Color Constancy

Relative spectral reflectance is an illumination invarient image feature that is related to many ecological phenomena that are difficult to measure, such as plant CO2 uptake. We describe a procedure to estimate the relative spectral reflectance of known subject using ...

The gamut mapping algorithm is one of the most promising methods to achieve computational color constancy. However, so far, gamut mapping algorithms are restricted to the use of pixel values to estimate the illuminant. Therefore, in this paper, gamut mapping is extended to incorporate the statistical nature of images. It is analytically shown that the proposed gamut mapping framework is able to include any linear filter output. The main focus is on the local n-jet describing the derivative structure of an image. It is shown that derivatives have the advantage over pixel values to be invariant to disturbing effects (i.e. deviations of the diagonal model) such as saturated colors and diffuse light. Further, as the n-jet based gamut mapping has the ability to use more information than pixel values alone, the combination of these algorithms are more stable than the regular gamut mapping algorithm. Different methods of combining are proposed.

Color constancy is the ability to measure colors of objects independent of the color of the light source. A well-known color constancy method is based on the Grey-World assumption which assumes that the average reflectance of surfaces in the world is achromatic. In this article, we propose a new hypothesis for color constancy namely the Grey-Edge hypothesis, which assumes that the average edge difference in a scene is achromatic. Based on this hypothesis, we propose an algorithm for color constancy. Contrary to existing color constancy algorithms, which are computed from the zero-order structure of images, our method is based on the derivative structure of images. Furthermore, we propose a framework which unifies a variety of known (Grey-World, max-RGB, Minkowski norm) and the newly proposed Grey-Edge and higher-order Grey-Edge algorithms. The quality of the various instantiations of the framework is tested and compared to the state-of-the-art color constancy methods on two large data sets of images recording objects under a large number of different light sources. The experiments show that the proposed color constancy algorithms obtain comparable results as the state-of-the-art color constancy methods with the merit of being computationally more efficient.

Skin detection plays an important role in a wide range of image processing applications ranging from face detection, face tracking, gesture analysis, content-based image retrieval systems and to various human computer interaction domains. Recently, skin detection methodologies based on skin-color information as a cue has gained much attention as skin-color provides computationally effective yet, robust information against rotations, scaling and partial occlusions. Skin detection using color information can be a challenging task as the skin appearance in images is affected by various factors such as illumination, background, camera characteristics, and ethnicity. Numerous techniques are presented in literature for skin detection using color. In this paper, we provide a critical up-to-date review of the various skin modeling and classification strategies based on color information in the visual spectrum. The review is divided into three different categories: first, we present the various color spaces used for skin modeling and detection. Second, we present different skin modeling and classification approaches. However, many of these works are limited in performance due to real-world conditions such as illumination and viewing conditions. To cope up with the rapidly changing illumination conditions, illumination adaptation techniques are applied along with skin-color detection. Third, we present various approaches that use skin-color constancy and dynamic adaptation techniques to improve the skin detection performance in dynamically changing illumination and environmental conditions. Wherever available, we also indicate the various factors under which the skin detection techniques perform well. ᭧

A well-known color constancy method is based on the Grey-World assumption i.e. the average reflectance of surfaces in the world is achromatic. In this article we propose a new hypothesis for color constancy, namely the Grey-Edge hypothesis assuming that the average edge difference in a scene is achromatic. Based on this hypothesis, we propose an algorithm for color constancy.

In u study of improving the color constancy of object colors, the spectral rejectances of the eight CIE color-rendering test samples (Munsell painted papers) were chosen as reference reflectance distributions. Many other distributions, more highly structured than those of the reference set, were synthesized by computer so as to be rendered by illuminant D6s at the chromaticity at which one or another of the CIE-Munsell samples is rendered by Ds5. The chromuticities, at which each of the synthesized rejectances is rendered by each of 30 additional illuminants, dejine both dominant wavelength and chroma vector for the resulting 50,000 illuminant-sample combinations. For most natural illuminants, and for present commercial lamplights, color constancy is maximized by synthesizing each sample reflectance from three relatively nurrow components, 5 0 4 0 nm at half height, peaking at wavelengths near 450 nm, 530 nm, and 610 nm.

