Local data fusion algorithm for fire detection through mobile robot

Multisensor data fusion is a technique that combines the readings of multiple sensors to detect some phenomenon. Data fusion applications are numerous and they can be used in smart buildings, environment monitoring, industry and defense applications. The main goal of multisensor data fusion is to minimize false alarms and maximize the probability of detection based on the detection of multiple sensors. In this paper a local data fusion algorithm based on luminosity, temperature and flame for fire detection is presented. The data fusion approach was embedded in a low cost mobile robot. The prototype test validation has indicated that our approach can detect fire occurrence. Moreover, the low cost project allow the development of robots that could be discarded in their fire detection missions. © 2013 IEEE.

Data fusion approaches and applications for construction engineering

Data fusion can be defined as the process of combining data or information for estimating the state of an entity. Data fusion is a multidisciplinary field that has several benefits, such as enhancing the confidence, improving reliability, and reducing ambiguity of measurements for estimating the state of entities in engineering systems. It can also enhance completeness of fused data that may be required for estimating the state of engineering systems. Data fusion has been applied to different fields, such as robotics, automation, and intelligent systems. This paper reviews some examples of recent applications of data fusion in civil engineering and presents some of the potential benefits of using data fusion in civil engineering.

Decentralised Data Fusion with Parzen Density Estimates

Decentralised sensor networks typically consist of multiple processing nodes supporting one or more sensors. These nodes are interconnected via wireless communication. Practical applications of Decentralised Data Fusion have generally been restricted to using Gaussian based approaches such as the Kalman or Information Filter This paper proposes the use of Parzen window estimates as an alternate representation to perform Decentralised Data Fusion. It is required that the common information between two nodes be removed from any received estimates before local data fusion may occur Otherwise, estimates may become overconfident due to data incest. A closed form approximation to the division of two estimates is described to enable conservative assimilation of incoming information to a node in a decentralised data fusion network. A simple example of tracking a moving particle with Parzen density estimates is shown to demonstrate how this algorithm allows conservative assimilation of network information.

BabelFuse data fusion unit with precision wireless clock synchronisation

A significant issue encountered when fusing data received from multiple sensors is the accuracy of the timestamp associated with each piece of data. This is particularly important in applications such as Simultaneous Localisation and Mapping (SLAM) where vehicle velocity forms an important part of the mapping algorithms; on fastmoving vehicles, even millisecond inconsistencies in data timestamping can produce errors which need to be compensated for. The timestamping problem is compounded in a robot swarm environment due to the use of non-deterministic readily-available hardware (such as 802.11-based wireless) and inaccurate clock synchronisation protocols (such as Network Time Protocol (NTP)). As a result, the synchronisation of the clocks between robots can be out by tens-to-hundreds of milliseconds making correlation of data difficult and preventing the possibility of the units performing synchronised actions such as triggering cameras or intricate swarm manoeuvres. In this thesis, a complete data fusion unit is designed, implemented and tested. The unit, named BabelFuse, is able to accept sensor data from a number of low-speed communication buses (such as RS232, RS485 and CAN Bus) and also timestamp events that occur on General Purpose Input/Output (GPIO) pins referencing a submillisecondaccurate wirelessly-distributed "global" clock signal. In addition to its timestamping capabilities, it can also be used to trigger an attached camera at a predefined start time and frame rate. This functionality enables the creation of a wirelessly-synchronised distributed image acquisition system over a large geographic area; a real world application for this functionality is the creation of a platform to facilitate wirelessly-distributed 3D stereoscopic vision. A ‘best-practice’ design methodology is adopted within the project to ensure the final system operates according to its requirements. Initially, requirements are generated from which a high-level architecture is distilled. This architecture is then converted into a hardware specification and low-level design, which is then manufactured. The manufactured hardware is then verified to ensure it operates as designed and firmware and Linux Operating System (OS) drivers are written to provide the features and connectivity required of the system. Finally, integration testing is performed to ensure the unit functions as per its requirements. The BabelFuse System comprises of a single Grand Master unit which is responsible for maintaining the absolute value of the "global" clock. Slave nodes then determine their local clock o.set from that of the Grand Master via synchronisation events which occur multiple times per-second. The mechanism used for synchronising the clocks between the boards wirelessly makes use of specific hardware and a firmware protocol based on elements of the IEEE-1588 Precision Time Protocol (PTP). With the key requirement of the system being submillisecond-accurate clock synchronisation (as a basis for timestamping and camera triggering), automated testing is carried out to monitor the o.sets between each Slave and the Grand Master over time. A common strobe pulse is also sent to each unit for timestamping; the correlation between the timestamps of the di.erent units is used to validate the clock o.set results. Analysis of the automated test results show that the BabelFuse units are almost threemagnitudes more accurate than their requirement; clocks of the Slave and Grand Master units do not di.er by more than three microseconds over a running time of six hours and the mean clock o.set of Slaves to the Grand Master is less-than one microsecond. The common strobe pulse used to verify the clock o.set data yields a positive result with a maximum variation between units of less-than two microseconds and a mean value of less-than one microsecond. The camera triggering functionality is verified by connecting the trigger pulse output of each board to a four-channel digital oscilloscope and setting each unit to output a 100Hz periodic pulse with a common start time. The resulting waveform shows a maximum variation between the rising-edges of the pulses of approximately 39¥ìs, well below its target of 1ms.

