Varying Illumination Conditions Research Articles

Optic Flow in Harmony

Most variational optic flow approaches just consist of three constituents: a data term, a smoothness term and a smoothness weight. In this paper, we present an approach that harmonises these three components. We start by developing an advanced data term that is robust under outliers and varying illumination conditions. This is achieved by using constraint normalisation, and an HSV colour representation with higher order constancy assumptions and a separate robust penalisation. Our novel anisotropic smoothness is designed to work complementary to the data term. To this end, it incorporates directional information from the data constraints to enable a filling-in of information solely in the direction where the data term gives no information, yielding an optimal complementary smoothing behaviour. This strategy is applied in the spatial as well as in the spatio-temporal domain. Finally, we propose a simple method for automatically determining the optimal smoothness weight. This method bases on a novel concept that we call "optimal prediction principle" (OPP). It states that the flow field obtained with the optimal smoothness weight allows for the best prediction of the next frames in the image sequence. The benefits of our "optic flow in harmony" (OFH) approach are demonstrated by an extensive experimental validation and by a competitive performance at the widely used Middlebury optic flow benchmark.

Feature extraction based on fuzzy local discriminant embedding with applications to face recognition

Recently, local discriminant embedding (LDE) was proposed to manifold learning and pattern classification. LDE achieves good discriminating performance by integrating the information of neighbour and class relations between data points. However, in the real-world applications, the performances of face recognition are always affected by variations in illumination conditions and different facial expressions. LDE still cannot solve illumination problem in face recognition. In this study, the fuzzy local discriminant embedding (FLDE) algorithm is proposed, in which the fuzzy k-nearest neighbour (FKNN) is implemented to reduce these outer effects to obtain the correct local distribution information to persuit good performance. In the proposed method, a membership degree matrix is firstly calculated using FKNN, then the membership degree is incorporated into the definition of the Laplacian scatter matrix to obtain the fuzzy Laplacian scatter matrix. The optimal projections of FLDE can be obtained by solving a generalised eigenfunction. Experimental results on ORL, Yale and AR face databases show the effectiveness of the proposed method.

A Total Variation Model for Retinex

Human vision has the ability to recognize color under varying illumination conditions. Retinex theory is introduced to explain how the human visual system perceives color. The main aim of this paper is to present a total variation model for Retinex. Different from the existing methods, we consider and study two important elements which include illumination and reflection. We assume spatial smoothness of the illumination and piecewise continuity of the reflection, where the total variation term is employed in the model. The existence of the solution of the model is shown in the paper. We employ a fast computation method to solve the proposed minimization problem. Numerical examples are presented to illustrate the effectiveness of the proposed model.

Controlling Depth Estimation for Robust Robotic Perception

AbstractIn this paper, a closed-loop control approach to the robust depth estimation problem in stereo vision is presented. The idea employed in this work is to introduce feedback control techniques at image processing level in order to improve the robustness of a robotic vision system with respect to external influences, such as cluttered scenes and variable illumination conditions. The control strategy detailed in this paper is based on the traditional open-loop mathematical model of the depth estimation process. Block matching has been considered as the technique to be used in the proposed depth calculation system. The suggested control law is derived from the known extremum seeking method which aims at finding optimal actuator values based on the minimum, or maximum, values of a feedback variable. The benefits of using feedback control techniques in machine vision, and particularly in stereo depth estimation, are demonstrated through performance evaluation results.

Indoor and Outdoor Navigation based on View Sequence under Variable Illumination Condition

Indoor and Outdoor Navigation based on View Sequence under Variable Illumination Condition

Autofocus using image phase congruency

The key issue in passive autofocus is to choose robust focus measures to judge optical blur in defocused images. Existing focus measures are sensitive to image contrast (illumination) as they use image intensity. In this report we demonstrate a focus measure using phase congruency. The proposed focus measure is robust for noisy imaging sensors in varying illumination conditions, and has great balance of defocus sensitivity and effective range. Its advantages are shown with a number of synthetic image sequences.

