Varying Illumination Conditions Research Articles

H2O-ice particle size variations across Ganymede's and Callisto's surface

The detailed investigation of the variations in the H2O-ice spectral signatures across Ganymede's and Callisto's surfaces derived from the NIMS (Near Infrared Mapping Spectrometer) data of the Galileo mission have shown that in the case of areal mixing of H2O ice and dark components the associated band depth ratios (BDRs) of the individual H2O-ice absorptions can be reliably used to qualitatively infer variations in the H2O ice particle size and even to semi-quantitatively estimate particle size ranges on the satellites' surfaces when largely unaffected by hydrated non-ice materials or varying illumination conditions. This modeling approach implies H2O ice particle radii ranging between ~1 μm and ~1 mm on Ganymede and up to ~2 mm on Callisto Our analyses point to a continuous decrease of H2O - ice particle sizes toward the poles on both satellites. These variations may be caused by similar surface processes. The smooth latitudinal trend may be related to the surface temperatures and possible thermal migration of H2O vapor to colder region in higher latitudes (Spencer, 1987) and particle welding at lower latitudes. Larger particles in the equatorial region of Callisto compared to Ganymede could be due to its higher maximum surface temperature and a longer Callistoan day resulting in more extensive particle welding.

Computer vision-based localisation of picking points for automatic litchi harvesting applications towards natural scenarios

Locating picking points plays an important role in robotic litchi harvesting in orchards. However, the localisation accuracy can easily be affected by unstructured growing environments with variable illumination conditions and the unpredictable growing shapes of weight-bearing stems carrying litchi clusters. A computer-vision-based method is proposed to locate acceptable picking points for litchi clusters. To improve the illumination distributions of weakly illuminated images while leaving those of well-illuminated images unchanged, an iterative retinex algorithm was developed. Then, the litchi regions are segmented by combining red/green chromatic mapping and Otsu thresholding in the RGB colour space. By incorporating both local spatial and local hue-level intensity relationships, the hue component in the HSV colour space is re-constructed to filter the noise, and the stem regions are segmented in accordance with the distributed intervals of hue-level intensity. Finally, based on the connection and position relationship among the segmented litchi and stem regions, the structural distribution of the corners generated via Harris corner detection is analysed to locate the picking points. More than 97% of the pixels within litchi regions are correctly segmented after illumination compensation, and an improvement of 7% in the number of correctly segmented pixels within stem regions is achieved with the re-construction of the hue-level intensity. The overall performance of the proposed method was evaluated on test images with high illumination diversity, and accuracy greater than 83% in locating litchi picking points was achieved, showing better performance than three similar frameworks that do not incorporate our proposed procedures.

Light-mediated effects of CdTe-MSA quantum dots on the autofluorescence of freshwater green microalgae: Spectroscopic studies

The water-soluble semiconductor quantum dots (QDs) serve as optically detectable models of nanoparticles and are commonly applied as photoluminescent markers in biological systems. The unicellular algae represent a popular model system suitable to evaluate pollution-induced effects. There is growing experimental evidence that release of metal ions cannot account for potential toxicity of metal containing nanoparticles, however, the underlying mechanisms are not clearly understood. Surrounding environment and illumination conditions are among the most important factors affecting the stability of QDs as well as the interaction between nanoparticles and cells such as microalgae. The measurements of changes in photoluminescence (PL) of QDs and autofluorescence (AF) of microalgae can thus be used as a non-invasive screening method for detecting mutual effects of nanoparticles and algae cells on each other under natural conditions.In this study, CdTe quantum dots (a peak of PL at 550 nm) capped with a mercaptosuccinic acid (MSA) were introduced into aqueous ionic medium containing wild type green freshwater microalgae Scenedesmus and Chlorella sp. cells under artificial and natural ambient illumination. The spectroscopy and microscopy techniques were applied to observe both the influence of the microalgae on the spectral properties of negatively charged CdTe-MSA quantum dots and the effects of nanoparticles on the microalgae. The presence of algae cells revealed a protecting effect on both medium-dependent and radiation-induced changes in photoluminescence properties of QDs, which could be related with the increased stability of the capping layer. The effects on cellular AF intensity and the interaction of QDs with cellular surface depended on type of microalgae. The observed changes in AF spectral properties and AF induction signals can't be explained only by the photodegradation of QDs and have revealed the ability of nanoparticles to retard the photoadaptation of wild type microalgae under naturally varying illumination conditions.

