Difficult Lighting Conditions Research Articles

Scanning, modelling and dissemination of the interior appearance of wooden historic churches in the Maramures region of Romania

In the Maramureș region of Romania there is a large number of historic wooden churches dating back to the 17th and 18th centuries. These objects of tangible cultural heritage continue to be exposed to degradation factors. Meanwhile, their interiors hide important and historically valuable artefacts of cultural heritage. Their loss would noticeably impoverish the heritage of local communities. This article presents the problems of 3D scanning the interiors of wooden historic churches, the scanning methodology specifically developed for this occasion, the equipment used and its parameters, and the results of its application. Four examples of wooden churches from the Maramureș region were studied: modern laser scanning technologies with appropriate selection of parameters permits a satisfactorily precise scan of the interior of a wooden religious building, even in difficult lighting conditions. The methodology and equipment choice was proven to be successful and is recommended here for future projects in the region and for structures facing similar challenges.

Potential of a laser pointer contact lens to improve the reliability of video-based eye-trackers in indoor and outdoor conditions.

Many video-based eye trackers rely on detecting and tracking ocular features, a task that can be negatively affected by a number of individual or environmental factors. In this context, the aim of this study was to practically evaluate how the use of a scleral contact lens with two integrated nearinfrared lasers (denoted CLP) could improve the tracking robustness in difficult lighting conditions, particularly outdoor ones. We assessed the ability of the CLP (on a model eye) to detect the lasers and to deduce a gaze position with an accuracy better than 1° under four lighting conditions (1 lx, 250 lx, 50 klux and alternating 1lx /250 lx) on an artificial eye. These results were compared to the ability of a commercial eye tracker (Pupil Core) to detect the pupil on human eyes with a confidence score equal to or greater than 0.9. CLP provided good results in all conditions (tracking accuracy and detection rates). In comparison, the Pupil Core performed well in all indoor conditions (99% detection) but failed in outdoor conditions (9.85% detection). In conclusion, the CLP presents strong potential to improve the reliability of video-based eyetrackers in outdoor conditions by providing easy trackable feature.

Pedestrian and Vehicle Detection in Autonomous Vehicle Perception Systems-A Review.

Autonomous Vehicles (AVs) have the potential to solve many traffic problems, such as accidents, congestion and pollution. However, there are still challenges to overcome, for instance, AVs need to accurately perceive their environment to safely navigate in busy urban scenarios. The aim of this paper is to review recent articles on computer vision techniques that can be used to build an AV perception system. AV perception systems need to accurately detect non-static objects and predict their behaviour, as well as to detect static objects and recognise the information they are providing. This paper, in particular, focuses on the computer vision techniques used to detect pedestrians and vehicles. There have been many papers and reviews on pedestrians and vehicles detection so far. However, most of the past papers only reviewed pedestrian or vehicle detection separately. This review aims to present an overview of the AV systems in general, and then review and investigate several detection computer vision techniques for pedestrians and vehicles. The review concludes that both traditional and Deep Learning (DL) techniques have been used for pedestrian and vehicle detection; however, DL techniques have shown the best results. Although good detection results have been achieved for pedestrians and vehicles, the current algorithms still struggle to detect small, occluded, and truncated objects. In addition, there is limited research on how to improve detection performance in difficult light and weather conditions. Most of the algorithms have been tested on well-recognised datasets such as Caltech and KITTI; however, these datasets have their own limitations. Therefore, this paper recommends that future works should be implemented on more new challenging datasets, such as PIE and BDD100K.

HDG and HDGG: an extensible feature extraction descriptor for effective face and facial expressions recognition

The potential of facial and facial expression recognitions has gained increased interest in social interactions and biometric identification. Earlier facial identification methods suffer from drawbacks due to the lower identification accuracy under difficult lighting conditions. This paper presents two novel new descriptors called Histogram of Directional Gradient (HDG) and Histogram of Directional Gradient Generalized (HDGG) to extracting discriminant facial expression features for better classification accuracy with good efficiency than existing classifiers. The proposed descriptors are based on the directional local gradients combined with SVM (Support Vector Machine) linear classification. To build an efficient face and facial expression recognition, features with reduced dimension are used to boost the performance of the classification. Experiments are conducted on two public-domain datasets: JAFFE for facial expression recognition and YALE for face recognition. The experiment results show the best overall accuracy of 92.12% compared to other existing works. It demonstrates a fast execution time for face recognition ranging from 0.4 to 0.7 s in all evaluated databases.

