Mobile Wireless Sensor and Actor Networks (MWSANs) can simply be defined as an extension of Wireless Sensor and Actor Networks (WSANs) in which the actor nodes are mobile. As such, in addition to challenges existing in WSAN, the mobility also imposes new challenges such as localization of actors, cooperative tracking of both actor-actor and actor-sensor collaboration, and communication infrastructure between distant actors. New communication protocols, specific to MWSANs, are needed. In this paper, we propose a self-organization and data collection protocol in order to provide energy efficiency, low latency, high success rate and suitably interactions between sensors and actors and take benefit from the mobility and resources existing on the network's actor nodes. The actor nodes move according to RWP mobility model. Each actor, during its pause time creates a temporary cluster, and is the head of it, collects and processes sensor data and performs actions on the environment based on the information gathered from sensor nodes in its cluster. Once an actor detects a base station it delivers the collected data to it. The simulations carried out (with TOSSIM tool), comfort us with good performances results.

In this paper, we propose a novel self-organization protocol for wireless sensor networks (WSNs) assisted by Unmanned Aerial Vehicle (UAV or Drone) called SSP (Self-organization Smart Protocol). In order to provide energy efficiency, low latency, high success rate and suitably interactions between sensors and UAVs while taking advantage of the air mobility (fly) and resource available on the UAVs in the network. The UAVs move according to RWP (Random Waypoint) mobility model. Each UAV, during its pause time at a known height, creates a temporary cluster, and acts as its head, collects and processes sensor data and performs actions on the environment based on the information gathered from sensor nodes in its cluster. Once an UAV detects a base station (BS) it forwards the collected data to it. The results of the simulations show the high performance of the proposed algorithm.

Scene text presents challenging characteristics mainly related to acquisition circumstances and environmental changes resulting in low quality videos. In this paper, we present a scene text detection algorithm based on pseudo Zernike moments (PZMs) and stroke features from low resolution lecture videos. Algorithm mainly consists of three steps: slide detection, text detection and segmentation and non-text filtering. In lecture videos, slide region is a key object carrying almost all important information; hence slide region has to be extracted and segmented from other scene objects considered as background for later processing. Slide region detection and segmentation is done by applying pseudo Zernike moment's based on RGB frames. Text detection and extraction is performed using PZMs segmentation over V channel of HSV colour space, and then stroke feature is used to filter out non-text region and to remove false positives. The algorithm is robust to illumination, low resolution and uneven luminance from compressed videos. Effectiveness of PZM description leads to very few false positives comparing to other approached. Moreover resulting images can be used directly by OCR engines and no more processing is needed.

With the huge increase of large-scale multimedia over Internet, especially images, building Content-Based Image Retrieval (CBIR) systems for large-scale images has become a big challenge. One of the drawbacks associated with CBIR is the very long execution time. In this article, we propose a fast Content-Based Image Retrieval system using Spark (CBIR-S) targeting large-scale images. Our system is composed of two steps. (i) image indexation step, in which we use MapReduce distributed model on Spark in order to speed up the indexation process. We also use a memory-centric distributed storage system, called Tachyon, to enhance the write operation (ii) image retrieving step which we speed up by using a parallel k-Nearest Neighbors (k-NN) search method based on MapReduce model implemented under Apache Spark, in addition to exploiting the cache method of spark framework. We have showed, through a wide set of experiments, the effectiveness of our approach in terms of processing time.