Skin detection plays an important role in a wide range of image processing applications ranging from face detection, face tracking, gesture analysis, content-based image retrieval systems and to various human computer interaction domains. Recently, skin detection methodologies based on skin-color information as a cue has gained much attention as skin-color provides computationally effective yet, robust information against rotations, scaling and partial occlusions. Skin detection using color information can be a challenging task as the skin appearance in images is affected by various factors such as illumination, background, camera characteristics, and ethnicity. Numerous techniques are presented in literature for skin detection using color. In this paper, we provide a critical up-to-date review of the various skin modeling and classification strategies based on color information in the visual spectrum. The review is divided into three different categories: first, we present the various color spaces used for skin modeling and detection. Second, we present different skin modeling and classification approaches. However, many of these works are limited in performance due to real-world conditions such as illumination and viewing conditions. To cope up with the rapidly changing illumination conditions, illumination adaptation techniques are applied along with skin-color detection. Third, we present various approaches that use skin-color constancy and dynamic adaptation techniques to improve the skin detection performance in dynamically changing illumination and environmental conditions. Wherever available, we also indicate the various factors under which the skin detection techniques perform well. ᭧

A quarter of a century ago, the first systematic behavioral experiments were performed to clarify the nature of color constancy—the effect whereby the perceived color of a surface remains constant despite changes in the spectrum of the illumination. At about the same time, new models of color constancy appeared, along with physiological data on cortical mechanisms and photographic colorimetric measurements of natural scenes. Since then, as this review shows, there have been many advances. The theoretical requirements for constancy have been better delineated and the range of experimental techniques has been greatly expanded; novel invariant properties of images and a variety of neural mechanisms have been identified; and increasing recognition has been given to the relevance of natural surfaces and scenes as laboratory stimuli. Even so, there remain many theoretical and experimental challenges, not least to develop an account of color constancy that goes beyond deterministic and relatively simple laboratory stimuli and instead deals with the intrinsically variable nature of surfaces and illuminations present in the natural world.

Computational color constancy is a fundamental prerequisite for many computer vision applications. This paper presents a survey of many recent developments and state-of-theart methods. Several criteria are proposed that are used to assess the approaches. A taxonomy of existing algorithms is proposed and methods are separated in three groups: static methods, gamut-based methods and learning-based methods. Further, the experimental setup is discussed including an overview of publicly available data sets. Finally, various freely available methods, of which some are considered to be state-of-the-art, are evaluated on two data sets.

Human color constancy has been studied for over 100 years, and there is extensive experimental data for the case where a spatially diffuse light source illuminates a set of flat matte surfaces. In natural viewing, however, three-dimensional objects are viewed in three-dimensional scenes. Little is known about color constancy for three-dimensional objects. We used a forced-choice task to measure the achromatic chromaticity of matte disks, matte spheres, and glossy spheres. In all cases, the test stimuli were viewed in the context of stereoscopically viewed graphics simulations of three-dimensional scenes, and we varied the scene illuminant. We studied conditions both where all cues were consistent with the simulated illuminant change (consistent-cue conditions) and where local contrast was silenced as a cue (reduced-cue conditions). We computed constancy indices from the achromatic chromaticities. To first order, constancy was similar for the three test object types. There was, however, a reliable interaction between test object type and cue condition. In the consistent-cue conditions, constancy tended to be best for the matte disks, while in the reduced-cue conditions constancy was best for the spheres. The presence of this interaction presents an important challenge for theorists who seek to generalize models that account for constancy for flat tests to the more general case of three-dimensional objects.

In the present study we used a hue scaling technique to examine human color constancy performance in simulated three-dimensional scenes. These scenes contained objects of various shape and materials and a matte test patch at the center of the scene.