Adaptive imaging system with spatial light modulator for robust shape measurement of partially specular objects

In imaging systems, when specular surfaces responding sensitively to varying illumination conditions are imaged on groups of CCD pixels using imaging optics, the obtained image usually suffers from pixel saturation, resulting in smearing or blooming phenomena. These problems are then serious obstacles when applying structured light-based optical profiling methods to the shape measurement of general objects with partially specular surfaces. Therefore, this paper combines a phase-based profiling system with an with an adaptive spatial light modulator in the imaging part for measuring the three-dimensional shapes of objects with an advanced dynamic range. The use of a spatial light modulator in front of a CCD camera prevents the image sensor from being saturated, as the pixel transmittance is controlled by monitoring the input images and providing modulator feedback signals over time and space. When using the proposed system, since the projected fringes are effectively imaged on the CCD without any pixel saturation, phase information according to the object's shape can be correctly extracted from non-saturated images. The configuration of the proposed system and transmittance control scheme are explained in detail, plus the performance is verified through a series of experiments, in which phase information was successfully extracted from areas that are not normally measurable due to saturation. Based on the results, the proposed shape measurement system showed a more advanced adaptive dynamic range when compared with a conventional system.

Band gap dependent thermophotovoltaic device performance using the InGaAs and InGaAsP material system

Thermophotovoltaic cells with a range of band gaps are modeled under a variety of illumination conditions, including a range of source temperatures and a variable degree of spectral control. Thus, the balance between the requirements of high power densities and high efficiencies can be investigated. The influence of elevated cell temperatures, cell cooling, Auger recombination, and series resistances have been included, and all weight the optimum band gap thermophotovoltaic cell toward higher band gaps than the ∼0.5–0.6 eV conventional optimum. The cells have been modeled using fundamental physical parameters from the InGaAs and InGaAsP material system which accurately reproduce reported device performance and allow a comparison to theoretical limits.

PS II model based analysis of transient fluorescence yield measured on whole leaves of Arabidopsis thaliana after excitation with light flashes of different energies

Our recently presented PS II model (Belyaeva et al., 2008) was improved in order to permit a consistent simulation of Single Flash Induced Transient Fluorescence Yield (SFITFY) traces that were earlier measured by Steffen et al. (2005) on whole leaves of Arabidopsis (A.) thaliana at four different energies of the actinic flash. As the essential modification, the shape of the actinic flash was explicitly taken into account assuming that an exponentially decaying rate simulates the time dependent excitation of PS II by the 10ns actinic flash. The maximum amplitude of this excitation exceeds that of the measuring light by 9 orders of magnitude. A very good fit of the SFITFY data was achieved in the time domain from 100ns to 10s for all actinic flash energies (the maximum energy of 7.5×1016 photons/(cm2flash) is set to 100%, the relative energies of weaker actinic flashes were of ∼8%, 4%, ∼1%). Our model allows the calculation and visualization of the transient PS II redox state populations ranging from the dark adapted state, via excitation energy and electron transfer steps induced by pulse excitation, followed by final relaxation into the stationary state eventually attained under the measuring light. It turned out that the rate constants of electron transfer steps are invariant to intensity of the actinic laser flash. In marked contrast, an increase of the actinic flash energy by more than two orders of magnitude from 5.4×1014 photons/(cm2flash) to 7.5×1016 photons/(cm2flash), leads to an increase of the extent of fluorescence quenching due to carotenoid triplet (3Car) formation by a factor of 14 and of the recombination reaction between reduced primary pheophytin (Phe−) and P680+ by a factor of 3 while the heat dissipation in the antenna complex remains virtually constant.The modified PS II model offers new opportunities to compare electron transfer and dissipative parameters for different species (e.g. for the green algae and the higher plant) under varying illumination conditions.

Signature extraction using mutual interdependencies

Recently, mutual interdependence analysis (MIA) has been successfully used to extract representations, or ''mutual features'', accounting for samples in the class. For example, a mutual feature is a face signature under varying illumination conditions or a speaker signature under varying channel conditions. A mutual feature is a linear regression that is equally correlated with all samples of the input class. Previous work discussed two equivalent definitions of this problem and a generalization of its solution called generalized MIA (GMIA). Moreover, it showed how mutual features can be computed and employed. This paper uses a parametrized version GMIA(@l) to pursue a deeper understanding of what GMIA features really represent. It defines a generative signal model that is used to interpret GMIA(@l) and visualize its difference to MIA, principal and independent component analysis. Finally, we analyze the effect of @l on the feature extraction performance of GMIA(@l) in two standard pattern recognition problems: illumination-independent face recognition and text-independent speaker verification.