Data fusion and tracking with multiple UAVs

This chapter describes decentralized data fusion algorithms for a team of multiple autonomous platforms. Decentralized data fusion (DDF) provides a useful basis with which to build upon for cooperative information gathering tasks for robotic teams operating in outdoor environments. Through the DDF algorithms, each platform can maintain a consistent global solution from which decisions may then be made. Comparisons will be made between the implementation of DDF using two probabilistic representations. The first, Gaussian estimates and the second Gaussian mixtures are compared using a common data set. The overall system design is detailed, providing insight into the overall complexity of implementing a robust DDF system for use in information gathering tasks in outdoor UAV applications.

Data fusion and matching by maximizing statistical dependencies

The core aim of machine learning is to make a computer program learn from the experience. Learning from data is usually defined as a task of learning regularities or patterns in data in order to extract useful information, or to learn the underlying concept. An important sub-field of machine learning is called multi-view learning where the task is to learn from multiple data sets or views describing the same underlying concept. A typical example of such scenario would be to study a biological concept using several biological measurements like gene expression, protein expression and metabolic profiles, or to classify web pages based on their content and the contents of their hyperlinks. In this thesis, novel problem formulations and methods for multi-view learning are presented. The contributions include a linear data fusion approach during exploratory data analysis, a new measure to evaluate different kinds of representations for textual data, and an extension of multi-view learning for novel scenarios where the correspondence of samples in the different views or data sets is not known in advance. In order to infer the one-to-one correspondence of samples between two views, a novel concept of multi-view matching is proposed. The matching algorithm is completely data-driven and is demonstrated in several applications such as matching of metabolites between humans and mice, and matching of sentences between documents in two languages.

An approach to implement data fusion techniques in wireless sensor networks using genetic machine learning algorithms

Wireless Sensor Networks (WSNs) can be used to monitor hazardous and inaccessible areas. In these situations, the power supply (e.g. battery) of each node cannot be easily replaced. One solution to deal with the limited capacity of current power supplies is to deploy a large number of sensor nodes, since the lifetime and dependability of the network will increase through cooperation among nodes. Applications on WSN may also have other concerns, such as meeting temporal deadlines on message transmissions and maximizing the quality of information. Data fusion is a well-known technique that can be useful for the enhancement of data quality and for the maximization of WSN lifetime. In this paper, we propose an approach that allows the implementation of parallel data fusion techniques in IEEE 802.15.4 networks. One of the main advantages of the proposed approach is that it enables a trade-off between different user-defined metrics through the use of a genetic machine learning algorithm. Simulations and field experiments performed in different communication scenarios highlight significant improvements when compared with, for instance, the Gur Game approach or the implementation of conventional periodic communication techniques over IEEE 802.15.4 networks. © 2013 Elsevier B.V. All rights reserved.

