ESHARP: Energy-Efficient and Smart Hierarchical Routing Protocol Based on Smart Slumber for Wireless Sensor Networks

Wireless Personal Communications - This paper proposes a new energy management function intended to be integrated in the Hierarchical Smart Routing Protocol (HSRP) mainly proposed for Wireless...     

RaCH: A New Radial Cluster Head Selection Algorithm for Wireless Sensor Networks

Wireless Personal Communications - This paper presents a radial cluster heads selection mechanism for homogenous wireless sensor networks. It aims to ensure a good load balancing and enhance the...     

An online approach for multi-sprite generation based on camera parameters estimation

We propose in this work to synthesize online the visual content of a complex video into multiple sprites, while detecting on-the-fly each sprite’s limits. For each received frame, physically meaningful camera rotation angles and focal lengths are firstly estimated from frame-to-sprite homography. These physical parameters are then used by a thresholding-based assignment stage to confirm whether the frame can be added without distortions on one of the sprites that have been built up to that instant. In this case, the selected sprite will be updated online accordingly by applying direct frame-to-sprite warping and advanced median blending of only the newly discovered background content. Else, a new sprite must be defined while selecting the current frame as a reference frame. Extensive experiments accomplished on challenging videos demonstrate that the proposed approach can process online a long video while preventing accumulation of alignment errors.     

Fuzzy VA-Files for multi-label image annotation based on visual content of regions

In this work, we propose an efficient image annotation approach based on visual content of regions. We assume that regions can be described using low-level features as well as high-level ones. Indeed, given a labeled dataset, we adopt a probabilistic semantic model to capture relationships between low-level features and semantic clusters of regions. Moreover, since most previous works on image annotation do not deal with the curse of dimensionality, we solve this problem by introducing a fuzzy version of the Vector Approximation Files (VA-Files). Indeed, the main contribution of this work resides in the association of the generative model with fuzzy VA-Files, which offer an accurate multi-dimensional indexing, to estimate relationships between low-level features and semantic concepts. In fact, the proposed approach reduces the computation complexity while optimizing the annotation quality. Preliminary experiments highlight that the suggested approach outperforms other state-of-the-art approaches.     

Reconstructing Convex Matrices by Integer Programming Approaches

We consider the problem of reconstructing two-dimensional convex binary matrices from their row and column sums with adjacent ones. Instead of requiring the ones to occur consecutively in each row and column, we maximize the number of adjacent ones. We reformulate the problem by using integer programming and we develop approximate solutions based on linearization and convexification techniques.