Adaptive Region-Based Image Enhancement Method for Robust Face Recognition Under Variable Illumination Conditions

Variable illumination conditions, especially the side lighting effects in face images, form a main obstacle in face recognition systems. To deal with this problem, this paper presents a novel adaptive region-based image preprocessing scheme that enhances face images and facilitates the illumination invariant face recognition task. The proposed method first segments an image into different regions according to its different local illumination conditions, then both the contrast and the edges are enhanced regionally so as to alleviate the side lighting effect. Different from existing contrast enhancement methods, we apply the proposed adaptive region-based histogram equalization on the low-frequency coefficients to minimize illumination variations under different lighting conditions. Besides contrast enhancement, by observing that under poor illuminations the high-frequency features become more important in recognition, we propose enlarging the high-frequency coefficients to make face images more distinguishable. This procedure is called edge enhancement (EdgeE). The EdgeE is also region-based. Compared with existing image preprocessing methods, our method is shown to be more suitable for dealing with uneven illuminations in face images. Experimental results on the representative databases, the Yale B+Extended Yale B database and the Carnegie Mellon University-Pose, Illumination, and Expression database, show that the proposed method significantly improves the performance of face images with illumination variations. The proposed method does not require any modeling and model fitting steps and can be implemented easily. Moreover, it can be applied directly to any single image without using any lighting assumption, and any prior information on 3-D face geometry.

Non-ideal class non-point light source quotient image for face relighting

Quotient Image (QI) algorithm has been widely used in face recognition and re-rendering under varying illumination conditions. One of the inaccuracies of QI algorithm is the assumption of “Ideal Class”, that all faces have the same surface normal (3D shape). However, in practice this assumption is often not true. To reduce the inaccuracy, the Non-Ideal Class Non-Point Light source QI (NIC-NPL-QI), which ignores the “Ideal Class” assumption, is developed in this paper for face relighting. Unlike that in the basic QI algorithm a fixed reference object for all test objects is used, in the NIC-NPL-QI algorithm a special reference object for each test object is constructed, so that the test and reference objects have similar illumination images, achieving the equal effect of “Ideal Class” assumption. In the proposed method, the wavelet algorithm is introduced to estimate an illumination image. Furthermore, the proposed NIC-NPL-QI algorithm can handle the harmonic light and shadows. Experiments on Extended Yale B and CMU-PIE databases show that NIC-NLP-QI algorithm obtains better quality in synthesizing face images as compared with state-of-the-art algorithms.

The influence of the illumination geometry and luminance contrast on gloss perception

Gloss is a main characteristic determining the appearance of objects. Physically, gloss results from directionally selective light scattering at the front surface of a material, with a preference towards the specular reflection direction. However, the sample illuminance and consequently the entire luminance distribution of the illumination scene around the sample could strongly influence gloss perception, especially for high glossy surfaces on which a reflected image becomes perceptible. In this study, the influence of variations in illumination conditions and engendered luminance contrasts on gloss perception has been examined. A psychophysical experiment was conducted in a light booth, especially designed for this purpose. The final outcome of the study is a psychophysical scaling function, relating visual gloss to the luminance of both the reflected image and the surround.

Road environment modeling using robust perspective analysis and recursive Bayesian segmentation

Recently, vision-based advanced driver-assistance systems (ADAS) have received a new increased interest to enhance driving safety. In particular, due to its high performance–cost ratio, mono-camera systems are arising as the main focus of this field of work. In this paper we present a novel on-board road modeling and vehicle detection system, which is a part of the result of the European I-WAY project. The system relies on a robust estimation of the perspective of the scene, which adapts to the dynamics of the vehicle and generates a stabilized rectified image of the road plane. This rectified plane is used by a recursive Bayesian classifier, which classifies pixels as belonging to different classes corresponding to the elements of interest of the scenario. This stage works as an intermediate layer that isolates subsequent modules since it absorbs the inherent variability of the scene. The system has been tested on-road, in different scenarios, including varied illumination and adverse weather conditions, and the results have been proved to be remarkable even for such complex scenarios.