Exploring presentation attack vulnerability and usability of face recognition systems

Commercial face recognition software intended for the use of access control is evaluated. Most of the systems are to be used with hand-held devices (smartphones). The systems under test also contain three stationary systems designed to unlock doors or other secure entrance systems. While specifics of the systems cannot be gone in-depth under test (due to NDAs), the results of the evaluation of liveness detection (or presentation attack detection) with different complexity levels and template comparison performance are presented. The robustness against presentation attack is compares with the systems usability, and highlight where current commercial of the shelf systems (COTS) stand in that regard. The results focusing on the tradeoff between acceptance, linked with usability, and security are examined, which usually negatively impacts usability. A first extension of the attacks to systems using the NIR spectrum for imaging is also presented. This is mostly limited to stationary systems as they can include dedicated hardware with NIR capabilities. This is their main differentiation to most COTS systems running on smartphones, which do not rely on dedicated hardware. Though exceptions to this already exist for example in Apple devices. It is shown that most of the systems are not secure and not user friendly, having huge problems with difficult lighting conditions while only providing the most basic liveness or presentation attack detection capabilities.

Noise Removal in the Developing Process of Digital Negatives.

Most modern color digital cameras are equipped with a single image sensor with a color filter array (CFA). One of the most important stages of preprocessing is noise reduction. Most research related to this topic ignores the problem associated with the actual color image acquisition process and assumes that we are processing the image in the sRGB space. In the presented paper, the real process of developing raw images obtained from the CFA sensor was analyzed. As part of the work, a diverse database of test images in the form of a digital negative and its reference version was prepared. The main problem posed in the work was the location of the denoising and demosaicing algorithms in the entire raw image processing pipeline. For this purpose, all stages of processing the digital negative are reproduced. The process of noise generation in the image sensors was also simulated, parameterizing it with ISO sensitivity for a specific CMOS sensor. In this work, we tested commonly used algorithms based on the idea of non-local means, such as NLM or BM3D, in combination with various techniques of interpolation of CFA sensor data. Our experiments have shown that the use of noise reduction methods directly on the raw sensor data, improves the final result only in the case of highly disturbed images, which corresponds to the process of image acquisition in difficult lighting conditions.

STAR: A Segmentation-Based Approximation of Point-Based Sampling Milano Retinex for Color Image Enhancement.

Milano Retinex is a family of spatial color algorithms inspired by Retinex and mainly devoted to the image enhancement. In the so-called point-based sampling Milano Retinex algorithms, this task is accomplished by processing the color of each image pixel based on a set of colors sampled in its surround. This paper presents STAR, a segmentation based approximation of the point-based sampling Milano Retinex approaches: it replaces the pixel-wise image sampling by a novel, computationally efficient procedure that detects once for all the color and spatial information relevant to image enhancement from clusters of pixels output by a segmentation. The experiments reported here show that STAR performs similarly to previous point-based sampling Milano Retinex approaches and that STAR enhancement improves the accuracy of the well-known algorithm scale-invariant feature transform on the description and matching of photographs captured under difficult light conditions.

New Carrier Made from Glass Nanofibres for the Colorimetric Biosensor of Cholinesterase Inhibitors.

Cholinesterase inhibitors are widely used as pesticides in agriculture, but also form a group of organophosphates known as nerve chemical warfare agents. This calls for close attention regarding their detection, including the use of various biosensors. One such biosensor made in the Czech Republic is the Detehit, which is based on a cholinesterase reaction that is assessed using a colour indicator—the Ellman’s reagent—which is anchored on cellulose filter paper together with the substrate. With the use of this biosensor, detection is simple, quick, and sensitive. However, its disadvantage is that a less pronounced yellow discoloration occurs, especially under difficult light conditions. As a possible solution, a new indicator/substrate carrier has been designed. It is made of glass nanofibres, so the physical characteristics of the carrier positively influence reaction conditions, and as a result improve the colour response of the biosensor. The authors present and discuss some of the results of the study of this carrier under various experimental conditions. These findings have been used for the development of a modified Detehit biosensor.