This paper proposes a solution to the spectral color constancy problem. The method is based on a statistical model for the surface reflectance spectrum and applies a maximum entropy constraint. Unlike prior methods based on linear models, the solution process does not require a set of basis functions to be defined, nor does it require a database of spectra to be specified in advance. Experiments on simulated and real data show that spectral estimation using the maximum entropy approach is feasible and performs similarly to existing spectral methods in spite of the lower level of a priori information required.

Color constancy algorithms are often evaluated by using a distance measure that is based on mathematical principles, such as the angular error. However, it is unknown whether these distance measures correlate to human vision. Therefore, the main goal of our paper is to analyze the correlation between several performance measures and the quality, obtained by using psychophysical experiments, of the output images generated by various color constancy algorithms. Subsequent issues that are addressed are the distribution of performance measures, suggesting additional and alternative information that can be provided to summarize the performance over a large set of images, and the perceptual significance of obtained improvements, i.e., the improvement that should be obtained before the difference becomes noticeable to a human observer.

Estimates of the frequency of metameric surfaces, which appear the same to the eye under one illuminant but different under another, were obtained from 50 hyperspectral images of natural scenes. The degree of metamerism was specified with respect to a color-difference measure after allowing for full chromatic adaptation. The relative frequency of metameric pairs of surfaces, expressed as a proportion of all pairs of surfaces in a scene, was very low. Depending on the criterion degree of metamerism, it ranged from about 10 −6 to 10 −4 for the largest illuminant change tested, which was from a daylight of correlated color temperature 25,000 K to one of 4000 K. But, given pairs of surfaces that were indistinguishable under one of these illuminants, the conditional relative frequency of metamerism was much higher, from about 10 −2 to 10 −1 , sufficiently large to affect visual inferences about material identity.

In this study human color constancy was tested for two-dimensional (2D) and three-dimensional (3D) setups with real objects and lights. Four different illuminant changes, a natural selection task and a wide choice of target colors were used. We found that color constancy was better when the target color was learned as a 3D object in a cue-rich 3D scene than in a 2D setup. This improvement was independent of the target color and the illuminant change. We were not able to find any evidence that frequently experienced illuminant changes are better compensated for than unusual ones. Normalizing individual color constancy hit rates by the corresponding color memory hit rates yields a color constancy index, which is indicative of observers' true ability to compensate for illuminant changes.

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection, (2) the role of the illuminance component of a color space, (3) the appropriate pixel based skin color modeling technique and finally, (4) the effect of color constancy algorithms on color based skin classification. The comprehensive color space and skin color modeling evaluation will help in the selection of the best combinations for skin detection. Nine skin modeling approaches (AdaBoost, Bayesian network, J48, Multilayer Perceptron, Naive Bayesian, Random Forest, RBF network, SVM and the histogram approach of Jones and Rehg ) in six color spaces (IHLS, HSI, RGB, normalized RGB, YCbCr and CIELAB) with the presence or absence of the illuminance component are compared and evaluated. Moreover, the impact of five color constancy algorithms on skin detection is reported. Results on a database of 8991 images with manually annotated pixel-level ground truth show that (1) the cylindrical color spaces outperform other color spaces, (2) the absence of the illuminance component decreases performance, (3) the selection of an appropriate skin color modeling approach is important and that the tree based classifiers (Random forest, J48) are well suited to pixel based skin detection. As a best combination, the Random Forest combined with the cylindrical color spaces, while keeping the illumi-Email addresses: [email protected] (Rehanullah Khan), [email protected] (Allan Hanbury), [email protected] (Julian Stöttinger), [email protected] (Abdul Bais) nance component outperforms other combinations, and (4) the usage of color constancy algorithms can improve skin detection performance.

Naïve observers viewed a sequence of colored "Mondrian" patterns, simulated on a color monitor. Each pattern was presented twice in succession, first under one daylight illuminant of color temperature either 16000 K or 4000 K, and then under the other, to test for color constancy. Observers compared the central square of the pattern across illuminants, either rating it for sameness of material appearance, or for sameness of hue and saturation, or judging an objective property, that is, whether its change of color originated from a change in material or only in illumination. Average color-constancy indices were high for materialappearance ratings and binary judgments of origin, and low for hue-saturation ratings.

