Leveraging Multiview Video Coding in clustered Multimedia Sensor networks

Abstract

Abstract-We experimentally characterize the compression efficiency of Multiview Video Coding (MVC) techniques in Wireless Multimedia Sensor network (WMSN) composed of multiple video cameras with possibly overlapping field of views. We derive an empirical model that predicts the compression efficiency as a function of the common sensed area (CSA) between different camera views. We show that the CSA depends not only on geometrical relationships among the relative positions of different cameras, but also on several object-related phenomena, e.g., occlusions and motion, and on low-level phenomena such as variations in illumination. We then apply the model to a WMSN, where we create clusters based on the CSA as estimated by exchanging local data. Based on this estimates, we form clusters and measure the resulting transmission rate. Numerical simulation results show that building clusters based on a CSA criterion can bring significant performance gains in terms of bandwidth efficiency. The herein presented promising results pave the way for clustering optimization taking into account different networks constraints and conditions.

An Empirical Model of Multiview Video Coding Efficiency for Wireless Multimedia Sensor Networks

“…This would facilitate in-network processing and reduce the wireless bandwidth needed to transmit the views to the sink. The single hop clustering scheme has been introduced in [8]. We report here the main results of this study.…”

“…The core novelty of this study is that, unlike previous work, we evaluate the MVC efficiency as a function of a parameter related to the scene content rather than to the geometry of the cameras only. Preliminary studies on this relationship have been presented in [8]. In this paper we extend these studies to different video sequences.…”

“…We recognize that the width is (6) being the horizontal angular camera width. The horizontal size of the object equals to (7) Besides, we recognize that the vertical size of the object equals to (8) being the vertical angular camera width. The remaining image pixels are occupied by projections of a subset of the background points, that is the subset of background points which are not occluded by the object itself.…”

“…To satisfy these requirements with a compact set of parameters, we propose to use a hyperbolic model, which can be formulated as follows (13) The model in (13) depends on two parameters, namely the constant 8 , which drives the hyperbole curvature, and . In the following, we relate the parameter to the efficiency of the temporal prediction and we provide a rational to set it based on the video sequence activity.…”

Game theoretic approach for cooperative feature extraction in camera networks

“…As an example, the cameras may exchange a downsampled version of their acquired image and compute a measure which is representative of the degree of similarity of the two views, hence on the expected redundancy between the extracted visual features. Here we rely on the Common Sensed Area (CSA) value, defined in, 26 as the ratio between the number of pixels belonging to the common area of two images i and j and the overall number of pixels of the image captured by camera i. In practice, such common area is approximated by applying a correlation-based image registration technique and counting the number of correctly registered pixels.…”