Multisensor data fusion for accurate modelling of mobile objects

In the last decade, multi-sensor data fusion has become a broadly demanded discipline to achieve advanced solutions that can be applied in many real world situations, either civil or military. In Defence,accurate detection of all target objects is fundamental to maintaining situational awareness, to locating threats in the battlefield and to identifying and protecting strategically own forces. Civil applications, such as traffic monitoring, have similar requirements in terms of object detection and reliable identification of incidents in order to ensure safety of road users. Thanks to the appropriate data fusion technique, we can give these systems the power to exploit automatically all relevant information from multiple sources to face for instance mission needs or assess daily supervision operations. This paper focuses on its application to active vehicle monitoring in a particular area of high density traffic, and how it is redirecting the research activities being carried out in the computer vision, signal processing and machine learning fields for improving the effectiveness of detection and tracking in ground surveillance scenarios in general. Specifically, our system proposes fusion of data at a feature level which is extracted from a video camera and a laser scanner. In addition, a stochastic-based tracking which introduces some particle filters into the model to deal with uncertainty due to occlusions and improve the previous detection output is presented in this paper. It has been shown that this computer vision tracker contributes to detect objects even under poor visual information. Finally, in the same way that humans are able to analyze both temporal and spatial relations among items in the scene to associate them a meaning, once the targets objects have been correctly detected and tracked, it is desired that machines can provide a trustworthy description of what is happening in the scene under surveillance. Accomplishing so ambitious task requires a machine learning-based hierarchic architecture able to extract and analyse behaviours at different abstraction levels. A real experimental testbed has been implemented for the evaluation of the proposed modular system. Such scenario is a closed circuit where real traffic situations can be simulated. First results have shown the strength of the proposed system.

Infrared image enhancement based on hybrid-domain consideration and data fusion methods

Au cours des dernières décennies, l’effort sur les applications de capteurs infrarouges a largement progressé dans le monde. Mais, une certaine difficulté demeure, en ce qui concerne le fait que les objets ne sont pas assez clairs ou ne peuvent pas toujours être distingués facilement dans l’image obtenue pour la scène observée. L’amélioration de l’image infrarouge a joué un rôle important dans le développement de technologies de la vision infrarouge de l’ordinateur, le traitement de l’image et les essais non destructifs, etc. Cette thèse traite de la question des techniques d’amélioration de l’image infrarouge en deux aspects, y compris le traitement d’une seule image infrarouge dans le domaine hybride espacefréquence, et la fusion d’images infrarouges et visibles employant la technique du nonsubsampled Contourlet transformer (NSCT). La fusion d’images peut être considérée comme étant la poursuite de l’exploration du modèle d’amélioration de l’image unique infrarouge, alors qu’il combine les images infrarouges et visibles en une seule image pour représenter et améliorer toutes les informations utiles et les caractéristiques des images sources, car une seule image ne pouvait contenir tous les renseignements pertinents ou disponibles en raison de restrictions découlant de tout capteur unique de l’imagerie. Nous examinons et faisons une enquête concernant le développement de techniques d’amélioration d’images infrarouges, et ensuite nous nous consacrons à l’amélioration de l’image unique infrarouge, et nous proposons un schéma d’amélioration de domaine hybride avec une méthode d’évaluation floue de seuil amélioré, qui permet d’obtenir une qualité d’image supérieure et améliore la perception visuelle humaine. Les techniques de fusion d’images infrarouges et visibles sont établies à l’aide de la mise en oeuvre d’une mise en registre précise des images sources acquises par différents capteurs. L’algorithme SURF-RANSAC est appliqué pour la mise en registre tout au long des travaux de recherche, ce qui conduit à des images mises en registre de façon très précise et des bénéfices accrus pour le traitement de fusion. Pour les questions de fusion d’images infrarouges et visibles, une série d’approches avancées et efficaces sont proposés. Une méthode standard de fusion à base de NSCT multi-canal est présente comme référence pour les approches de fusion proposées suivantes. Une approche conjointe de fusion, impliquant l’Adaptive-Gaussian NSCT et la transformée en ondelettes (Wavelet Transform, WT) est propose, ce qui conduit à des résultats de fusion qui sont meilleurs que ceux obtenus avec les méthodes non-adaptatives générales. Une approche de fusion basée sur le NSCT employant la détection comprime (CS, compressed sensing) et de la variation totale (TV) à des coefficients d’échantillons clairsemés et effectuant la reconstruction de coefficients fusionnés de façon précise est proposée, qui obtient de bien meilleurs résultats de fusion par le biais d’une pré-amélioration de l’image infrarouge et en diminuant les informations redondantes des coefficients de fusion. Une procédure de fusion basée sur le NSCT utilisant une technique de détection rapide de rétrécissement itératif comprimé (fast iterative-shrinking compressed sensing, FISCS) est proposée pour compresser les coefficients décomposés et reconstruire les coefficients fusionnés dans le processus de fusion, qui conduit à de meilleurs résultats plus rapidement et d’une manière efficace.

