In many vision problems, we want to infer two (or more) hidden factors which interact to produce our observations. We may want to disentangle illuminant and object colors in color constancy; rendering conditions from surface shape in shape-from-shading; face identity and head pose in face recognition; or font and letter class in character recognition. We refer to these two factors

Color is a useful feature for machine vision tasks. However, its effectiveness is often limited by the fact that the measured pixel values in a scene are influenced by both object surface reflectance properties and incident illumination. Color constancy algorithms attempt to compute color features which are invariant of the incident illumination by estimating the parameters of the global scene illumination and factoring out its effect. A number of recently developed algorithms utilize statistical methods to estimate the maximum likelihood values of the illumination parameters. This paper details the use of KL-divergence as a means of selecting estimated illumination parameter values. We provide experimental results demonstrating the usefulness of the KL-divergence technique for accurately estimating the global illumination parameters of real world images. 1

The ¨generic viewpointässumption states that an observer is not in a special position relative to the scene. It is commonly used to disqualify scene interpretations that assume special viewpoints, following a binary decision that the viewpoint was either generic or accidental. In this paper, we apply Bayesian statistics to quantify the probability of a view, and so derive a useful tool to estimate scene parameters. This approach may increase the scope and accuracy of scene estimates. It applies to a range of vision problems. We show shape from shading examples, where we rank shapes or reflectance functions in cases where these are otherwise unknown. The rankings agree with the perceived values.

Abstract not found

Color can be a useful feature in autonomous vehicle systems that are based on machine vision, for tasks such as obstacle detection, lane/road following, and recognition of miscellaneous scene objects. Unfortunately, few existing autonomous vehicle systems use color to its full extent, largely because color-based recognition in outdoor scenes is complicated, and existing color ma-chine vision techniques have not been shown to be e ective in realistic outdoor images. This paper presents a technique for achieving e ective real-time color recognition in outdoor scenes. The technique uses Multivariate Decision Trees for piecewise linear non-parametric func-tion approximation to learn the color of a target object from training samples, and then detects targets by classifying pixels based on the approximated function. The method has been success-fully tested in several domains, such as autonomous highway navigation, o-road navigation and target detection for unmanned military vehicles, in projects such as the U.S. National Automated Highway System (AHS) and the U.S. Defense Advanced Project Agency- Unmanned Ground Vehicle (DARPA-UGV). MDT-based systems have been used in stand-alone mode, as well as in conjunction with systems based on other sensor con gurations.

. We present an algorithm which uses information from both surface reflectance and illumination variation to solve for colour constancy. Most colour constancy algorithms assume that the illumination across a scene is constant, but this is very often not valid for real images. The method presented in this work identifies and removes the illumination variation, and in addition uses the variation to constrain the solution. The constraint is applied conjunctively to constraints found from surface reflectances. Thus the algorithm can provide good colour constancy when there is sufficient variation in surface reflectances, or sufficient illumination variation, or a combination of both. We present the results of running the algorithm on several real scenes, and the results are very encouraging. 1 Introduction Many colour constancy algorithms have been developed, but all are subject to quite restrictive assumptions and few have been tested on real images. Of the existing algorithm...

The main thrust of this paper is to investigate the multi-scale retinex (MSR) approach to image enhancement to explain the effect of the processing from a theoretical standpoint. This leads to a new algorithm with fewer arbitrary parameters that is more flexible, maintains colour fidelity, and still preserves the contrast-enhancement benefits of the original MSR method. To accomplish this we identify the explicit and implicit processing goals of MSR. By decoupling the MSR operations from one another, we build an algorithm composed of independent steps that separates out the issues of gamma adjustment, colour balance, dynamic range compression, and colour enhancement, which are all jumbled together in the original MSR method. We then extend MSR with colour constancy and chromaticity-preserving contrast enhancement.

This paper presents experiments designed to extend our understanding of color constancy. To perform our experiments, we have constructed and calibrated an experimental room where the illumination is under computer control. An apparatus in the room allows us to measure asymmetric color matches 10,15,18,26,45 under nearly natural viewing conditions. Our emphasis is on developing models that characterize the effect of the illuminant on color appearance

Abstract — The problem of colour constancy in the context of visual surveillance applications is addressed in this paper. We seek to reduce the variability of the surface colours inherent in the video of most indoor and outdoor surveillance scenarios to improve the robustness and reliability of applications which depend on reliable colour descriptions e.g. content retrieval. Two well-known colour constancy algorithms – the Grey-World and Gamut-Mapping – are applied to frame sequences containing significant variations in the colour temperature of the illuminant. We also consider the problem of automatically selecting a reference image, representative of the scene under the canonical illuminant. A quantitative evaluation of the performance of the colour constancy algorithms is undertaken. I.

This report describes an interactive approach to the computerized processing and interpretation of visual information. The objective is to facilitate the development of interactive applications that analyze and interpret video input. The approach is to transform video from raw sensory data into symbolic media events which can be incorporated into the design of event-driven programs.