The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Energy based detection measures sensor received signal strength (RSS) transmitted from a target. In this paper, we propose a new approach for estimating a moving target trajectory over a sensor field via energy based detections as an alternative to trilateration positioning or nonlinear estimation. In 2D case, possible target locations described by a RSS ratio from two sensors are approximated using...
This paper proposes an automatic semantic video content indexing and retrieval system based on fusing various low level visual and shape descriptors. Extracted features from region and sub-image blocks segmentation of video shots key-frames are described via IVSM signature (Image Vector Space Model) in order to have a compact and efficient description of the content. Static feature fusion based on...
Modern passive sonar systems employ a high degree of automation to produce a track-level sonar picture. Further refinement of the track-level information is normally performed by a human operator. Providing automated assistance would reduce the operator's workload and is a key enabler for semi- and fully automated sonar systems. The nature of the signals emitted by targets and of the underwater environment...
Feature ranking, due to its simplicity and computational efficiency, is a widely used dimensionality reduction technique, especially for large dataset where other methods are computationally too expensive. Conventionally feature ranking is done based on a single ranking criterion. One drawback associated with the conventional, single-criterion ranking is that the ranking order of the features is very...
Over the past several years, the NATO Undersea Research Centre has conducted extensive research in multisensor networks for undersea surveillance, culminating in the development of the DMHT tracker. In this paper, we discuss upgrades to this technology and its application to maritime surveillance.
A model for characterizing communications behaviors has been generalized to a probabilistic model for intentional behavior. Responsive actions are decomposed into measurement, inference, planning and control components) and are predicted as a function of the estimated capability, opportunity and intent of given agents to perform such component actions. This representational scheme enables the generation...
This paper presents our work which involves the application of a recursive Bayesian filter, the Gaussian mixture probability hypothesis density (GMPHD) filter, to a visual tracking problem. Foreground objects are detected using statistical background modeling to obtain measurements which are input into the filter. The GMPHD filter explicitly models the birth, survival and death of objects by managing...
This paper considers the use of the Hough transform image processing method applied to the problem of agent-based multi-platform, multi-sensor emitter geolocation. In this paper, improved geolocation is obtained through the fusion of three different types of measurement: angle of arrival, time difference of arrival and frequency difference of arrival. One of the main aims of this paper is to introduce...
Bayesian networks are useful for predicting future activities on the battlefield. Bayesian mathematics provides the most benefit in JDL fusion levels 2+, i.e. situation, threat, and performance assessment. However, these networks are exceedingly difficult for the average person to develop, much less a soldier in the middle of a war. We are in the process of developing a Bayesian modeling aid that...
In this paper, we propose a method of combining some interacting multiple model-extended Viterbi (IMM-EV) algorithms for target tracking. The objective of the proposed scheme is to take the maximum advantage of the combined strengths of some IMM-EV algorithms so as to achieve better performance and/or computational efficiency than the IMM and some tracking algorithms. Simulation results demonstrate...
Evidence gathered from different sources may have different reliabilities. Such reliability should be integrated into corresponding evidence model to make the evidence combination result rational. In this paper, a novel discounting strategy is developed for the integration of evidence's model and reliability. Dissimilar to the current one based on BPA, this strategy discounts the evidence's plausibility...
Current conceptual models for information fusion, including the JDL model do not consider the fact that their information sources are often based on different ontological bases. We therefore suggest that the Alignment functional process of the JDL model, which caters for space and time common referencing, be augmented with the notional aspect of common ontological alignment We illustrate this with...
Real radar data containing a small manoeuvring boat in sea clutter is processed using a grid based finite difference implementation of continuous-discrete filtering. Both two dimensional diffusion and four dimensional constant velocity models are implemented using Gaussian and Rayleigh sea clutter models. Superior performance is observed for the constant velocity model and significant sensitivity...
In March 2007, the Networked Underwater Warfare Technology Demonstration Project at Defence R&D Canada-Atlantic conducted an at-sea antisubmarine trial utilizing Net-centric warfare (NCW) constructs to demonstrate improved technologies for underwater warfare. User feedback was solicited during and after the trial for the purpose of documenting the manner in which the systems were used during the...
We propose a hybrid method of seeded region growing and region hue-area information fusion for object segmentation under patterned background. At first, image is segmented into many small regions according to hue homogeneity by seeded region growing algorithm, then background texture mode is discovered by the regions' hue-area information fusion, finally, the background texture is removed according...
Naive-Bayes and k-NN classifiers are two machine learning approaches for text classification. Rocchio is the classic method for text classification in information retrieval. Based on these three approaches and using classifier fusion methods, we propose a novel approach in text classification. Our approach is a supervised method, meaning that the list of categories should be defined and a set of training...
In this paper, we consider a parallel distributed detection network consisting of a fusion center and N sensors. We assume that the observations at different sensors are conditionally dependent, and optimize the system performance under the Neyman- Pearson criterion. Unlike previous papers dealing with the optimal N-P detection problem, we allow the sensor decision rules to be randomized, and obtain...
The wavelet-based contourlet transform (WBCT) is a new directional transform. This transform uses the wavelet transform and the directional filter bank (DFB) to obtain a multiscale and multidirection decomposition of image. The wavelet transform and the DFB are non-redundant and perfect reconstruction. So the WBCT can be regarded as a non-redundant version of the contourlet transform. A new image...
This paper presents the method for the detection and localization of moving targets in passive infrared (PIR) sensor networks in both indoor and outdoor settings. It reports our design and implementation of PIR sensor network, especially, we proposed a detection algorithm, which uses adaptive threshold with constant false alarm rate; and developed a localization algorithm using direction search in...
In this paper, a goal-driven net-enabled distributed data fusion system is described for CanCoastWatch (CCW) project. Multiple sensors are deployed and managed to achieve the goals of situation assessment using a net-enabled architecture. The local tracks reported by multiple sensors are first integrated into global tracks. Decision making is then performed on basic sub-goals that can be directly...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.