A Robust Object Segmentation System Using a Probability-Based Background Extraction Algorithm

A video-based monitoring system must be capable of continuous operation under various weather and illumination conditions. Moreover, background subtraction is a very important part of surveillance applications for successful segmentation of objects from video sequences, and the accuracy, computational complexity, and memory requirements of the initial background extraction are crucial in any background subtraction method. This paper proposes an algorithm to extract initial color backgrounds from surveillance videos using a probability-based background extraction algorithm. With the proposed algorithm, the initial background can be extracted accurately and quickly, while using relatively little memory. The intrusive objects can then be segmented quickly and correctly by a robust object segmentation algorithm. The segmentation algorithm analyzes the threshold values of the background subtraction from the prior frame to obtain good quality while minimizing execution time and maximizing detection accuracy. The color background images can be extracted efficiently and quickly from color image sequences and updated in real time to overcome any variation in illumination conditions. Experimental results for various environmental sequences and a quantitative evaluation are provided to demonstrate the robustness, accuracy, effectiveness, and memory economy of the proposed algorithm.

Cortical dynamics of surface lightness anchoring, filling-In, and perception

This study proposes how the visual cortex may process natural images under variable illumination conditions to generate surface lightness percepts. It is known that visual representations can adapt to a million-fold change in luminance. How such adaptation also anchors percepts of surface lightness to use the full dynamic range of neurons remains an unsolved problem. Such an anchoring of lightness helps to make an image look natural. Anchoring properties include articulation, insulation, configuration, and area effects (e.g., Gilchrist et al., 1999). A cortical model is developed that quantitatively simulates such psychophysical data, as well as psychophysical data about discounting the illumination gradient and the Cornsweet effect, among others. The model is also consistent with a range of anatomical and neurophysiological data about how the brain may use boundary representations to gate the filling-in of surface lightness via horizontal cortical interactions. The model filling-in mechanism runs a thousand times faster than mechanisms of previous biological filling-in models, and thereby helps to clarify how filling-in can occur at the speeds shown in perceptual experiments. The model can process natural images even under dim moonlight and dazzling sunlight. Application of the model to color domain illustrates that it is also able to process natural color images.

Spectral anomaly detection in deep shadows

Although several hyperspectral anomaly detection algorithms have proven useful when illumination conditions provide for enough light, many of these same detection algorithms fail to perform well when shadows are also present. To date, no general approach to the problem has been demonstrated. In this paper, a novel hyperspectral anomaly detection algorithm that adapts the dimensionality of the spectral detection subspace to multiple illumination levels is described. The novel detection algorithm is applied to reflectance domain hyperspectral data that represents a variety of illumination conditions: well illuminated and poorly illuminated (i.e., shadowed). Detection results obtained for objects located in deep shadows and light-shadow transition areas suggest superiority of the novel algorithm over standard subspace RX detection.

Articulated body motion tracking using illumination invariant optical flow

We propose a model-based tracking method for articulated objects in monocular video sequences under varying illumination conditions. The tracking method uses estimates of optical flows constructed by projecting model textures into the camera images and comparing the projected textures with the recorded information. An articulated body is modelled in terms of 3D primitives, each possessing a specified texture on its surface. An important step in model-based tracking of 3D objects is the estimation of the pose of the object during the tracking process. The optimal pose is estimated by minimizing errors between the computed optical flow and the projected 2D velocities of the model textures. This estimation uses a least-squares method with kinematic constraints for the articulated object and a perspective camera model. We test our framework with an articulated robot and show results.

Face detection based on AdaBoost algorithm with Local AutoCorrelation image

This paper proposes a novel concept of Local AutoCorrelation (LAC), which is converted to LAC images for robust face detection under varying illumination conditions. We have applied LAC images to face detection based on AdaBoost algorithm. MIT CBCL images are used for training, while CMU PIE face database including a variety of illumination directions is used for detection. As a result, the LAC is found to be so effective that face detection rate is improved by up to 4.7%.

Dynamic-Range Widening in a CMOS Image Sensor Through Exposure Control Over a Dual-Photodiode Pixel

In this paper, we propose a technique for automatic-exposure control and synthesis for a wide-dynamic-range sensor based on dual-exposure method. Using the proposed technique, a sensor can adaptively adjust its exposure to widely varying illumination conditions and consequently accomplish an infinite dynamic range in theory. An artificial test bench consisting of a virtual illumination source and its imaging system is introduced to verify the performance of the proposed technique. Simulations show how a wider dynamic range can be achieved by the proposed technique. It is also shown that a VGA-resolution CMOS image sensor developed based on the proposed technique can support up to a 119-dB dynamic range.