Poor Lighting Conditions Research Articles

A No-Reference Image Quality Measure for Blurred and Compressed Images Using Sparsity Features

Images can be distorted in the real world via many sources like faulty sensors, artifacts generated by compression algorithms, defocus, faulty lens, and poor lighting conditions. Our biological vision system can identify the quality of image by looking at the images, but developing an algorithm to assess the quality of an image is a very challenging task as an image can be corrupted by different types of distortions and statistical properties of different types of distortions are dissimilar. The main objective of this article is to propose an image quality assessment technique for images corrupted by blurring and compression-based artifacts. Machine learning-based approaches have been used in recent times to perform this task. Images can be analyzed in different transform domains like discrete cosine transform domain, wavelet domains, curvelet domains, and singular value decomposition. These domains generate sparse matrices. In this paper, we propose no-reference image quality assessment algorithms for images corrupted by blur and different compression algorithms using sparsity-based features computed from different domains and all features pooled by support vector regression. The proposed model has been tested on three standard image quality assessment datasets LIVE, CSIQ, and TID2013, and correlation with subjected human opinion scores has been presented along with comparative study with state-of-the-art quality measures. Experiments run on standard image quality databases show that the results obtained are outperforming the existing results.

Real-time computerized video enhancement for minimally invasive fetoscopic surgery

BackgroundThe only definitive treatment for twin-to-twin transfusion syndrome is minimally invasive fetoscopic surgery for the selective coagulation of placental blood vessels. Fetoscopic surgery is a technically challenging operation, mainly due to the poor visibility conditions in the uterine environment. We present the design of an algorithm for the computerized enhancement of fetoscopic video and show that the enhanced video increases the ability of human users to identify blood vessels within fetoscopic video rapidly and accurately. MethodsA computer algorithm for the enhancement of fetoscopic video frames was created. First, optical fiber artifacts were removed via a modification of unsharp masking. Second, image contrast was increased via Contrast Limited Adaptive Histogram Equalization (CLAHE). Third, the effect of contrast enhancements on stationary features was removed by normalizing to a windowed mean of the video frames. Fourth, color information was reincorporated by combining the mean-normalized result with the unnormalized contrast enhanced image using the soft light blending algorithm. Medical trainees (n = 16) were recruited into a study to validate the algorithm. Subjects were shown enhanced or unenhanced fetoscopic video frames on a screen and were asked to identify whether a randomly placed marker fell on a blood vessel or on background. The accuracy of their responses was recorded. ResultsOn the subset of images where subjects had the lowest mean accuracy in identifying the placement of the marker, subjects performed better when viewing video frames enhanced by the computer (accuracy 74.27%; SE 0.97) than when viewing unenhanced video frames (accuracy 63.78%; SE 2.79). This result was statistically significant (p < 0.01). ConclusionReal-time computerized enhancement of fetoscopic video has the potential to ease the readability of video in poor lighting conditions, thus providing a benefit to the surgeon intraoperatively.

Confined spaces industrial inspection with micro aerial vehicles and laser range finder localization

This work addresses the problem of semi-automatic inspection and navigation in confined environments. A system that overcomes many challenges at the state of the art is presented. It comprises a multirotor able to inspect an industrial combustion chamber thus working in a GPS-denied environment with poor lighting conditions, in the presence of magnetic and communication disturbances, iron dust and repetitive patterns on the structure walls. The presented system is able to pass through narrow entrances but still capable of acquiring high resolution images and to allow operators to perform inspection of the structures. Starting from the captured data, the system is able to provide a 3D reconstruction of the inspected environment for offline analysis.

Robust Collaborative Discriminative Learning for RGB-Infrared Tracking

Tracking target of interests is an important step for motion perception in intelligent video surveillance systems. While most recently developed tracking algorithms are grounded in RGB image sequences, it should be noted that information from RGB modality is not always reliable (e.g. in a dark environment with poor lighting condition), which urges the need to integrate information from infrared modality for effective tracking because of the insensitivity to illumination condition of infrared thermal camera. However, several issues encountered during the tracking process limit the fusing performance of these heterogeneous modalities: 1) the cross-modality discrepancy of visual and motion characteristics, 2) the uncertainty of degree of reliability in different modalities, and 3) large target appearance variations and background distractions within each modality. To address these issues, this paper proposes a novel and optimal discriminative learning framework for multi-modality tracking. In particular, the proposed discriminative learning framework is able to: 1) jointly eliminate outlier samples caused by large variations and learn discriminability-consistent features from heterogeneous modalities, and 2) collaboratively perform modality reliability measurement and target-background separation. Extensive experiments on RGB-infrared image sequences demonstrate the effectiveness of the proposed method.