We address the problem of contrast enhancement for color images. Our method to enhance images is inspired from the retinex theory. We try to estimate the illumination and separate it from the reflectance component of an image. We use denoising techniques to estimate the illumination and while doing so achieve color constancy. We enhance only the illumination component of the image. The parameters for enhancement are estimated automatically. This enhanced illumination is then multiplied with the reflectance to obtain enhanced images with better contrast. We provide validation of our color constancy approach and show performance better than state-of-the-art approaches. We also show "visually better" results while comparing our enhancement results with those from other enhancement techniques and from commercial software packages. We perform statistical analysis of our results and quantitatively show that our approach produces effective image enhancement. This is validated by ratings from human observers.

The European Space Agency (ESA) defines as Earth observation (EO) Level 2 information product a single-date multi-spectral (MS) image corrected for atmospheric, adjacency and topographic effects, stacked with its data-derived scene classification map (SCM), whose thematic map legend includes quality layers cloud and cloud-shadow. ESA EO Level 2 product generation is an inherently ill-posed computer vision (CV) problem never accomplished to date in operating mode by any EO data provider at the ground segment. Herein, it is considered: (I) necessary not sufficient pre-condition for the yet-unaccomplished dependent problems of semantic content-based image retrieval (SCBIR) and semantics-enabled information/knowledge discovery (SEIKD) in multi-source EO big data cubes. (II) Synonym of EO Analysis Ready Data (ARD) format. (III) Equivalent to a horizontal policy for background developments in Space Economy 4.0. In compliance with the GEO-CEOS Quality Assurance Framework for EO Calibration/Validation guidelines, to contribute toward filling an analytic and pragmatic information gap from multi-sensor EO big data to timely, comprehensive and operational EO value-adding information products and services, this work presents an innovative AutoCloud+ CV software toolbox for cloud and cloud-shadow quality layer detection in ESA EO Level 2 product. In vision, spatial information dominates color information. Inspired by this true-fact, the inherently ill-posed AutoCloud+ CV software was conditioned, designed and implemented to be “universal”, meaning fully automated (no human-machine interaction is required), near real-time, robust to changes in input data and scalable to changes in MS imaging sensor’s spatial and spectral resolution specifications.

The most widely used color-difference formulas are based on color-difference data obtained under D65 illumination or similar and for a 10°visual field; i.e., these formulas hold true for the CIE 1964 observer adapted to D65 illuminant. This work considers the psychometric color-vision model based on the Optical Society of America-Uniform Color Scales (OSA-UCS) system previously published by the first author [J. Opt. Soc. Am. A 21, 677 (2004); Color Res. Appl. 30, 31 (2005)] with the additional hypothesis that complete illuminant adaptation with perfect color constancy exists in the visual evaluation of color differences. In this way a computational procedure is defined for color conversion between different illuminant adaptations, which is an alternative to the current chromatic adaptation transforms. This color conversion allows the passage between different observers, e.g., CIE 1964 and CIE 1931. An application of this color conversion is here made in the color-difference evaluation for any observer and in any illuminant adaptation: these transformations convert tristimulus values related to any observer and illuminant adaptation to those related to the observer and illuminant adaptation of the definition of the color-difference formulas, i.e., to the CIE 1964 observer adapted to the D65 illuminant, and then the known colordifference formulas can be applied. The adaptations to the illuminants A, C, F11, D50, Planckian and daylight at any color temperature and for CIE 1931 and CIE 1964 observers are considered as examples, and all the corresponding transformations are given for practical use. RMS ¼ 0:030; t 12 ðtÞ ¼ 0:7872 − 2:0294t þ 1:4156t 2 ; RMS ¼ 0:031; t 13 ðtÞ ¼ −0:16 þ ð−1:6922 þ 13:0688t − 0:9485t 2 Þ −1 ; RMS ¼ 0:009; t 21 ðtÞ ¼ −0:7329 þ 1:9264t − 1:2103t 2 ; RMS ¼ 0:019; t 22 ðtÞ ¼ 1:6334 − 1:8833t þ 1:2583t 2 ; RMS ¼ 0:037; t 23 ðtÞ ¼ −0:04 þ ð−4:1279 þ 26:1611t − 2:1565t 2 Þ −1 ; RMS ¼ 0:008; t 31 ðtÞ ¼ −0:08 þ ð0:8129 þ 15:5929t − 7:1356t 2 Þ −1 ; RMS ¼ 0:012; t 32 ðtÞ ¼ 0:08 − ð1:1344 þ 18:6290t − 7:9995t 2 Þ −1 ; RMS ¼ 0:016; t 33 ðtÞ ¼ 0:21 þ ð−0:5269 þ 3:2939t − 0:6501t 2 Þ −1 ; RMS ¼ 0:045;

