Natural contrast statistics and the selection of visual fixations

Abstract

In this paper we address the problem of visual surveillance, which we define as the problem of optimally extracting information from the visual scene with a fixating, foveated imaging system. We are explicitly concerned with eye/camera movement strategies that result in maximizing information extraction from the visual field. Here we demonstrate how a novel characterization of the contrast statistics of natural images can be used for selecting fixation points that minimize the total contrast uncertainty (entropy) of natural images. We demonstrate the performance of the algorithm and compare its performance to ground truth methods. The results show that our algorithm performs favorably in terms of both efficiency and its ability to find salient features in the image.

A new automated quality assessment algorithm for image fusion

“…Raj [18] pointed out that this parameter has little effect on the measured contrast because the mean luminance of most images are typically larger than 1 cd/m 2 .…”

“…Local contrast measures have received extensive study, see for example work by Peli, Lubin, Winkler, and other researchers [12,[16][17][18]. In our research we consider what might be called the three most popular contrast calculation methods: a local RMS contrast definition [18], a local band-limited contrast measure [16,17], and an isotropic local contrast measure [12].…”

“…Define I ¼ P N i¼1 x i I i , then the local contrast function of an input image I is defined as [18]:…”

A New Automated Quality Assessment Algorithm for Night Vision Image Fusion

“…Local contrast measures have received extensive study, see for example work by Peli, Winkler, and other researchers [14], [15], [16]. In our research we consider a local band-limited contrast measure [15].…”

Optimization of slant scanning in the systems of combined two-step location

“…В работах [11,12] предложена стратегия, согласно которой разли-чимость объектов определяется как результат макси-мизации декомпозиции методом анализа независимых компонент. В работе [13] среднеквадратическая вели-чина контраста оценивалась с использованием множе-ства фиксированных точек, заданных наблюдателем, наблюдающим за статическими изображения пейзажа. Сформированная при этом модель различимости ба-зировалась на минимизации суммарной контрастной энтропии.…”