International Journal of Sensors Wireless Communications and Control - Volume 6, Issue 3, 2016

Background: Visual place recognition is an interesting technology that can be used in many domains such as localizing historical photos, autonomous navigation and augmented reality. The main stream of research in that domain was based on the use of local invariant features like SIFT. Little attention was given to region descriptors which can encompass local and global visual appearances. In this paper, we provide an empirical study on two main visual descriptors: (i) Local Binary Patterns, and (ii) Covariance matrices. Methods: In order to enhance the discriminative power of the final descriptor of each type, multi-block based descriptors are designed and compared. The descriptor corresponding to each input is formed by the concatenation of the features extracted from each building block. We show experimental results on matching test images with reference images acquired in dense urban scenes in the streets of the city of Paris. The problems of scale changes and occlusions are both treated by simulation. Different combinations of processing steps are treated (covariance and LBP descriptors, mono and multi-blocks, L1 and Chi-Squared distances). Results: The obtained results for the tested scenarios show an improvement in the classification rate for at least three scenarios when using multi-block based features rather than mono-block based ones. Conclusion: The use of multi-block based features can thus enhance the discrimination of the obtained final descriptor. The corresponding matching algorithms can lead to both high accuracy and scalability.

Background: Most techniques that adopt the BOW model in annotating images declined favorable information that can be mined from image categories to build discriminative visual vocabularies. We introduce a detailed framework for automatically annotating natural scene images with local semantic labels from a predefined vocabulary. Methods: The proposed framework is based on a hypothesis that assumes that, in natural scenes, intermediate semantic concepts are correlated with the local keypoints. Based on this hypothesis, image regions can be efficiently represented by BOW model and using a machine learning approach, such as SVM, to label image regions with semantic annotations. Another objective of this paper is to address the implications of generating visual vocabularies from image halves, instead of producing them from the whole image, on the performance of annotating image regions with semantic labels. Results: The reported results have shown the plausibility of using the BOW model to represent the semantic information of image regions and thus to automatically annotate image regions with semantic labels. Conclusion: Our experimental results shows the plausibility of local from global approach for image region annotation as well as the discriminative power of using visual vocabularies from image halves. It showed an improved annotation results using integrated bag of visual words combined with low-level features.

Background: A typical content-based image retrieval system deals with the query image and images in the dataset as a collection of low-level features and retrieves a ranked list of images based on the similarities between features of the query image and features of images in the image dataset. However, top ranked images in the retrieved list, which have high similarities to the query image, may be different from the query image in terms of the semantic interpretation of the user which is known as the semantic gap. In order to reduce the semantic gap, this paper investigates how natural scene retrieval can be performed using the bag of visual word model and the distribution of local semantic concepts. Methods: We study the efficiency of using different approaches for representing the semantic information, depicted in natural scene images, for image retrieval. Results: The semantic representation of the natural scene images has been implemented using the annotated and un-annotated images. Firstly, the retrieval performance when employing the COV to summarize the amount of local semantic concepts depicted in an image have reported an encouraging results. The COV constructed from the labels of image regions represented by the BOW model have shown better performance compared with the baseline methods, such as color histogram, and also comparable with the COV benchmark. Secondly, the retrieval performance of using different configuration of the bag of visual word model have been studied and evaluated experimentally using three natural scene datasets. Conclusion: The experimental results obtained using the different image datasets have shown that the concept occurrence vector approaches achieved better retrieval accuracy compared to the BOW-based approaches and baseline.

This paper presents a vision-based monitoring system for developing low-cost and contactless Parking Management Services (PMS). Additionally, this paper describes a flexible and adaptive parking space monitoring system. More precisely, this system can be exploited for detecting parking space occupancies. Experimental results have been conducted by using a webcam that is connected to a conventional micro-computer in order to detect available car parking slots. The system can be installed either at the top of a street pole or a building and can be oriented in direction of a targeted car parking.

Background: Despite plenty of applications and improvements related to traditional networking schema based on Internet Protocol (IP), there is a lack of a generic networking schema for low-cost Internet of Things, based on non-TCP/UDP protocols, standards and devices. One may also point out limited possibilities for address-free networking at a small scale (within a room, a workplace, at home) based on broadcast and multicast, as well as multi-hop relaying. Method: We took into attention several communication modes and hardware modules for AVR and Raspberry microcontrollers, both wired and wireless, spiked with symmetric cryptography and textual (human-readable) format of the messages. Results: In this paper we propose a new way of networking called Home Computer Network (HCN), devoted to home and DIY applications. HCN protocol stands for a flexible standard of generic, stateless information exchange among two or more nodes, regardless the communication links on the way from a sender node to all the receivers. The proposal covers both address-free and addressable transmission. In the address-free mode, the incoming message is to be accepted by the receiving node based on message contents, i.e., its semantics and parameters. Once a message is accepted, the node performs certain actions related to the message. In parallel, the message is re-transmitted to other communication channels (except the channel the message arrived by) to be inspected by other nodes – this is so called multi-hop communication. To eliminate possible loops in information flow, the repeated messages are identified and eliminated, based on unique descriptors of the messages. In the addressable mode, the message is linked with an identifier of the receiving node – such a message is accepted only by a certain node, and is not propagated in multi-hop mode by any other node. Each message may be encrypted. Due to limited node resources, simple, however powerful encryption standard has been applied, namely xxTEA algorithm, with pre-shared encryption key common for all the nodes. Conclusion: HCN makes it possible to automate the process of linking several micro-controllers at home into a single consistent network, with limited amount of programmers’ work and with very low-cost hardware such as AVR-based computers, Raspberry boards, 2,4GHz and 433/868MHz networking modules, Bluetooth, classical cable connections such as RS-232 and RS-485, 1-wire, SPI, and many other DIY solutions.

Background: In smart grids mainly there are two types of communications based on the paths travelled by the received signals. These are line of sight (LOS) communication and non-line of sight (NLOS) communication. These communication models are formed because of different harsh environments like 500 kV outdoor substations, main power control room and underground transformer vaults which are very difficult to access and monitor for a human being during an operational power grid. In the recent research, the network lifetime has been evaluated with respect to the arrival rate, distance and duty cycle for LOS and NLOS communication. Methods:The systematic analysis is performed to characterize the aptness of the cluster tree topology of ZigBee based wireless sensor networks in the monitoring of non-line of sight regions having different shadowing channel properties in the smart grids. Results: The performance is evaluated by thoroughly analyzing the average end-to-end delay with respect to the packet interval, throughput, energy consumption, packet reception rate and network lifetime with respect to the packet size. The simulations are performed on QualNet 6.1 simulator. The objective of this work is to determine the influence of packet interval, packet size and different NLOS environments on the performance of ZigBee based wireless sensor network deployed in smart grids and to give prominence to this field for further exploration. Conclusion: The simulation results illustrate that huge errors in packet reception and variable link capacity in complex environments of the smart grid spectrum gives rise to many challenges in the reliability of ZigBee based wireless communications in smart grids. The design and implementation of efficient algorithms and protocols to reduce the collisions and interference can be considered for the future work.