Performance measures for quantifying human color constancy and computational color constancy are very different. The former relate to measurements on individual object colors whereas the latter relate to the accuracy of the estimated illuminant. To bridge this gap, we propose a psychophysical method in which observers judge the global color fidelity of the visual scene rendered under different illuminants. In each experimental trial, the scene is rendered under three illuminants, two chromatic test illuminants and one neutral reference illuminant. Observers indicate which of the two test illuminants leads to better color fidelity in comparison to the reference illuminant. Here we study multicolor scenes with chromatic distributions that are differently oriented in color space, while having the same average chromaticity. We show that when these distributions are rendered under colored illumination they lead to different perceptual estimates of the color fidelity.

Color constancy is the ability to assign a constant color to an object independent of changes in illumination. Color constancy is achieved by taking context information into account. Previous approaches that have used matching paradigms to quantify color constancy found degrees of constancy between 20% and 80%. Here, we studied color constancy in a color-naming task under different conditions of surround illumination and patch size. Observers categorized more than 400 patches for each illumination condition. This allows one to overcome inherent limitations in color naming and to study the changes in color categories under illumination changes. When small central test patches with a full context illumination were categorized, observers followed the illumination shift almost completely, showing a high degree of constancy (99%). Reducing the available context information or increasing the patch size decreased the degree of constancy to about 50%. Moderate degrees of constancy (66%) occurred even when the test patches were never viewed simultaneously but only in temporal alternation with the illumination. Boundaries between color categories were largely stable within and across observers under neutral illumination. Under changing illumination, there were small but systematic variations in the color category boundaries. Color category boundaries tended to rotate away from the illumination color. This variation was largest under full context conditions where highest degrees of color constancy were obtained.

Automatic focusing is very important to high-quality image acquisition for digital still camera system. This paper will propose a new automatic focusing method using skincolor face detection to automatically determine focusing area. In order to overcome the influence of color temperature on the face detection method, this paper proposes a new automatic white balance method by learning color temperature curve with a statistical method. The method compensates color shifts of images by locating a set of compensation gains from the trained color temperature regression curve. A comparative setup of experiments is built to verify the effectiveness of the proposed method. Controlled experimental factors include light source, object distance and initial lens position. Modulation transfer function of images is applied to objectively evaluate the image quality before and after the new automatic focusing method. Experimental results show our method has high success rate of face localization, and effectively achieves automatic focusing.

