In the field of scene analysis for computer vision, a trade-off must be found between the quality of the results expected and the amount of computer resources allocated for each task. Using an adaptive vision system provides a more flexible solution as its analysis strategy can be changed according to the information available concerning the execution context. The authors describe how to create and evaluate a visual attention system tailored for interacting with a computer vision system so that it adapts its processing according to the interest (or salience) of each element of the scene. The authors propose a new set of constraints called ‘PAIRED’ to evaluate the adequacy of a model with respect to its different applications. The authors then justify why dynamical systems are a good choice for visual attention simulation, and we show that predator-prey models provide good properties for simulating the dynamic competition between different kinds of information. They present different results (cross-correlation, Kullback-Leibler divergence, normalized scanpath salience) that demonstrate that, in spite of being fast and highly configurable, their results are as plausible as existing models designed for high biological fidelity.

Implementation and evaluation of a computational model of attention for computer vision

Innovations in computer vision technology continue to advance the applications and design of image processing and its influence on multimedia applications.Intelligent Computer Vision and Image Processing: Innovation, Application, and Design provides methods and research on various disciplines related to the science and technology of machines. This reference source is essential for academicians, researchers, and practitioners interested in the latest developments and innovations in computer science, education, and security.

Intelligent Computer Vision and Image Processing: Innovation, Application, and Design

This paper considers the conversion of the parametric Bezier surfaces, classically used in CAD-CAM, into patched of a class of non-spherical degree 4 algebraic surfaces called Dupin cyclides, and the definition of 3D triangle with circular edges on Dupin cyclides. Dupin cyclides was discovered by the French mathematician Pierre-Charles Dupin at the beginning of the 19th century. A Dupin cyclide has one parametric equation, two implicit equations, and a set of circular lines of curvature. The authors use the properties of these surfaces to prove that three families of circles meridian arcs, parallel arcs, and Villarceau circles can be computed on every Dupin cyclide. A geometric algorithm to compute these circles so that they define the edges of a 3D triangle on the Dupin cyclide is presented. Examples of conversions and 3D triangles are also presented to illustrate the proposed algorithms.

Construction of 3D Triangles on Dupin Cyclides

This paper presents a novel approach for region of interest (ROI) extraction in infrared images based on the one-bit transform. Potential interest regions in the infrared image are obtained by a target mask that is obtained using the one-bit transform in a local way. The histograms of the original image and the masked image are compared and the histogram region that remains unchanged is used to obtain an automated threshold value that is then utilized to detect the ROI in the infrared image. The proposed approach can be used as an effective pre-process for target detection and tracking algorithms in infrared images.

Region of Interest Extraction in Infrared Images Using One-Bit Transform

Infrared imaging guidance is a research hotspot in accurate terminal guidance field now. An idea on automatic extraction of region (ROI) of interest in infrared serial images is proposed in order to treat intelligently infrared serial images which are captured. The target detection algorithm of target is researched and the applying scene of the target detection algorithm is confirmed based on analysis for the features of infrared serial images. According to differences of detection algorithm for infrared serial images between static and dynamic scenes, the corresponding detection and extraction algorithm of ROI is discussed respectively. The algorithms are all simulated in real scene. A new stepwise approaching and recurring threshold search algorithm based on two-dimensional maximum entropy principle was proposed by studying recurring formulation optimized of two-dimensional maximum entropy in order to realize to detect target and extract ROI of serial images under complex background. The algorithm above realizes automatic extraction of ROI in Infrared serial images. The results improve the efficiency of accurate terminal guidance and they have good application value by practicing.

http://www.jsoftware.us/vol6/jsw0602-8.pdf

Research on Target Detection and Automatic Extraction of Region of Interest in Infrared Serial Images

Toruses and double spheres are particular cases of Dupin cyc lides. In this paper, we study the conversion of rational biquadratic B́ezier surfaces into Dupin cyclide patches. We give the condi ti s that the B́ezier surface should satisfy to be convertible, and present a new conversion algorithm to cons truct the torus or double sphere patch corresponding to a giv en Bézier surface, some conversion examples are illustrated an d commented.

Conversion of biquadratic rational Bézier surfaces into patches of particular Dupin cyclides: The torus and the double sphere

Les Cyclides de Dupin ont ete introduites en 1822 par le Mathematicien francais Charles Dupin. Ce sont des surfaces algebriques non spheriques de degre 4 dont les lignes de courbure sont des cercles. Elles sont interessantes pour la modelisation geometrique puisqu'elles possedent une equation parametrique et deux equations implicites. Une cyclide de Dupin peut etre obtenue

comme l'image d'un tore de revolution, d'un cone de revolution ou d'un cylindre de revolution par une inversion. Un tore de revolution possede, par construction, deux familles de cercles : les meridiens et les paralleles. Sur un tore a collier, il existe une troisieme famille de cercles : les cercles de Villarceau. Une inversion transformant un cercle en un cercle ou en une droite, le but de cet article est de construire, a partir de trois points de l'espace, un triangle non plan a bords circulaires sur un tore, chaque bord appartenant a l'une des trois familles de cercles precitees. En prenant differentes images de ce triangle par des inversions adequates, nous pouvons obtenir des triangles 3D a bords circulaires sur des cyclides de Dupin en anneau. A terme, nous comptons remplacer les triangles plans utilises dans les maillages par ces triangles 3D.

Construction de triangles rectangles 3D à bords circulaires passant par trois points donnés

Dupin cyclides are non-spherical algebraic surfaces of degree 4, discovered by the French mathematician Pierre-Charles Dupin at the beginning of the 19th century. A Dupin cyclide has a parametric equation and two implicit equations and circular lines of curvature. It can be defined as the image of a torus, a cone of revolution or a cylinder of revolution by an inversion. A torus has two families of circles : meridians and parallels. There is a third family of circles on a ring torus: Villarceau circles. As the image, by an inversion, of a circle is a circle or a straight line, there are three families of circles onto a Dupin cyclide too. The goal of this paper is to construct, onto a Dupin cyclide, 3D triangles with circular edges: a meridian arc, a parallel arc and a Villarceau circle arc.

Bertrand Belbis

Papers

Construction of 3D Triangles on Dupin Cyclides

Conversion of biquadratic rational Bézier surfaces into patches of particular Dupin cyclides: The torus and the double sphere

Construction de triangles rectangles 3D à bords circulaires passant par trois points donnés

An Algorithm to Construct 3D Triangles with Circular Edges