Detecting salient cues through illumination-invariant color ratios

نویسندگان

  • Eduardo Todt
  • Carme Torras
چکیده

This work presents a novel technique for embedding color constancy into a saliency-based system for detecting potential landmarks in outdoor environments. Sincemultiscale color opponencies are among the ingredients determining saliency, the ideais to make such opponencies directly invariant to illumination variations, rather thanenforcing the invariance of colors themselves. The new technique is compared againstthe alternative approach of preprocessing the images with a color constancy procedurebefore entering the saliency system. The first procedure used in the experimentalcomparison is the well-known image conversion to chromaticity space, and the secondone is based on successive lighting intensity and illuminant color normalizations. Theproposed technique offers significant advantages over the preceding two ones since, ata lower computational cost, it exhibits higher stability in front of illumination variationsand even of slight viewpoint changes, resulting in a better correspondence of visualsaliency to potential landmark elements.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Time-lapse ratios of cone excitations in natural scenes

The illumination in natural environments varies through the day. Stable inferences about surface color might be supported by spatial ratios of cone excitations from the reflected light, but their invariance has been quantified only for global changes in illuminant spectrum. The aim here was to test their invariance under natural changes in both illumination spectrum and geometry, especially in ...

متن کامل

View and Illumination Invariant Object Classification Based on 3D Color Histogram Using Convolutional Neural Networks

Object classification is an important step in visual recognition and semantic analysis of visual content. In this paper, we propose a method for classification of objects that is invariant to illumination color, illumination direction and viewpoint based on 3D color histogram. A 3D color histogram of an image is represented as a 2D image, to capture the color composition while preserving the ne...

متن کامل

Shadow identification and classification using invariant color models

A novel approach to shadow detection is presented in this paper. The method is based on the use of invariant color models to identify and to classify shadows in digital images. The procedure is divided into two levels: first, shadow candidate regions are extracted; then, by using the invariant color features, shadow candidate pixels are classified as self shadow points or as cast shadow points....

متن کامل

Estimating Face orientation from Robust Detection of Salient Facial Structures

This paper addresses the problem of estimating face orientation from automatic detection of salient facial structures using learned robust features. Face imagettes are detected using color and described using a weighted sum of locally normalized Gaussian receptive fields. Robust face features are learned by clustering the Gaussian derivative responses within a training set face imagettes. The m...

متن کامل

Invariant cone-excitation ratios may predict transparency.

Cone-excitation ratios for pairs of surfaces are almost invariant under changes in illumination and offer a possible basis for color constancy [Proc. R. Soc. London Ser. B 257, 115 (1994)]. We extend this idea to the perception of transparency on the basis of the close analogy between the changes in color signals that occur for surfaces when the illumination changes and the changes in color sig...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Robotics and Autonomous Systems

دوره 48  شماره 

صفحات  -

تاریخ انتشار 2004