Adaptation to a steady background has a profound effect on both color appearance and discrimination. We determined the temporal characteristics of chromatic adaptation for appearance and discrimination along different color directions. Subjects were adapted to a large uniform background made up of a CRT screen and a 45 × 64 deg wall, illuminated by computer controlled lamps. After an instant change in background color along a red-green or blue-yellow color axes, we measured thresholds for the detection of increments along the same axes at fixed times between 25 ms and 121 s. Analogously, color appearance was determined using achromatic matching. Three components of adaptation could be identified by their temporal characteristics. A slow exponential time course of adaptation with a half-life of about 20 seconds was common to appearance and discrimination. A faster component with a half-life of 40 -70 ms -probably due to photoreceptor adaptation -was also common to both. Exclusive for color appearance, there was a third, extremely rapid mechanism with a half-life faster than 10ms. This instantaneous process explained more than 50% of total adaptation for color appearance and could be shown to act in a multiplicative manner. We conclude that this instantaneous adaptation mechanism for color appearance is situated at a later processing stage, after mechanisms common to appearance and discrimination, and is based on multiplicative spatial interactions rather than on local, temporal adaptational processes. Color appearance, and thus color constancy, seems to be determined in large part by cortical computations.

This paper presents a unified approach to crowd segmentation. A global solution is generated using an Expectation Maximization framework. Initially, a head and shoulder detector is used to nominate an exhaustive set of person locations and these form the person hypotheses. The image is then partitioned into a grid of small patches which are each assigned to one of the person hypotheses. A key idea of this paper is that while whole body monolithic person detectors can fail due to occlusion, a partial response to such a detector can be used to evaluate the likelihood of a single patch being assigned to a hypothesis. This captures local appearance information without having to learn specific appearance models. The likelihood of a pair of patches being assigned to a person hypothesis is evaluated based on low level image features such as uniform motion fields and color constancy. During the E-step, the single and pairwise likelihoods are used to compute a globally optimal set of assignments of patches to hypotheses. In the M-step, parameters which enforce global consistency of assignments are estimated. This can be viewed as a form of occlusion reasoning. The final assignment of patches to hypotheses constitutes a segmentation of the crowd. The resulting system provides a global solution that does not require background modeling and is robust with respect to clutter and partial occlusion.

Charge-Coupled Device (CCD) cameras are widely used imaging sensors in computer vision systems. Many photometric algorithms, such as shape from shading, color constancy, and photometric stereo, implicitly assume that the image intensity is proportional to scene radiance. The actual image measurements deviate significantly from this assumption since the transformation from scene radiance to image intensity is non-linear and is a function of various factors including: noise sources in the CCD sensor, as well as various transformations occurring in the camera including: white balancing, gamma correction and automatic gain control. This paper illustrates how careful modelling of the error sources and the various processing steps enable us to accurately estimate the "response function", the inverse mapping from image measurements to scene radiance for a given camera exposure setting. It is shown that the estimation algorithm outperforms the calibration procedures known to us in terms of reduced bias and variance. Further, we demonstrate how the error modelling helps us to obtain uncertainty estimates of the camera irradiance value. The power of this uncertainty modeling is illustrated by a vision task involving High Dynamic Range image generation followed by change detection. Change can be detected reliably even in situation where the two images (the reference scene image and the current image) are taken several hours apart.

Full spectra allow the generation of a physically correct rendering of a scene under different lighting conditions. In this paper we devise a tool to augment a palette of given lights and material reflectances with constructed spectra yielding specified colors or spectral properties such as metamerism or objective color constancy. We utilize this to emphasize or hide parts of a scene by matching or differentiating colors under different illuminations. These color criteria are expressed as a quadratic programming problem, which may be solved with positivity constraints. Further, we characterize full spectra of lights, surfaces, and transmissive materials in an efficient linear subspace model by forming eigenvectors of sets of spectra and transform them to an intermediate space in which spectral interactions reduce to simple component-wise multiplications during rendering. The proposed method enhances the user's freedom in designing photo-realistic scenes and helps to create expressive visualizations. A key application of our technique is to use specific spectral lighting to scale the visual complexity of a scene by controlling visibility of texture details in surface graphics or material details in volume rendering.

Computational color constancy is a fundamental prerequisite for many computer vision applications. This paper presents a survey of many recent developments and state-of-theart methods. Several criteria are proposed that are used to assess the approaches. A taxonomy of existing algorithms is proposed and methods are separated in three groups: static methods, gamut-based methods and learning-based methods. Further, the experimental setup is discussed including an overview of publicly available data sets. Finally, various freely available methods, of which some are considered to be state-of-the-art, are evaluated on two data sets.