Photoelectrochemical Water Splitting using Adapted Silicon Based Multi-Junction Solar Cell Structures: Development of Solar Cells and Catalysts, Upscaling of Combined Photovoltaic-Electrochemical Devices and Performance Stability

Abstract Thin film silicon based multi-junction solar cells were developed for application in combined photovoltaic electrochemical systems for hydrogen production from water splitting. Going from single, tandem, triple up to quadruple junctions, we cover a range of open circuit voltages from 0.5 V to 2.8 V at photovoltaic cell (PV) efficiencies above 13%. The solar cells were combined with electrochemical (EC) cells in integrated devices from 0.5 cm2 to 64 cm2. Various combinations of catalyst pairs for the oxygen and hydrogen evolution reaction side (OER and HER) were investigated with respect to electrochemical activity, stability, cost and – important for the integrated device – optical quality of the metal catalyst on the HER side as back reflector of the attached solar cell. The combined PV-EC systems were further investigated under varied operation temperatures and illumination conditions for estimation of outdoor performance and annual fuel production yield. For 0.5 cm2 size combined systems a maximum solar-to-hydrogen efficiency ηSTH = 9.5% was achieved under standard test conditions. For device upscaling to 64 cm2 various concepts of contact interconnects for reduced current and fill factor loss when using large size solar cells were investigated. To replace high performance noble metal based catalyst pairs (Pt/RuO2 or Pt/IrOx), more abundant and cheaper NiMo (HER) and NiFeOx (OER) compounds were prepared via electrodeposition. With the NiMo/NiFeOx catalyst pair we obtained ηSTH = 5.1% for a 64 cm2 size solar cell which was even better than the performance of the Pt/IrO2 system (ηSTH = 4.8%). In simulated day-night cycle operation the NiMo/NiFeOx catalyst pair showed excellent stability over several days. The experimental studies were successfully accompanied by simulation of the entire PV-EC device using a series connection model which allowed studies and pre-estimations of device performance by varying individual components such as catalysts, electrolytes, or solar cells. Based on these results we discuss the prospects and challenges of integrated PV-EC devices on large area for hydrogen and solar fuel production in general.

Hyperspectral lidar point cloud segmentation based on geometric and spectral information

Light detection and ranging (lidar) can record a 3D environment as point clouds, which are unstructured and difficult to process efficiently. Point cloud segmentation is an effective technology to solve this problem and plays a significant role in various applications, such as forestry management and 3D building reconstruction. The spectral information from images could improve the segmentation result, but suffers from the varying illumination conditions and the registration problem. New hyperspectral lidar sensor systems can solve these problems, with the capacity to obtain spectral and geometric information simultaneously. The former segmentation on hyperspectral lidar were mainly based on spectral information. The geometric segmentation method widely used by single wavelength lidar was not employed for hyperspectral lidar yet. This study aims to fill this gap by proposing a hyperspectral lidar segmentation method with three stages. First, Connected-Component Labeling (CCL) using the geometric information is employed for base segmentation. Second, the output components of the first stage are split by the spectral difference using Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Third, the components of the second stage are merged based on the spectral similarity using Spectral Angle Match (SAM). Two indoor experimental scenes were setup for validation. We compared the performance of our mothed with that of the 3D and intensity feature based method. The quantitative analysis indicated that, our proposed method improved the point-weighted score by 19.35% and 18.65% in two experimental scenes, respectively. These results showed that the geometric segmentation method for single wavelength lidar could be combined with the spectral information, and contribute to the more effective hyperspectral lidar point cloud segmentation.