Robust vehicle detection in different weather conditions: Using MIPM

Intelligent Transportation Systems (ITS) allow us to have high quality traffic information to reduce the risk of potentially critical situations. Conventional image-based traffic detection methods have difficulties acquiring good images due to perspective and background noise, poor lighting and weather conditions. In this paper, we propose a new method to accurately segment and track vehicles. After removing perspective using Modified Inverse Perspective Mapping (MIPM), Hough transform is applied to extract road lines and lanes. Then, Gaussian Mixture Models (GMM) are used to segment moving objects and to tackle car shadow effects, we apply a chromacity-based strategy. Finally, performance is evaluated through three different video benchmarks: own recorded videos in Madrid and Tehran (with different weather conditions at urban and interurban areas); and two well-known public datasets (KITTI and DETRAC). Our results indicate that the proposed algorithms are robust, and more accurate compared to others, especially when facing occlusions, lighting variations and weather conditions.

Performance Evaluation of Feature Detectors and Descriptors Beyond the Visible

Feature detection and description algorithms represent an important milestone in most computer vision applications. They have been examined from various perspectives during the last decade. However, most studies focused on their performance when used on visible band imagery. This modality suffers considerably in poor lighting conditions and notably during night-time. Infrared cameras, which noticed a considerable proliferation in recent years, offer a viable alternative in such conditions. Understanding how the building blocks of computer vision applications behave in this modality would help the community accommodating them. For this reason, we carried out a performance analysis of the most commonly used feature detectors and descriptors beyond the visible. A dataset accounting for the various challenges on these algorithms has been generated. In addition, challenges inherent to the thermal modality have been considered, notably the non-uniformity noise. A comprehensive quantitative investigation into the performance of feature detectors and descriptors is therefore presented. This study would serve to filling the gap in the literature as most analyzes have been based on visible band imagery.

Mixotrophic phytoplankton dynamics in a shallow Mediterranean water body: how to make a virtue out of necessity

Mixotrophy is a combination of photosynthesis and direct access to organic carbon sources, mainly through osmotrophy or phagotrophy. This strategy is adopted by several, phylogenetically distinct, phytoplankton groups and is commonly occurring in marine, brackish and freshwater ecosystems. Traditionally, it has been put in relation to both scarcity of inorganic nutrients and poor light conditions. However, we observed blooms of the mixotrophic, toxic haptophyte Prymnesium parvum in different periods of the year and under variable resources availability. The analysis of a 6.5-year data set of phytoplankton weekly records from a Sicilian shallow lake (Biviere di Gela, south-eastern Sicily) allowed us to hypothesise that a depleted condition as regards inorganic nutrients is not the main fuel to the growth of P. parvum, neither this is due to light limitation. The results achieved show that an increased availability in suitable preys can stimulate the growth of this phagotrophic photoautotroph. Contemporarily, it was not found any clear environmental patterns to explain species dominance and growth patterns as related to inorganic nutrient availability. Moreover, it is shown that these organisms tend to monopolise resources when these become available irrespective of seasons, and under variable conditions as regards inorganic nutrient availability.

Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images.

Due to the poor lighting condition and limited dynamic range of digital imaging devices, the recorded images are often under-/over-exposed and with low contrast. Most of previous single image contrast enhancement (SICE) methods adjust the tone curve to correct the contrast of an input image. Those methods, however, often fail in revealing image details because of the limited information in a single image. On the other hand, the SICE task can be better accomplished if we can learn extra information from appropriately collected training data. In this work, we propose to use the convolutional neural network (CNN) to train a SICE enhancer. One key issue is how to construct a training dataset of low-contrast and high-contrast image pairs for end-to-end CNN learning. To this end, we build a large-scale multi-exposure image dataset, which contains 589 elaborately selected high-resolution multi-exposure sequences with 4,413 images. Thirteen representative multi-exposure image fusion and stack-based high dynamic range imaging algorithms are employed to generate the contrast enhanced images for each sequence, and subjective experiments are conducted to screen the best quality one as the reference image of each scene. With the constructed dataset, a CNN can be easily trained as the SICE enhancer to improve the contrast of an under-/over-exposure image. Experimental results demonstrate the advantages of our method over existing SICE methods with a significant margin.