Dynamics of pattern writing and erasure in photorefractive lithium niobate for data storage applications

The present rate of technological advance continues to place significant demands on data storage devices. The sheer amount of digital data being generated each year along with consumer expectations, fuels these demands. At present, most digital data is stored magnetically, in the form of hard disk drives or on magnetic tape. The increase in areal density (AD) of magnetic hard disk drives over the past 50 years has been of the order of 100 million times, and current devices are storing data at ADs of the order of hundreds of gigabits per square inch. However, it has been known for some time that the progress in this form of data storage is approaching fundamental limits. The main limitation relates to the lower size limit that an individual bit can have for stable storage. Various techniques for overcoming these fundamental limits are currently the focus of considerable research effort. Most attempt to improve current data storage methods, or modify these slightly for higher density storage. Alternatively, three dimensional optical data storage is a promising field for the information storage needs of the future, offering very high density, high speed memory. There are two ways in which data may be recorded in a three dimensional optical medium; either bit-by-bit (similar in principle to an optical disc medium such as CD or DVD) or by using pages of bit data. Bit-by-bit techniques for three dimensional storage offer high density but are inherently slow due to the serial nature of data access. Page-based techniques, where a two-dimensional page of data bits is written in one write operation, can offer significantly higher data rates, due to their parallel nature. Holographic Data Storage (HDS) is one such page-oriented optical memory technique. This field of research has been active for several decades, but with few commercial products presently available. Another page-oriented optical memory technique involves recording pages of data as phase masks in a photorefractive medium. A photorefractive material is one by which the refractive index can be modified by light of the appropriate wavelength and intensity, and this property can be used to store information in these materials. In phase mask storage, two dimensional pages of data are recorded into a photorefractive crystal, as refractive index changes in the medium. A low-intensity readout beam propagating through the medium will have its intensity profile modified by these refractive index changes and a CCD camera can be used to monitor the readout beam, and thus read the stored data. The main aim of this research was to investigate data storage using phase masks in the photorefractive crystal, lithium niobate (LiNbO3). Firstly the experimental methods for storing the two dimensional pages of data (a set of vertical stripes of varying lengths) in the medium are presented. The laser beam used for writing, whose intensity profile is modified by an amplitudemask which contains a pattern of the information to be stored, illuminates the lithium niobate crystal and the photorefractive effect causes the patterns to be stored as refractive index changes in the medium. These patterns are read out non-destructively using a low intensity probe beam and a CCD camera. A common complication of information storage in photorefractive crystals is the issue of destructive readout. This is a problem particularly for holographic data storage, where the readout beam should be at the same wavelength as the beam used for writing. Since the charge carriers in the medium are still sensitive to the read light field, the readout beam erases the stored information. A method to avoid this is by using thermal fixing. Here the photorefractive medium is heated to temperatures above 150�C; this process forms an ionic grating in the medium. This ionic grating is insensitive to the readout beam and therefore the information is not erased during readout. A non-contact method for determining temperature change in a lithium niobate crystal is presented in this thesis. The temperature-dependent birefringent properties of the medium cause intensity oscillations to be observed for a beam propagating through the medium during a change in temperature. It is shown that each oscillation corresponds to a particular temperature change, and by counting the number of oscillations observed, the temperature change of the medium can be deduced. The presented technique for measuring temperature change could easily be applied to a situation where thermal fixing of data in a photorefractive medium is required. Furthermore, by using an expanded beam and monitoring the intensity oscillations over a wide region, it is shown that the temperature in various locations of the crystal can be monitored simultaneously. This technique could be used to deduce temperature gradients in the medium. It is shown that the three dimensional nature of the recording medium causes interesting degradation effects to occur when the patterns are written for a longer-than-optimal time. This degradation results in the splitting of the vertical stripes in the data pattern, and for long writing exposure times this process can result in the complete deterioration of the information in the medium. It is shown in that simply by using incoherent illumination, the original pattern can be recovered from the degraded state. The reason for the recovery is that the refractive index changes causing the degradation are of a smaller magnitude since they are induced by the write field components scattered from the written structures. During incoherent erasure, the lower magnitude refractive index changes are neutralised first, allowing the original pattern to be recovered. The degradation process is shown to be reversed during the recovery process, and a simple relationship is found relating the time at which particular features appear during degradation and recovery. A further outcome of this work is that the minimum stripe width of 30 ìm is required for accurate storage and recovery of the information in the medium, any size smaller than this results in incomplete recovery. The degradation and recovery process could be applied to an application in image scrambling or cryptography for optical information storage. A two dimensional numerical model based on the finite-difference beam propagation method (FD-BPM) is presented and used to gain insight into the pattern storage process. The model shows that the degradation of the patterns is due to the complicated path taken by the write beam as it propagates through the crystal, and in particular the scattering of this beam from the induced refractive index structures in the medium. The model indicates that the highest quality pattern storage would be achieved with a thin 0.5 mm medium; however this type of medium would also remove the degradation property of the patterns and the subsequent recovery process. To overcome the simplistic treatment of the refractive index change in the FD-BPM model, a fully three dimensional photorefractive model developed by Devaux is presented. This model shows significant insight into the pattern storage, particularly for the degradation and recovery process, and confirms the theory that the recovery of the degraded patterns is possible since the refractive index changes responsible for the degradation are of a smaller magnitude. Finally, detailed analysis of the pattern formation and degradation dynamics for periodic patterns of various periodicities is presented. It is shown that stripe widths in the write beam of greater than 150 ìm result in the formation of different types of refractive index changes, compared with the stripes of smaller widths. As a result, it is shown that the pattern storage method discussed in this thesis has an upper feature size limit of 150 ìm, for accurate and reliable pattern storage.