Nonlinear Feature Normalization for Hyperspectral Domain Adaptation and Mitigation of Nonlinear Effects

Domain adaptation in remote sensing aims at the automatic knowledge transfer between a set of multitemporal and multisource images. This process is often impaired by nonlinear effects in the data, e.g., varying illumination conditions, different viewing angles, and geometry-dependent reflection. In this paper, we introduce the Nonlinear Feature Normalization (NFN), a fast and robust way to align the spectral characteristics of multiple hyperspectral data sets. NFN employs labeled training spectra for the different classes in an image to describe the corresponding underlying low-dimensional manifold structure. A linear basis for data representation is defined by arbitrary class reference vectors, and the image is aligned to the new basis in the same space. This results in samples of the same class being pulled closer together and samples of different classes pushed apart. NFN transforms the data in its original domain, preserving physical interpretability. We use the continuous invertibility of NFN to derive the NFN Alignment (NFNalign) transformation, which can be used for domain adaptation, by transforming one data set to the domain of a chosen reference. The evaluation is performed on multiple hyperspectral data sets as well as our new benchmark for multitemporal hyperspectral data. In a first step, we show that the NFN transformation successfully mitigates nonlinear effects by comparing classification of the linear Spectral Angle Mapper on original and transformed data. Finally, we demonstrate successful domain adaptation with NFNalign by applying it to the task of hyperspectral data preprocessing. The evaluation shows that our approach for alignment of multitemporal data produces high-spectral similarity and successfully allows knowledge transfer, e.g., of classifier models and training data.

In-field citrus detection and localisation based on RGB-D image analysis

In-field citrus detection and localisation are highly challenging tasks due to varying illumination conditions, partial occlusion of citrus, and the colour variation of citrus at different stages of maturity. A reliable algorithm based on red-green-blue-depth (RGB-D) images was developed to detect and locate citrus in real, outdoor orchard environments for robotic harvesting. A depth filter and a Bayes-classifier-based image segmentation method were first developed to exclude as many backgrounds as possible. A density clustering method was then used to group adjacent points in the filtered RGB-D images into clusters, where each cluster represents a possible citrus. A colour, gradient, and geometry feature-based support vector machine classifier was trained to remove false positives. To test the method, a dataset with 506 RGB-D images was acquired in a citrus orchard on sunny and cloudy days. Results showed that the proposed algorithm was robust with an F1 score of 0.9197; the positioning errors in the x, y and z directions were 7.0 ± 2.5 mm, −4.0 ± 3.0 mm and 13.0 ± 3.0 mm, respectively, and the sizing error was −1.0 ± 4.0 mm. These excellent performance values demonstrate that the proposed method could be used to guide a citrus-harvesting robot.

Real-Time Dense Reconstruction of Tissue Surface From Stereo Optical Video.

We propose an approach to reconstruct dense three-dimensional (3D) model of tissue surface from stereo optical videos in real-time, the basic idea of which is to first extract 3D information from video frames by using stereo matching, and then to mosaic the reconstructed 3D models. To handle the common low-texture regions on tissue surfaces, we propose effective post-processing steps for the local stereo matching method to enlarge the radius of constraint, which include outliers removal, hole filling, and smoothing. Since the tissue models obtained by stereo matching are limited to the field of view of the imaging modality, we propose a model mosaicking method by using a novel feature-based simultaneously localization and mapping (SLAM) method to align the models. Low-texture regions and the varying illumination condition may lead to a large percentage of feature matching outliers. To solve this problem, we propose several algorithms to improve the robustness of the SLAM, which mainly include 1) a histogram voting-based method to roughly select possible inliers from the feature matching results; 2) a novel 1-point RANSAC-based [Formula: see text] algorithm called as DynamicR1PP [Formula: see text] to track the camera motion; and 3) a GPU-based iterative closest points (ICP) and bundle adjustment (BA) method to refine the camera motion estimation results. Experimental results on ex- and in vivo data showed that the reconstructed 3D models have high-resolution texture with an accuracy error of less than 2 mm. Most algorithms are highly parallelized for GPU computation, and the average runtime for processing one key frame is 76.3 ms on stereo images with 960×540 resolution.

On the design of a human–robot interaction strategy for commercial vehicle driving based on human cognitive parameters

A proper design of human–robot interaction strategies based on human cognitive factors can help to compensate human limitations for safety purposes. This work is focused on the development of a human–robot interaction system for commercial vehicle (Renault Twizy) driving, that uses driver cognitive parameters to improve driver’s safety during day and night tasks. To achieve this, eye blink behavior measurements are detected using a convolutional neural network, which is capable of operating under variable illumination conditions using an infrared camera. Percentage of eye closure measure values along with blink frequency are used to infer diver’s sleepiness level. The use of such algorithm is validated with experimental tests for subjects under different sleep-quality conditions. Additional cognitive parameters are also analyzed for the human–robot interaction system such as driver sleep quality, distraction level, stress level, and the effects related to not wearing glasses. Based on such driver cognitive state parameters, a human–robot interaction strategy is proposed to limit the speed of a Renault Twizy vehicle by intervening its acceleration and braking system. The proposed human–robot interaction strategy can increase safety during driving tasks for both users and pedestrians.