A flexible system for gesture based human-robot interaction

In industrial collaborative robotics, operators and robots perform complex tasks working together without physical barriers. Under this premise, the availability of a flexible, robust and fast interaction system between the robot and the workers is a necessity.Human beings use voice and gestures to achieve a natural interaction. Taking into account the environmental conditions usually present in workshops with noise and poor lighting conditions, combining both communication channels can contribute to make the interaction more robust.This research work presents a solution to define, setup and run a flexible and robust gesture interaction system to integrate in collaborative robotics applications.

A Qualitative Approach to Understanding the Neighborhood Environmental Influences on Active Aging

Numerous researches mainly in western countries have found that active aging is associated with a wide range of health benefits for older adults. Although research related to active aging has gained considerable interest, in Malaysia, older adults’ active aging is still in its infancy. The crucial role of neighborhood characteristics as promoting active aging has led the WHO to adopt more comprehensive approaches by introducing ‘Age-Friendly Cities’ program. This study used a qualitative approach to explore the experience of older adults’ active aging as influenced by neighborhood characteristics. The data explication centered on concept of active aging. Main themes emerged were: physical activity, facilitators to physical activity, and barriers to physical activity, accessibility, social interaction, and safety. The results show that older adults are sensitive with respect to perceived falling hazards due to poor lighting and poor walkway conditions. Regular maintenance is required to avoid restrictions upon their physical activity.

Prepartum daylight exposure increases serum calcium concentrations in dairy cows at the onset of lactation.

In dairy cows, hypocalcemia is caused by the sudden calcium demand by the mammary gland at the onset of lactation. Calcitriol (1,25-dihydroxy vitamin D; 1,25-VitD) increases the intestinal calcium absorption and the renal calcium reabsorption. Daylight contributes to the formation of 1,25-VitD, as it transforms 7-dehydrocholesterol into cholecalciferol, a 1,25-VitD precursor. Calving pens are usually set in quiet places where cows can stay calm and relaxed before parturition. However, those pens often have poor lighting conditions and therefore cows may become vitamin D deficient because of inadequate daylight exposure. Therefore, we have tested the hypothesis that direct daylight exposure supports the synthesis of 1,25-VitD and consequently attenuates the decline of calcium concentrations at parturition. Twenty Holstein dairy cows were randomly assigned to 2 experimental groups (daylight group, DL; and control group). Beginning on d -10 before expected parturition, both groups were placed in a standard indoor calving pen from 1700 h to 800 h. From 800 h to 1700 h cows from the DL group were moved into a contiguous open pen with direct access to daylight whereas controls remained at the standard indoor calving pen. After parturition both groups were permanently placed in an indoor calving pen until the end of the experimental period (d 30 postpartum). Blood samples were collected daily from d -10 prior to expected parturition through d 7 postpartum with an additional sample on d 30 postpartum. Milk yield was recorded at each milking during the whole experimental period. In the DL group, 25-hydroxyvitamin D (25-VitD), 1,25-VitD and total calcium concentrations around parturition were higher than in the controls. Higher parathyroid hormone concentrations were observed in the control group compared to the DL group at parturition. Pyridinoline concentrations did not differ between groups on d 1, and therefore it is assumed that the intensity of calcium transfer from the bones to the bloodstream was not affected by the increased daylight exposure. The measured plasma metabolites (β-hydroxybutyrate, fatty acids and glucose) as well as milk yield were not affected by the increased daylight exposure. In conclusion, the increased daylight exposure before parturition increased 25-VitD and 1,25-VitD concentrations, preventing a considerable decline of total calcium concentrations around parturition.

Measurement of Face Detection Accuracy Using Intensity Normalization Method and Homomorphic Filtering

One of the factors that affects the detection system or face recognition is lighting. Image color processing can help the face recognition system in poor lighting conditions. In this study, homomorphic filtering and intensity normalization methods used to help improve the accuracy of face image detection. The experimental results show that the non-uniform of the illumination of the face image can be uniformed using the intensity normalization method with the average value of Peak Signal to Noise Ratio (PSNR) obtained from the whole experiment is 22.05314 and the average Absolute Mean Brightness Error (AMBE) value obtained is 6.147787. The results showed that homomorphic filtering and intensity normalization methods can be used to improve the detection accuracy of a face image.