For a stable visual world, the colours; of objects should appear the same under different lights. This property of colour constancy has been assumed to be fundamental to vision, and many experimental attempts have been made to quantify it. I contend here, however, that the usual methods of measurement are either too coarse or concentrate not on colour constancy itself, but on other, complementary aspects of scene perception. Whether colour constancy exists other than in nominal terms remains unclear.

A well known property of human vision, known as color constancy, is the ability to correct for color deviations caused by a difference in illumination. A common approach to investigate color constant behavior is by psychophysical experiments, regarding the human visual system as a black box responding to a well defined change in an laboratory setup.

We explored the relation between individual differences in working memory (WM) and color constancy, the phenomenon of color perception that allows us to perceive the color of an object as relatively stable under changes in illumination. Successive color constancy (measured by first viewing a colored surface under a particular illumination and later recalling it under a new illumination) was better for higher WM individuals than for lower WM individuals. Moreover, the magnitude of this WM difference depended on how much contextual information was available in the scene, which typically improves color constancy. By contrast, simple color memory, measured by viewing and recalling a colored surface under the same illumination, showed no significant relation to WM. This study reveals a relation between WM and a low-level perceptual process not previously thought to operate within the confines of attentional control, and it provides a first account of the individual differences in color constancy known about for decades.

To contribute toward systematic European Space Agency (ESA) Earth observation (EO) Level 2 product generation at the ground segment, requiring a cloud/cloud-shadow quality layer detection in operating mode, but never accomplished to date by any EO data provider, this work presents the research and technological development (RTD) of an innovative AutoCloud+ approach. Designed and implemented to be " universal " , i.e., robust to changes in multi-spectral (MS) imaging sensor's spatial and spectral resolution specifications, AutoCloud+ aims at cloud/cloud-shadow detection in multi-sensor single-date MS imagery without human-machine interaction. Sensitive to spatial topological and spatial non-topological information components in addition to MS color properties in compliance with an object-based image analysis (OBIA) paradigm, AutoCloud+ adopts a hybrid (combined top-down/physical model-based and bottom-up/statistical model-based) CV workflow. The AutoCloud+ software prototype was tested starting from a 10 m resolution Sentinel-2 MS imagery, in comparison with alternative cloud/cloud-shadow detectors in operating mode, specifically, the single-date ESA Sentinel-2 (atmospheric) Correction Prototype Processor (Sen2Cor) and the multi-date CNES/CESBIO/DLR MACCS-ATCOR Joint Algorithm (MAJA). In this difficult test case affected by several error-prone situations, AutoCloud+ ran automatically with high accuracy, qualitatively affected by few false positives and few false negatives. KEYWORDS: color naming, color constancy, object-based image analysis (OBIA), physical and statistical data models, radiometric calibration, spatial topological and spatial non-topological information components, vision. 2 GEOBIA'2018

Existing color constancy methods are all based on specific assumptions such as the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that performs best for a specific image. To achieve selection and combining of color constancy algorithms, in this paper, natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g. grain size and contrast) is used. It is shown that the Weibull parameterization is related to the image attributes to which the used color constancy methods are sensitive to. A MoG-classifier is used to learn the correlation and weighting between the Weibull-parameters and the image attributes (number of edges, amount of texture and SNR). The output of the classifier is the selection of the best performing color constancy method for a certain image. Experimental results show a large improvement over state-of-the-art single algorithms. On a data set consisting of more than 11,000 images, an increase in color constancy performance up to 20% (median angular error) can be obtained compared to the best-performing single algorithm. Further, it is shown that for certain scene categories, one specific color constancy algorithm can be used instead of the classifier considering several algorithms.

