Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997)

In support of the AFOSR program in Information Fusion, the CNS Technology Laboratory at Boston University is developing and applying neural models of image and signal processing, pattern learning and recognition, associative learning dynamics, and 3D visualization, to the domain of Information Fusion for Image Analysis in a geospatial context. Our research is focused by a challenge problem involving the emergence of a crisis in an urban environment, brought on by a terrorist attack or other man-made or natural disaster. We aim to develop methods aiding preparation and monitoring of the battlespace, deriving context from multiple sources of imagery (high-resolution visible and low-resolution hyperspectral) and signals (GMTI from moving vehicles, and ELINT from emitters). This context will serve as a foundation, in conjunction with existing knowledge nets, for exploring neural methods in higher level information fusion supporting situation assessment and creation of a common operating picture (COP).

There is an obvious need to be able to integrate both linguistic-based and stochastic-based input information in data fusion. In particular, this need is critical in addressing problems of track association, including cyber-state intrusions. This paper treats this issue through a new insight into how three apparently distinct mathematical tools can be combined: "boolean relational event algebra" (BREA), "one point random set coverage representations of fuzzy sets" (OPRSC), and "complexity-reducing algorithm for near optimal fusion" (CRANOF).

Bayesian networks are an attractive modeling tool for human sensing, as they combine an intuitive graphical representation with efficient algorithms for inference and learning. Temporal fusion of multiple sensors can be efficiently formulated using dynamic Bayesian networks (DBNs) which allow the power of statistical inference and learning to be combined with contextual knowledge of the problem. Unfortunately, simple learning methods can cause such appealing models to fail when the data exhibits complex behavior We first demonstrate how boosted parameter learning could be used to improve the performance of Bayesian network classifiers for complex multimodal inference problems. As an example we apply the framework to the problem of audiovisual speaker detection in an interactive environment using "off-the-shelf" visual and audio sensors (face, skin, texture, mouth motion, and silence detectors). We then introduce a boosted structure learning algorithm. Given labeled data, our algorithm modifies both the network structure and parameters so as to improve classification accuracy. We compare its performance to both standard structure learning and boosted parameter learning. We present results for speaker detection and for datasets from the UCI repository.

In intensive agricultural regions, accurate assessment of the spatial and temporal variation of winter vegetation covering is a key indicator of water transfer processes, essential for controlling land management and helping local decision making. Spatial prediction modeling of winter bare soils is complex and it is necessary to introduce uncertainty in modeling land use and cover changes, especially as high spatial and temporal variability are encountered. Dempster's fusion rule is used in the present study to spatially predict the location of winter bare fields for the next season on a watershed located in an intensive agricultural region. It expresses the model as a function of past-observed bare soils, field size, distance from farm buildings, agro-environmental action, and production quotas per ha. The model well predicted the presence of bare soils on 4/5 of the total area. The spatial distribution of misrepresented fields is a good indicator for identifying change factors.

The paper combines IMM and JPDA for tracking of multiple possibly maneuvering targets in case of clutter and possibly missed measurements while avoiding sensitivity to track coalescence. The effectiveness of the filter is illustrated through Monte Carlo simulations.

Conference proceedings front matter may contain various advertisements, welcome messages, committee or program information, and other miscellaneous conference information. This may in some cases also include the cover art, table of contents, copyright statements, title-page or half title-pages, blank pages, venue maps or other general information relating to the conference that was part of the original conference proceedings.

The paper describes a novel integrated sensor validation and fusion scheme based on the Nadaraya-Watson statistical estimator. The basis of the sensor validation scheme is that observations used to implement the estimator are obtained from valid sensor readings. Pattern matching techniques are used to relate a measurement vector that is not consistent with the training data to the closest a-priori observation. Defective sensor(s) can be identified and 'masked', and the estimator reconfigured to compute the estimate using data from the remaining sensors. Test results are provided for a range of typical fault conditions using an array of thick film pH sensors. The new algorithm is shown to reliably detect and compensate for bias errors, spike errors, hardover faults, drift faults and erratic operation, affecting up to three of the five sensors in the array. The fused result is more accurate than the single best sensor.

Image fusion and information extraction from multiple spacecraft can occur after each image is sampled and digitized. A more tantalizing, but difficult, approach would be to optically phase multiple spacecraft flying in formation. Phasing of multiple spacecraft allows for coherent addition of imagery resulting in an optical system with a synthetic aperture as large as distance between the spacecraft. Thus, space based optical imaging systems approaching 100's of meters could theoretically be achieved; ultimately allowing for resolution of the solar disks of stars and resolution of extra-solar planets around these stars. The methods and techniques for systems of this type, as well as a number of optical testbeds for proof of principle and validation of the methods are currently under study at NASA Goddard Space Flight Center. In this work we give an overview of the underlying principles, the technology required and the state of development of the various testbeds involved.

In this paper, a new Bayes fusion algorithm with the Parzen window method, which introduces the non-parameter estimation method of partition recognition into traditional Bayes fusion criterion, is propose. During the process of fusion, which is a repetitious and iterative process, conditional probability density is continuously modified and learned using the Parzen window method, and the global decision is obtained at the fusion center under the bayes decision criterion. In the practical application, the method has been successfully applied into the temperature fault detection and diagnosis system of hydroelectric simulation system of J. Fengman. The analysis of data indicates that the improved algorithm takes precedence over the traditional Bayes criterion.

Many information fusion applications especially in military domains are often characterized as a high degree of complexity due to three challenges: 1) data are often acquired from sensors of different modalities and with different degrees of uncertainty; 2) decision must be made quickly; and 3) the world situation as well as sensory observations evolve over time. In this paper, we propose a dynamic active information fusion framework that can simultaneously address the three challenges. The proposed framework is based on Dynamic Bayesian Networks (DBNs) with an embedded active sensor controller. The DBNs provide a coherent and unified hierarchical probabilistic framework to represent, integrate and infer corrupted dynamic sensory information of different modalities. The sensor controller allows it to actively select and invoke a subset of sensors to produce the sensory information that is most relevant to the current task with reasonable time and limited resources. The proposed framework can therefore provide dynamic, purposive and sufficing information fusion particularly well suited to applications where the decision must be made from dynamically available information of diverse and disparate sources. To verify the proposed framework, we use target recognition problem as a proof-of-concept. The experimental results demonstrate the utility of the proposed framework in efficiently modeling and inferring dynamic events.