CAPTURING REALITY AT CENTRE BLOCK

Abstract. The Centre Block of Canada’s Parliament buildings, National Historic Site of Canada is set to undergo a major rehabilitation project that will take approximately 10 years to complete. In preparation for this work, Heritage Conservation Services (HCS) of Public Services and Procurement Canada has been completing heritage documentation of the entire site which includes laser scanning of all interior rooms and accessible confined spaces such as attics and other similar areas. Other documentation completed includes detailed photogrammetric documentation of rooms and areas of high heritage value. Some of these high heritage value spaces present certain challenges such as accessibility due to the height and the size of the spaces. Another challenge is the poor lighting conditions, requiring the use of flash or strobe lighting to either compliment or completely eliminate the available ambient lighting. All the spaces captured at this higher level of detail were also captured with laser scanning. This allowed the team to validate the information and conduct a quality review of the photogrammetric data. As a result of this exercise, the team realized that in most, if not all cases, the photogrammetric data was more detailed and at a higher quality then the terrestrial laser scanning data. The purpose and motivation of this paper is to present these findings, as well provide the advantages and disadvantages of the two methods and data sets.

Autonomous robotic system for tunnel structural inspection and assessment

This paper presents a robotic platform, capable of autonomous tunnel inspection, developed under ROBO-SPECT European union funded research project. The robotic vehicle consists of a robotized production boom lift, a high precision robotic arm, advanced computer vision systems, a 3D laser scanner and an ultrasonic sensor. The autonomous inspection of tunnels requires advanced capabilities of the robotic vehicle and the computer vision sub-system. The robot localization in underground spaces and on long linear paths is a challenging task, as well as the mm accurate positioning of a robotic tip installed on a five-ton crane vehicle. Moreover, the 2D and 3D vision tasks, which support the inspection process, should tackle with poor and variable lighting conditions, low textured lining surfaces and the need for high accuracy. This contribution describes the final robotic vehicle and the developments as designed for concrete lining tunnel inspection. Results from the validation and benchmarking of the system are also included following the final tests at the operating Egnatia Motorway tunnels in northern Greece.

Influence of environmental variables on fear of crime: Comparing self-report data with physiological measures in an experimental design

Self-reports and questionnaires have been the preferred research methods in the criminological field of “fear of crime” (FOC) since its rise in the 1960s. Our study had two main goals: (1) to measure the physiological indicators of fear in real time and (2) to compare these data with those obtained through self-reports, designed also to measure the emotion of fear. An experimental study was conducted over the course of a week during late February 2016 in Aarhus (Denmark), in which the focus was on traditional environmental variables in the field of FOC (i.e., poor lighting conditions). Our results support the ideas that: (1) the absence of good luminosity in an open public space in an urban setting elicits physiological reactions of arousal that can be taken as indicators of experiences of fear and (2) heart rate appears to capture aspects of the emotion of fear that are not reflected in data obtained through self-report questionnaires. This study, introducing a pioneering approach to the study of FOC, presents great potentials in complementing traditional methods in the crime sciences. The many challenges we faced are significant and reported with the hope that subsequent literature will build upon. We propose that traditional methods and new measurements could be combined to advance research in the field by allowing researchers to more unambiguously constrain the interpretation of their data. This becomes particularly relevant in a field like FOC, which has long suffered from irreconcilable results stemming from different investigations.

Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic Processing System.

Neuromorphic hardware emulates dynamics of biological neural networks in electronic circuits offering an alternative to the von Neumann computing architecture that is low-power, inherently parallel, and event-driven. This hardware allows to implement neural-network based robotic controllers in an energy-efficient way with low latency, but requires solving the problem of device variability, characteristic for analog electronic circuits. In this work, we interfaced a mixed-signal analog-digital neuromorphic processor ROLLS to a neuromorphic dynamic vision sensor (DVS) mounted on a robotic vehicle and developed an autonomous neuromorphic agent that is able to perform neurally inspired obstacle-avoidance and target acquisition. We developed a neural network architecture that can cope with device variability and verified its robustness in different environmental situations, e.g., moving obstacles, moving target, clutter, and poor light conditions. We demonstrate how this network, combined with the properties of the DVS, allows the robot to avoid obstacles using a simple biologically-inspired dynamics. We also show how a Dynamic Neural Field for target acquisition can be implemented in spiking neuromorphic hardware. This work demonstrates an implementation of working obstacle avoidance and target acquisition using mixed signal analog/digital neuromorphic hardware.

