Weghorst, 2004) to classroom learning (Pantelidis, 1993). One of the most exciting aspects of VR is its ability to leverage interactivity. Virtual systems offer a novel, flexible environment with affordances not possible from previous mediums like video and text (Blascovich et al., 2002). These virtual environments offer unique opportunities for learning on-demand (Trondsen & Vickery, 1997), customization and personalization (Kalyanaraman & Sundar, 2006), and feedback mechanisms (Lee & Nass, 2005). Previous research has shown that on-demand learning provides an advantage over face-to-face human interaction (Trondsen & Vickery, 1997). In a variety of contexts, VR offers possibilities to extend the notion of interactive learning in ways not possible through face-to-face interaction (see Bailenson et al., 2008, for a review of research on learning in VR).The current studies measured the effects of learning physical tasks from a virtual system when compared to video, leveraging features such as threedimensional depth cues, representations of the participant next to the instructor, and changes of scene angle not possible through traditional video representations. INTERACTIVITY IN MEDIAAs Sundar and Nass (2000) point out, digital technology has drastically changed the way in which communication occurs; audiences, typically referred to as passive receivers, have now become more active in their media experience, often being referred to as ''users.'' Conceptual definitions of interactivity typically emphasize three dimensions: technology, process, and user. Proponents of the technology dimension argue that interactivity is an affordance of technology (Steuer, 1...

Background estimation and foreground segmentation are important steps in many high-level vision tasks. Many existing methods estimate background as a low-rank component and foreground as a sparse matrix without incorporating the structural information. Therefore, these algorithms exhibit degraded performance in the presence of dynamic backgrounds, photometric variations, jitter, shadows, and large occlusions. We observe that these backgrounds often span multiple manifolds. Therefore, constraints that ensure continuity on those manifolds will result in better background estimation. Hence, we propose to incorporate the spatial and temporal sparse subspace clustering into the robust principal component analysis (RPCA) framework. To that end, we compute a spatial and temporal graph for a given sequence using motion-aware correlation coefficient. The information captured by both graphs is utilized by estimating the proximity matrices using both the normalized Euclidean and geodesic distances. The low-rank component must be able to efficiently partition the spatiotemporal graphs using these Laplacian matrices. Embedded with the RPCA objective function, these Laplacian matrices constrain the background model to be spatially and temporally consistent, both on linear and nonlinear manifolds. The solution of the proposed objective function is computed by using the linearized alternating direction method with adaptive penalty optimization scheme. Experiments are performed on challenging sequences from five publicly available datasets and are compared with the 23 existing state-of-the-art methods. The results demonstrate excellent performance of the proposed algorithm for both the background estimation and foreground segmentation.