Illumination pre‐processing method for face recognition using 2D DWT and CLAHE

This study presents an illumination pre-processing method termed as `Discrete wavelet transform enhanced contrast limited adaptive histogram equalisation' (DWT E-CLAHE) to recognise the front view facial images in the difficult light conditions. A recent image enhancement method CLAHE-DWT motivates to combine the two-dimensional discrete wavelet transform (2D DWT) and CLAHE. The DWT E-CLAHE is implemented as follows: The original image is enhanced using the Gamma intensity correction (GIC); then split into low-frequency and high-frequency components using 2D DWT; finally, to the low-frequency components, the logarithmic transform, GIC and CLAHE are applied in the sequential order. The face recognition of DWT E-CLAHE is made using Gabor magnitude features. The face recognition of CLAHE-DWT is implemented for the first time. The experimental results of DWT E-CLAHE in the various face databases prove the following: (i) The proper selection of parameters of DWT E-CLAHE improves the brightness and contrast of the image. (ii) The recognition accuracy of DWT E-CLAHE in the Carnegie Mellon University (CMU) Pose, Illumination, and Expression (PIE) and Extended Yale B databases are extremely good, since the brightness and contrast are improved significantly. (iii) The performance comparison of DWT E-CLAHE outperforms CLAHE-DWT and state-of-the-art face recognition methods. (iv) DWT E-CLAHE recognises the varying facial expressions.

Augmented Reality in Forest Machine Cabin

Augmented reality human machine interface is demonstrated in the cabin of a forest machine outdoors for the first time in real time. In this work, we propose a system setup and a real-time capable algorithm to augment the operator’s visual field with measurements from the forest machine and its environment. In the demonstration, an instrumented forestry crane and a lidar are used to model the pose of the crane and its surroundings. In our approach, a camera and an inertial measurement unit are used to estimate the pose of the operator’s head in difficult lighting conditions with the help of planar markers placed on the cabin structures. Using the estimate, a point cloud and a crane model are superimposed on the video feed to form an augmented reality view. Our system is tested to work outdoors using a forest machine research platform in real time with encouraging initial results.

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.

Lighting Equilibrium Distribution Maps and Their Application to Face Recognition Under Difficult Lighting Conditions

In this paper, a novel facial-patch based recognition framework is proposed to deal with the problem of face recognition (FR) on the serious illumination condition. First, a novel lighting equilibrium distribution maps (LEDM) for illumination normalization is proposed. In LEDM, an image is analyzed in logarithm domain with wavelet transform, and the approximation coefficients of the image are mapped according to a reference-illumination map in order to normalize the distribution of illumination energy due to different lighting effects. Meanwhile, the detail coefficients are enhanced to achieve detail information emphasis. The LEDM is obtained by blurring the distances between the test image and the reference illumination map in the logarithm domain, which may express the entire distribution of illumination variations. Then, a facial-patch based framework and a credit degree based facial patches synthesizing algorithm are proposed. Each normalized face images is divided into several stacked patches. And, all patches are individually classified, then each patch from the test image casts a vote toward the parent image classification. A novel credit degree map is established based on the LEDM, which is deciding a credit degree for each facial patch. The main idea of credit degree map construction is the over-and under-illuminated regions should be assigned lower credit degree than well-illuminated regions. Finally, results are obtained by the credit degree based facial patches synthesizing. The proposed method provides state-of-the-art performance on three data sets that are widely used for testing FR under different illumination conditions: Extended Yale-B, CAS-PEAL-R1, and CMUPIE. Experimental results show that our FR frame outperforms several existing illumination compensation methods.