Rich probabilistic representations for bearing only decentralised data fusion

The aim of this paper is to demonstrate the validity of using Gaussian mixture models (GMM) for representing probabilistic distributions in a decentralised data fusion (DDF) framework. GMMs are a powerful and compact stochastic representation allowing efficient communication of feature properties in large scale decentralised sensor networks. It will be shown that GMMs provide a basis for analytical solutions to the update and prediction operations for general Bayesian filtering. Furthermore, a variant on the Covariance Intersect algorithm for Gaussian mixtures will be presented ensuring a conservative update for the fusion of correlated information between two nodes in the network. In addition, purely visual sensory data will be used to show that decentralised data fusion and tracking of non-Gaussian states observed by multiple autonomous vehicles is feasible.

Multi-sensor data fusion for UAV navigation during landing operations

This paper presents a practical framework to synthesize multi-sensor navigation information for localization of a rotary-wing unmanned aerial vehicle (RUAV) and estimation of unknown ship positions when the RUAV approaches the landing deck. The estimation performance of the visual tracking sensor can also be improved through integrated navigation. Three different sensors (inertial navigation, Global Positioning System, and visual tracking sensor) are utilized complementarily to perform the navigation tasks for the purpose of an automatic landing. An extended Kalman filter (EKF) is developed to fuse data from various navigation sensors to provide the reliable navigation information. The performance of the fusion algorithm has been evaluated using real ship motion data. Simulation results suggest that the proposed method can be used to construct a practical navigation system for a UAV-ship landing system.

Laser-radar data fusion with Gaussian Process Implicit Surfaces

This work considers the problem of building high-fidelity 3D representations of the environment from sensor data acquired by mobile robots. Multi-sensor data fusion allows for more complete and accurate representations, and for more reliable perception, especially when different sensing modalities are used. In this paper, we propose a thorough experimental analysis of the performance of 3D surface reconstruction from laser and mm-wave radar data using Gaussian Process Implicit Surfaces (GPIS), in a realistic field robotics scenario. We first analyse the performance of GPIS using raw laser data alone and raw radar data alone, respectively, with different choices of covariance matrices and different resolutions of the input data. We then evaluate and compare the performance of two different GPIS fusion approaches. The first, state-of-the-art approach directly fuses raw data from laser and radar. The alternative approach proposed in this paper first computes an initial estimate of the surface from each single source of data, and then fuses these two estimates. We show that this method outperforms the state of the art, especially in situations where the sensors react differently to the targets they perceive.