Neurobiologically inspired algorithms have been developed to continuously learn behavioral patterns at a variety of conceptual, spatial, and temporal levels. In this paper, we outline our use of these algorithms for situation awareness in the maritime domain. Our algorithms take real-time tracking information and learn motion pattern models on-the-fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance. The constantly refined models, resulting from concurrent incremental learning, are used to evaluate the behavior patterns of vessels based on their present motion states. At the event level, learning provides the capability to detect (and alert) upon anomalous behavior. At a higher (inter-event) level, learning enables predictions, over pre-defined time horizons, to be made about future vessel location. Predictions can also be used to alert on anomalous behavior. Learning is context-specific and occurs at multiple levels: for example, for individual vessels as well as classes of vessels. Features and performance of our learning system using recorded data are described

We describe a video surveillance system that detects abandoned packages automatically. In this system, multiple cameras locate objects in space and time despite occlusions and distracting lighting effects observed by subsets of the cameras. A multiple-state model of an abandoned package provides the ability to detect realistic abandoned package events. The paper outlines the system by describing the modules for camera view segmentation, object classification, view-object association, 3D object tracking, and finally detection of the event of a package being abandoned, which highlights object association using multiple cameras and the multiple-state abandoned package model.

In this paper, we show that an NPR M-channel filter bank with a diagonal system inserted between the analysis and synthesis filterbanks, with appropriately chosen analysis and synthesis filters, may be used to decompose an arbitrary FIR system of O(L) into M FIR complex subband components each of O(L/K), where K is the downsampling rate. This decomposition is at the expense of using complex arithmetic for the subband processing. The proposed filter bank structure has application in the identification and equalization of long channels, (such as those that occur in reverberative environments) where existing algorithms may be intractable. By reducing the order of the problem in the subbands, such problems become computationally feasible. The improved performance and reduced computational requirements afforded by the proposed method are verified using the acoustic echo cancellation (AEC) problem as an example.

The authors address the problem of generating representations of 3-D objects automatically from exploratory view sequences of unoccluded objects. In building the models, processed frames of a video sequence are clustered into view categories called aspects, which represent characteristic views of an object invariant to its apparent position, size, 2-D orientation, and limited foreshortening deformation. The aspects as well as the aspect transitions of a view sequence are used to build (and refine) the 3-D object representations online in the form of aspect-transition matrices. Recognition emerges as the hypothesis that has accumulated the maximum evidence at each moment. The 'winning' object continues to refine its representation until either the camera is redirected or another hypothesis accumulates greater evidence. This work concentrates on 3-D appearance modeling and succeeds under favorable viewing conditions by using simplified processes to segment objects from the scene and derive the spatial agreement of object features.>