Visual servoing, or the control of motion on the basis of image analysis in a closed loop, is more and more recognized as 9 an important tool in modern robotics. Here, we present a new model-driven approach to derive a description of the motion 10 of a target object. This method can be subdivided into an illumination invariant target detection stage and a servoing process 11 which uses an adaptive Kalman filter to update the model of the non-linear system. This technique can be applied to any 12 pan-tilt zoom camera mounted on a mobile vehicle as well as to a static camera tracking moving environmental features.

The spectral distribution of illumination light is a basic element deciding color rendering property, since the object color is dependent on the spectral distribution of the illumination light and the spectral reflectance of the object surface. Although the natural the sunlight is the standard light of the color rendering property, the sunlight spectral distribution changes to some extent according to time of day, weather, geographic position and season. It means that the color appearance of the object changes under the variable natural light from hour to hour in a day. In other words, it shows the possibility that daily fluctuations happen in the object color under the natural light. In this paper, we measured daily fluctuations of the spectral distribution of the sunlight and the spectral reflectance of various objects, in order to see if distinct change of the color appearance can be seen under diurnal change of the sunlight spectral distribution. As a result, we found the clear color appearance change of the object surface breaking color constancy under diurnal change of the sunlight spectral distribution.

Ratios of excitations in each cone-photoreceptor class produced by light reflected from pairs of surfaces in a scene are almost invariant under natural illuminant changes. The stability of these spatially defined ratios may explain the remarkable ability of human observers to efficiently discriminate illuminant changes from changes in surface reflectances. Spatial cone-excitation ratios are not, however, exactly invariant. This study is concerned with observers' sensitivity to these invariance violations. Simulations of Mondrian paintings with either 49 or two natural surfaces under Planckian illuminants were presented as images on a computer-controlled display in a two-interval experimental design: in one interval, the surfaces underwent an illuminant change; in the other interval, the surfaces underwent the same change but the images were then corrected so that, for each cone class, ratios of excitations were preserved exactly. Although the intervals with corrected images corresponded individually to highly improbable natural events, observers systematically misidentified them as containing the illuminant changes, the probability of error increasing as the violation of invariance in the other interval increased. For the range of illuminants and surfaces tested, sensitivity to violations of invariance was found to depend on cone class: it was greatest for long-wavelength-sensitive cones and least for short-wavelength-sensitive cones. Spatial cone-excitation ratios, or some closely related quantities, seem to be the cues preferred by observers for making inferences about surface illuminant changes.

Colour constancy refers to the constant perceived or apparent colour of a surface despite changes in illumination spectrum. Laboratory measurements have often found it imperfect. The aim here was to estimate the frequency of constancy failures in natural outdoor environments and relate them to colorimetric surface properties. A computational analysis was performed with 50 hyperspectral reflectance images of outdoor scenes undergoing simulated daylight changes. For a chromatically adapted observer, estimated colour appearance changed noticeably for at least 5% of the surface area in 60% of scenes, and at least 10% of the surface area in 44% of scenes. Somewhat higher frequencies were found for estimated changes in perceived colour relations represented by spatial ratios of cone-photoreceptor excitations. These estimated changes correlated with surface chroma and saturation. Outdoors, the colour constancy of some individual surfaces seems likely to fail, particularly if those surfaces are colourful.

Relational color constancy, which refers to the constancy of perceived relations between surface colors under changes in illuminant, may be based on the computation of spatial ratios of cone excitations. As this activity need occur only within rather than between cone pathways, relational color constancy might be assumed to be based on relative luminance processing. This hypothesis was tested in a psychophysical experiment in which observers viewed simulated images of Mondrian patterns undergoing colorimetric changes that could be attributed either to an illuminant change or to a nonilluminant change; the images were isoluminant, achromatic, or unmodified. Observers reliably discriminated the two types of changes in all three conditions, implying that relational color constancy is not based on luminance cues alone. A computer simulation showed that in these isoluminant and achromatic images spatial ratios of cone excitations and of combinations of cone excitations were almost invariant under illuminant changes and that discrimination performance could be predicted from deviations in these ratios.