INNOVATIV AIRBORNE SENSORS FOR DISASTER MANAGEMENT

Abstract. Modern Disaster Management Systems are based on 3 columns, crisis preparedness, early warning and the final crisis management. In all parts, special data are needed in order to analyze existing structures, assist in the early warning system and in the updating after a disaster happens to assist the crises management organizations. How can new and innovative sensors assist in these tasks? Aerial images have been frequently used in the past for generating spatial data, however in urban structures not all information can be extracted easily. Modern Oblique camera systems already assist in the evaluation of building structures to define rescue paths, analyze building structures and give also information of the stability of the urban fabric. For this application there is no need of a high geometric accurate sensor, also SLC Camera based Oblique Camera system as the OI X5, which uses Nikon Cameras, do a proper job. Such a camera also delivers worth full information after a Disaster happens to validate the degree of deformation in order to estimate stability and usability for the population. Thermal data in combination with RGB give further information of the building structure, damages and potential water intrusion. Under development is an oblique thermal sensor with 9 heads which enables nadir and oblique thermal data acquisition. Beside the application for searching people, thermal anomalies can be created out of humidity in constructions (transpiration effects), damaged power lines, burning gas tubes and many other dangerous facts. A big task is in the data analysis which should be made automatically and fast. This requires a good initial orientation and a proper relative adjustment of the single sensors. Like that, many modern software tools enable a rapid data extraction. Automated analysis of the data before and after a disaster can highlight areas of significant changes. Detecting anomalies are the way to get the focus on the prior area. Also Lidar supports Disaster management by analyzing changes in the DSM before and after the “event”. Advantage of Lidar is that beside rain and clouds, no other weather conditions limit their use. As an active sensor, missions in the nighttime are possible. The new mid-format cameras that make use CMOS sensors (e.g. Phase One IXU1000) can capture data also under poor and difficult light conditions and might will be the first choice for remotely sensed data acquisition in aircrafts and UAVs. UAVs will surely be more and more part of the disaster management on the detailed level. Today equipped with video live cams using RGB and Thermal IR, they assist in looking inside buildings and behind. Thus, they can continue with the aerial survey where airborne anomalies have been detected.

INNOVATIV AIRBORNE SENSORS FOR DISASTER MANAGEMENT

Modern Disaster Management Systems are based on 3 columns, crisis preparedness, early warning and the final crisis management. In all parts, special data are needed in order to analyze existing structures, assist in the early warning system and in the updating after a disaster happens to assist the crises management organizations. How can new and innovative sensors assist in these tasks? <br><br> Aerial images have been frequently used in the past for generating spatial data, however in urban structures not all information can be extracted easily. Modern Oblique camera systems already assist in the evaluation of building structures to define rescue paths, analyze building structures and give also information of the stability of the urban fabric. For this application there is no need of a high geometric accurate sensor, also SLC Camera based Oblique Camera system as the OI X5, which uses Nikon Cameras, do a proper job. Such a camera also delivers worth full information after a Disaster happens to validate the degree of deformation in order to estimate stability and usability for the population. <br><br> Thermal data in combination with RGB give further information of the building structure, damages and potential water intrusion. Under development is an oblique thermal sensor with 9 heads which enables nadir and oblique thermal data acquisition. Beside the application for searching people, thermal anomalies can be created out of humidity in constructions (transpiration effects), damaged power lines, burning gas tubes and many other dangerous facts. <br><br> A big task is in the data analysis which should be made automatically and fast. This requires a good initial orientation and a proper relative adjustment of the single sensors. Like that, many modern software tools enable a rapid data extraction. Automated analysis of the data before and after a disaster can highlight areas of significant changes. Detecting anomalies are the way to get the focus on the prior area. <br><br> Also Lidar supports Disaster management by analyzing changes in the DSM before and after the “event”. Advantage of Lidar is that beside rain and clouds, no other weather conditions limit their use. As an active sensor, missions in the nighttime are possible. <br><br> The new mid-format cameras that make use CMOS sensors (e.g. Phase One IXU1000) can capture data also under poor and difficult light conditions and might will be the first choice for remotely sensed data acquisition in aircrafts and UAVs. <br><br> UAVs will surely be more and more part of the disaster management on the detailed level. Today equipped with video live cams using RGB and Thermal IR, they assist in looking inside buildings and behind. Thus, they can continue with the aerial survey where airborne anomalies have been detected.