Lighting Environment Optimization of Highway Tunnel Entrance Based on Simulation Research

At the entrance of a tunnel, reflection of sunlight from the surrounding environment and a lack of adequate lighting usually cause some vision problems. The purpose of this study is to optimize the lighting environment at the entrance of highway tunnels. Firstly, based on a highway tunnel in Zhejiang Province, the natural illumination intensity in different seasons and climate conditions inside and outside the tunnel entrance was analyzed by means of DIALux simulation software. Then the variation in illumination conditions with distance at the entrance of the tunnel was analyzed. Finally, based on the results above, this study proposes four solutions as follows: setting up a shading shed, auxiliary lighting facilities, decelerating reflective markings, and an adaptive dimming system.

Infield oilseed rape images segmentation via improved unsupervised learning models combined with supreme color features

The variability of illumination and weather conditions lead to a big challenge for infield image segmentation. Therefore, robust, fast, and automated algorithms are highly required to obtain reliable image segmentation results. This research was aimed to develop efficient unsupervised clustering algorithms for oilseed rape image segmentation in the field. The Naïve Bayes rule was first employed to select a supreme color feature from ten color models. An initialization approach based on the genetic algorithm (GA) was then used to define the initial cluster centroids for subsequent Gaussian mixture model (GMM), self-organizing map (SOM), fuzzy c-mean (FCM), and k-means algorithms. The length of the chromosome was determined using cluster validity indices. Finally, the performances of these algorithms were evaluated based on the image segmentation quality and computation time. After testing the proposed method on the image datasets from two fields, the results revealed that the highest segmentation accuracy of 96% was obtained using the optimized SOM and the lowest computation time was obtained using the k-means. The GA-based initialization speeded up the convergence process and ensured consistent labeling between runs. All clustering algorithms were proved to be robust to varying illumination conditions and can process images with a very complex background in an automated fashion.

Deep Learning Classification of Face Images with varying Illumination Conditions

In face recognition system, the accuracy of recognition is greatly affected by varying degree of illumination on both the probe and testing faces. Particularly, the changes in direction and intensity of illumination are two major contributors to varying illumination. In overcoming these challenges, different approaches had been proposed. However, the study presented in this paper proposes a novel approach that uses deep learning, in a MATLAB environment, for classification of face images under varying illumination conditions. One thousand one hundred (1100) face images employed were obtained from Yale B extended database. The obtained face images were divided into ten (10) folders. Each folder was further divided into seven (7) subsets based on different azimuthal angle of illumination used. The images obtained were filtered using a combination of linear filters and anisotropic diffusion filter. The filtered images were then segmented into light and dark zones with respect to the azimuthal and elevation angles of illumination. Eighty percent (80%) of the images in each subset which forms the training set, were used to train the deep learning network while the remaining twenty percent (20%), which forms the testing set, were used to test the accuracy of classification of the deep learning network generated. With three successive iterations, the performance evaluation results showed that the classification accuracy varies from 81.82% to 100.00%.

Robust optical flow estimation based on wavelet

Concentrating on the issue that the systematic error caused by variation of illumination conditions and sensor noise leads to poor robustness and low accuracy of optical flow calculation, based on the wavelet multi-resolution theory, a robust optical flow estimation method is developed in this paper. With the multi-resolution characteristics of wavelet, the systematic error is incorporated into the calculation of optical flow to improve the robustness and estimation accuracy. In what follows, the total least squares method can be exploited to solve the obtained overdetermined wavelet optical flow equations such that the optical flow vector can be achieved. As compared to the traditional Lucas–Kanade approach, Horn–Schunck method, and the optical flow estimation algorithm in omnidirectional images using wavelet approach, simulation results show that the proposed algorithm can significantly improve the accuracy of optical flow estimation and the robustness of the optical flow field.

