This paper describes a method for visual surveillance based on biologically motivated dynamic visual attention in video image sequences. Our system is based on the extraction and integration of local (pixels and spots) as well as global (objects) features. Our approach defines a method for the generation of an active attention focus on a dynamic scene for surveillance purposes. The system segments in accordance with a set of predefined features, including gray level, motion and shape features, giving raise to two classes of objects: vehicle and pedestrian. The solution proposed to the selective visual attention problem consists of decomposing the input images of an indefinite sequence of images into its moving objects, defining which of these elements are of the user's interest at a given moment, and keeping attention on those elements through time. Features extraction and integration are solved by incorporating mechanisms of charge and discharge-based on the permanency effect-, as well as mechanisms of lateral interaction. All these mechanisms have proved to be good enough to segment the scene into moving objects and background.

No abstract

A new computational model for active visual attention is introduced in this paper. The method extracts motion and shape features from video image sequences, and integrates these features to segment the input scene. The aim of this paper is to highlight the importance of the motion features present in our algorithms in the task of refining and/or enhancing scene segmentation in the method proposed. The estimation of these motion parameters is performed at each pixel of the input image by means of the accumulative computation method, using the so-called permanency memories. The paper shows some examples of how to use the ''motion presence'', ''module of the velocity'' and ''angle of the velocity'' motion features, all obtained from accumulative computation method, to adjust different scene segmentation outputs in this dynamic visual attention method.

A neural network model called lateral interaction in accumulative computation for detection of non-rigid objects from motion of any of their parts in indefinite sequences of images is presented. Some biological evidences inspire the model. After introducing the model, the complete multi-layer neural architecture is offered in this paper. The architecture consists of four layers that perform segmentation by gray level bands, accumulative charge computation, charge redistribution by gray level bands and moving object fusion. The lateral interaction in accumulative computation associated learning algorithm is also introduced. Some examples that explain the usefulness of the system we propose are shown at the end of this article. q

No abstract