Estimation of Tree Stem Attributes Using Terrestrial Photogrammetry with a Camera Rig

We propose a novel photogrammetric method for field plot inventory, designed for simplicity and time efficiency on-site. A prototype multi-camera rig was used to acquire images from field plot centers in multiple directions. The acquisition time on-site was less than two minutes. From each view, a point cloud was generated using a novel, rig-based matching of detected SIFT keypoints. Stems were detected in the merged point cloud, and their positions and diameters were estimated. The method was evaluated on 25 hemi-boreal forest plots of a 10-m radius. Due to difficult lighting conditions and faulty hardware, imagery from only six field plots was processed. The method performed best on three plots with clearly visible stems with a 76% detection rate and 0% commission. Diameters could be estimated for 40% of the stems with an RMSE of 2.8–9.5 cm. The results are comparable to other camera-based methods evaluated in a similar manner. The results are inferior to TLS-based methods. However, our method is easily extended to multiple station image schemas, something that could significantly improve the results while retaining low commission errors and time on-site. Furthermore, with smaller hardware, we believe this could be a useful technique for measuring stem attributes in the forest.

The night vision distance measurement method dedicated for mobile robots

Abstract The paper presents a vision based visual servoing system and active laser triangulation method for distance measurement. The proposed hybrid system is dedicated to mobile robot operating in difficult lighting conditions. The problems caused by the use of the video system in extremely underexposured 3D scene have been discussed and two devices performing the distance measurement together with an analysis measurements have been analyzed.

Long-duration animal tracking in difficult lighting conditions.

High-throughput analysis of animal behavior requires software to analyze videos. Such software typically depends on the experiments’ being performed in good lighting conditions, but this ideal is difficult or impossible to achieve for certain classes of experiments. Here, we describe techniques that allow long-duration positional tracking in difficult lighting conditions with strong shadows or recurring “on”/“off” changes in lighting. The latter condition will likely become increasingly common, e.g., for Drosophila due to the advent of red-shifted channelrhodopsins. The techniques enabled tracking with good accuracy in three types of experiments with difficult lighting conditions in our lab. Our technique handling shadows relies on single-animal tracking and on shadows’ and flies’ being accurately distinguishable by distance to the center of the arena (or a similar geometric rule); the other techniques should be broadly applicable. We implemented the techniques as extensions of the widely-used tracking software Ctrax; however, they are relatively simple, not specific to Drosophila, and could be added to other trackers as well.

Two new specimens for the Bolivian endemic titi monkeys, <i>Callicebus olallae</i> and <i>Callicebus modestus</i>

No abstract

Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions

Making recognition more reliable under uncontrolled lighting conditions is one of the most important challenges for practical face recognition systems. We tackle this by combining the strengths of robust illumination normalization, local texture-based face representations, distance transform based matching, kernel-based feature extraction and multiple feature fusion. Specifically, we make three main contributions: 1) we present a simple and efficient preprocessing chain that eliminates most of the effects of changing illumination while still preserving the essential appearance details that are needed for recognition; 2) we introduce local ternary patterns (LTP), a generalization of the local binary pattern (LBP) local texture descriptor that is more discriminant and less sensitive to noise in uniform regions, and we show that replacing comparisons based on local spatial histograms with a distance transform based similarity metric further improves the performance of LBP/LTP based face recognition; and 3) we further improve robustness by adding Kernel principal component analysis (PCA) feature extraction and incorporating rich local appearance cues from two complementary sources--Gabor wavelets and LBP--showing that the combination is considerably more accurate than either feature set alone. The resulting method provides state-of-the-art performance on three data sets that are widely used for testing recognition under difficult illumination conditions: Extended Yale-B, CAS-PEAL-R1, and Face Recognition Grand Challenge version 2 experiment 4 (FRGC-204). For example, on the challenging FRGC-204 data set it halves the error rate relative to previously published methods, achieving a face verification rate of 88.1% at 0.1% false accept rate. Further experiments show that our preprocessing method outperforms several existing preprocessors for a range of feature sets, data sets and lighting conditions.

An Intelligent Active Video Surveillance System Based on the Integration of Virtual Neural Sensors and BDI Agents

In this paper we present an intelligent active video surveillance system currently adopted in two different application domains: railway tunnels and outdoor storage areas. The system takes advantages of the integration of Artificial Neural Networks (ANN) and symbolic Artificial Intelligence (AI). This hybrid system is formed by virtual neural sensors (implemented as WiSARD–like systems) and BDI agents. The coupling of virtual neural sensors with symbolic reasoning for interpreting their outputs, makes this approach both very light from a computational and hardware point of view, and rather robust in performances. The system works on different scenarios and in difficult light conditions.