Photochemical Degradation of Cyanides and Thiocyanates from an Industrial Wastewater.

We have explored the simultaneous degradation of cyanides and thiocyanate present in wastewaters from a cokemaking factory using photoassisted methods under varied illumination conditions (from simulated solar light to UV light). Overall, the photochemical degradation of cyanides was more efficient than that of thiocyanates, regardless of the illumination conditions, the effect being more pronounced in the absence of a photocatalyst. This is due to their different degradation mechanism that in the case of thiocyanates is dominated by fast recombination reactions and/or charge transfer reactions to electron scavengers. In all cases, cyanate, ammonia, nitrates, and nitrites were formed at different amounts depending on the illumination conditions. The conversion yield under simulated solar light was almost complete for cyanides and quite high for thiocyanates after 6 h of illumination. Regarding toxicity, photochemical oxidation at 254 nm and under simulated solar light decreased significantly the toxicity of the pristine wastewater, showing a correlation with the intensity of the irradiation source. This indicate that simulated light can be effectively used to reduce the toxicity of industrial effluents, opening an interesting perspective for optimizing cyanide detoxification systems based on natural light.

Traffic Light Recognition With High Dynamic Range Imaging and Deep Learning

Traffic light recognition (TLR) detects the traffic light from an image and then estimates the state of the light signal. TLR is important for autonomous vehicles because running against a red light could cause a deadly car accident. For a practical TLR system, computation time, varying illumination conditions, and false positives are three key challenges. In this paper, a novel real-time method is proposed to recognize a traffic light with high dynamic imaging and deep learning. In our approach, traffic light candidates are robustly detected from low exposure/dark frames and accurately classified using a deep neural network in consecutive high exposure/bright frames. This dual-channel mechanism can make full use of undistorted color and shape information in dark frames as well as the rich context in bright frames. In the dark channel, a non-parametric multi-color saliency model is proposed to simultaneously extract lights with different colors. A multiclass classifier with convolutional neural network (CNN) model is then adopted to reduce the number of false positives in the bright channel. The performance is further boosted by incorporating temporal trajectory tracking. In order to speed up the algorithm, a prior detection mask is generated to limit the potential search regions. Intensive experiments on a large dual-channel dataset show that the proposed approach outperforms the state-of-the-art real-time deep learning object detector, which could cause more false positives because it uses bright images only. The algorithm has been integrated into our autonomous vehicle and can work robustly on real roads.

Assessing the Performance of UAS-Compatible Multispectral and Hyperspectral Sensors for Soil Organic Carbon Prediction

Laboratory spectroscopy has proved its reliability for estimating soil organic carbon (SOC) by exploiting the relationship between electromagnetic radiation and key spectral features of organic carbon located in the VIS-NIR-SWIR (350–2500 nm) region. While this approach provides SOC estimates at specific sampling points, geo-statistical or interpolation techniques are required to infer continuous spatial information. UAS-based proximal or remote sensing has the potential to provide detailed and spatially explicit spectral sampling of the topsoil at the field or even watershed scale. However, the factors affecting the quality of spectral acquisition under outdoor conditions need to be considered. In this study, we investigate the capabilities of two portable hyperspectral sensors (STS-VIS and STS-NIR), and two small-form multispectral cameras with narrow bands in the VIS-NIR region (Parrot Sequoia and Mini-MCA6), to predict SOC content. We collected spectral data under both controlled laboratory and outdoor conditions, with the latter being affected by variable illumination and atmospheric conditions and sensor-sample distance. We also analysed the transferability of the prediction models between different measurement setups by aligning spectra acquired under different conditions (laboratory and outdoor) or by different instruments. Our results indicate that UAS-compatible small-form sensors can be used to reliably estimate SOC. The results show that: (i) the best performance for SOC estimation under outdoor conditions was obtained using the VIS-NIR range, while the addition of the SWIR region decreased the prediction accuracy; (ii) prediction models using only the narrow bands of multispectral cameras gave similar or better performances than those using continuous spectra from the STS hyperspectral sensors; and (iii) when used in outdoor conditions, the micro hyperspectral sensors substantially benefitted from a laboratory model calibration followed by a spectral transfer using an internal soil standard. Based on this analysis, we recommend VIS-NIR portable instruments for estimating spatially distributed SOC data. The integration of these sensors in UAS-mapping devices could represent a cost-effective solution for soil research and precision farming applications when high resolution data are required.