Humanoid push recovery using sensory reweighting

In this paper we propose a novel system that uses sensory input from both vision and inertial sensors for an improved perception of the robot current status of equilibrium. We use MonoSLAM vision odometry as a basis for the visual perception and a gyro for angular velocity measurements; and we devise a reweighting method within a Kalman filter framework. Moreover, our approach is designed to be robust against visual and measurement noise such as blur, poor lighting conditions, and faulty sensory output. The novelty in this work is a robust humanoid fall avoidance system, which relies on the fusion of sensory input, mainly gyroscope and visual odometry, taking into account changes in the environment. The fusion of the mentioned sensors in addition to the image quality assessment, ensure a more human-like fall avoidance in comparison to currently existing systems. We implement our method on the NAO humanoid, where seven sets of experiments are performed to assess the effectiveness of our approach. The fusion of camera and gyro information not only enables a more human-like behavior, but also provides more humanoid stability and faster recovery, and thus leads to more robust fall avoidance.

FUSION OF THERMAL AND RGB IMAGES FOR BORDER SECURITY SURVEILLANCE

Border security surveillance in remote areas are often suffer from low visibility and poor lighting conditions Thus, tracking and recognizing the intruder in such a situation is a daunting task. In this study a fusion technique is presented for enhancing the visibility by merging feature sets from thermal and RGB image sequence. The technique also solves the problem of computing the feature sets in massive sequences o images by carry-forwarding the past feature sets for consequent image sequence.

Thermal photogrammetric imaging: A new technique for monitoring dome eruptions

Structure-from-motion (SfM) algorithms greatly facilitate the generation of 3-D topographic models from photographs and can form a valuable component of hazard monitoring at active volcanic domes. However, model generation from visible imagery can be prevented due to poor lighting conditions or surface obscuration by degassing. Here, we show that thermal images can be used in a SfM workflow to mitigate these issues and provide more continuous time-series data than visible-light equivalents. We demonstrate our methodology by producing georeferenced photogrammetric models from 30 near-monthly overflights of the lava dome that formed at Volcán de Colima (Mexico) between 2013 and 2015. Comparison of thermal models with equivalents generated from visible-light photographs from a consumer digital single lens reflex (DSLR) camera suggests that, despite being less detailed than their DSLR counterparts, the thermal models are more than adequate reconstructions of dome geometry, giving volume estimates within 10% of those derived using the DSLR.Significantly, we were able to construct thermal models in situations where degassing and poor lighting prevented the construction of models from DSLR imagery, providing substantially better data continuity than would have otherwise been possible. We conclude that thermal photogrammetry provides a useful new tool for monitoring effusive volcanic activity and assessing associated volcanic risks.

Discriminative multi-layer illumination-robust feature extraction for face recognition

Tackling illumination variation is a major problem and it is also an important challenge for practical face recognition systems. Some related methods consider that lighting intensity components mainly lie in large-scale features, and they use a lot of image decomposition techniques to extract the small-scale illumination-invariant features and remove the large-scale features from original face images. However, it argues that the large-scale features contain a lot useful information which can be further extracted, and the small-scale illumination-invariant features are not robust enough due to they contain some detrimental features (noise, etc.). In this paper, we propose a discriminative multi-layer illumination-robust feature extraction (DMI) model to address this problem. First, we decompose the large-scale features into multi-layer small-scale illumination-robust features as a linear combination, and then a weight is assigned to each layer to adjust its importance and influence. The idea is to take full advantage of these useful information in large-scale features for face recognition. Second, we learn a discriminant filter to improve the robustness and statistical discriminative ability of the reconstructed illumination-robust face for face recognition under poor lighting conditions. Extensive experiments on three benchmark face databases and a video image database show that DMI performs better than the related methods, especially in difficult lighting conditions.