Improving the efficiency and accuracy of visual attention

Abstract

Visual attention is the cognitive process of selectively focusing on certain areas of a visual scene while ignoring the others. It is a desirable capability for intelligent video surveillance systems, as it allows them to control the aim of mobile cameras or to selectively process the most relevant parts of the captured images. This paper proposes an adaptation of a well-known biologicallyinspired visual attention model in order to increase its computational efficiency without sacrificing its accuracy, and shows that the latter can be further improved through a supervised training stage that fine-tunes the model to the particular application scope in which the system is being utilized. Experimental results and comparisons with previous visual attention techniques are shown and discussed.

Visual attention based on a joint perceptual space of color and brightness for improved video tracking

“…We have also estimated the seven coefficients in the above equation (s0, s1, (14) and (15). In turn, After having formulated the achromatic components Y 1 and Y 2 as bivariate functions of α and β, with the latter being normalized JND indices, it is essential to define the mapping between RGB color vectors and those normalized JND indices.…”

“…The Sobel edge detector has already been shown to be a computationally efficient alternative to the four Gabor filters applied in IKN [14,15]. In particular, let I t (x, y) be the gray-scale image corresponding to ψ t (x, y), with the brightness feature I being computed as (9).…”