Robust Optical Flow Estimation Using Tchebichef Moment Invariant Feature

In this paper, orthogonal moment invariant-based features are used to compute 2D optical flow from sequence of images. The gray level of pixel is described in terms of its local neighborhood using Tchebichef moment invariants rather than its individual intensity value. The description is then normalized in order to make it insensitive to intensity fluctuations due to noise or other perturbations such as varying illumination conditions. The principle of conservation of moment invariance is used to derive overdetermined system of 2D motion constraint equations in local neighborhood of each pixel. The velocity field is then estimated using the least square method. Experimental results are performed on sequential video and thermal image frames under varying environmental conditions. The run time, robustness against noisy and varying illumination conditions and rotation invariance of proposed method are compared with already existing moment and non-moment-based techniques.

One-Shot Learning for Custom Identification Tasks; A Review

Deep Learning has great achievements in computer vision for various classification and regression tasks. The automation of tasks such as component sorting, bin-picking and anomaly detection may be of great use in the process industry. However, most machine learning-based object categorization algorithms require training on hundreds or thousands of images and very large datasets. The requirement for large training datasets presents a barrier to the adoption of deep learning methodologies in many custom object classification tasks. For example, in defect detection, positive instances of a defect, take for instance a tank leakage, may seldom occur and therefore creating a dataset of sufficient size for conventional deep learning procedures is not always possible. One-shot learning aims to learn information about object categories from only a handful of labelled examples per category. One-shot learning has received the most attention in face-recognition and person re-identification (re-id) tasks due to their potential practical applications in surveillance security. This research will review these one-shot learning methodologies and investigate how they may be transferred to other domains. Concepts such as Siamese Networks and triplet loss which are commonly used for one-shot learning will be examined. Challenges such as variations in illumination conditions, object pose, camera resolution and partial occlusion will be discussed. Finally, the implications and advantages of deploying such techniques to practical applications in the process industry will be analysed.

Low-Light Image Enhancement Based on Maximal Diffusion Values

A vast amount of pictures are taken every day by using cameras mounted on various mobile devices. Even though the clarity of such acquired images has been significantly improved due to the advance of the image sensor technology, the visual quality is hardly guaranteed under varying illumination conditions. In this paper, a novel yet simple method for low-light image enhancement is proposed via the maximal diffusion value. The key idea of the proposed method is to estimate the illumination component, which is likely to appear as the bright pixel even under the low-light condition, by exploring multiple diffusion spaces. Specifically, the illumination component can be accurately separated from the scene reflectance by selecting the maximal value at each pixel position of those diffusion spaces, and thus independently adjusted for the visual quality enhancement. That is, we propose to adopt the maximal value among diffused intensities at each pixel position, so-called maximal diffusion value, as the illumination component since illumination components buried in the dark tend to be revealed with bright intensities through the iterative diffusion process. In contrast to previous approaches that still pose difficulties to balance between over-saturated and conservative restorations, the proposed method improves the image quality without any significant distortion while successfully suppressing the problem of noise amplification. Experimental results on benchmark datasets show the efficiency and robustness of the proposed method compared to previous approaches introduced in literature.

Integrated Velocity Measurement Algorithm Based on Optical Flow and Scale-Invariant Feature Transform

The pyramid Lucas-Kanade (LK) optical flow algorithm has been widely used in velocity measurement applications. However, these applications are limited by some shortcomings of the algorithm, such as its slow calculation speed and susceptibility to illumination changes. To solve these problems, a data fusion scheme based on the scale-invariant feature transform (SIFT) and optical flow is proposed to alleviate the dependence of the optical flow on the illumination conditions. In addition, an improved cubature Kalman filter (CKF) based on multi-rate residual correction (CKF-MRC) is proposed to solve the problem of inconsistency between the sampling frequencies of the SIFT and the optical flow, and takes full advantage of the high sampling frequency of SIFT. The experimental results demonstrate that the proposed CKF-MRC method can effectively improve the accuracy of velocity measurement under variable illumination conditions with a high sampling frequency.