Background Light Conditions Research Articles

3D target detection and spectral classification for single-photon LiDAR data.

3D single-photon LiDAR imaging has an important role in many applications. However, full deployment of this modality will require the analysis of low signal to noise ratio target returns and very high volume of data. This is particularly evident when imaging through obscurants or in high ambient background light conditions. This paper proposes a multiscale approach for 3D surface detection from the photon timing histogram to permit a significant reduction in data volume. The resulting surfaces are background-free and can be used to infer depth and reflectivity information about the target. We demonstrate this by proposing a hierarchical Bayesian model for 3D reconstruction and spectral classification of multispectral single-photon LiDAR data. The reconstruction method promotes spatial correlation between point-cloud estimates and uses a coordinate gradient descent algorithm for parameter estimation. Results on simulated and real data show the benefits of the proposed target detection and reconstruction approaches when compared to state-of-the-art processing algorithms.

Physical-Layer Network Coding Enhanced Visible Light Communications Using RGB LEDs

Compared with traditional radio frequency (RF)-based techniques, the advantages of wider bandwidth, higher security, and stronger electromagnetic immunity (EMI) capability make visible light communications (VLC) a good candidate technology for the 6th generation (6G) wireless communications. Red, green, and blue (RGB) light-emitting diodes (LEDs) based VLC has become an important research branch due to its low price and high reliability. However, the saturation of photodiode (PD) caused by the ambient background light may seriously degrade the bit error rate (BER) performance of an RGB-VLC system's three spatially uncoupled information streams (i.e., red, green, and blue LEDs can transmit different data packets simultaneously) in practical applications. To mitigate the ambient light interference in point-to-point RGB-VLC systems, we propose, PNC-VLC, a network-coded scheme that uses two LEDs with the same color at the transmitter to transmit two different data streams and we make use of the naturally overlapped signals at the receiver to formulate physical-layer network coding (PNC). The adaptivity of PNC-VLC could effectively improve the BER degradation problem caused by the saturation of PD under the influence of ambient light. We conducted simulations based on the parameters of commercial off-the-shelf (COTS) products to prove the superiority of the PNC-VLC under the influence of four typical illuminants. Simulation results show that the PNC-VLC system can maintain a better and more stable system BER performance under different ambient background light conditions. Remarkably, with 2/3 throughput efficiency, PNC-VLC can bring 133.3% gain to the BER performance when compared with the traditional RGB-VLC systems under the Illuminant A interference model, making it a good option for VLC with unpredictable ambient background interferences.

Research on Improving Denoising Performance of ROI Computer Vision Method for Transmission Tower Displacement Identification

The health monitoring technology of transmission towers based on vibration data had become a research hotspot. At present, vibration data mainly relied on sensors installed on the tower, which was time-consuming and laborious. Nevertheless, the ROI computer vision method could achieve long-distance, multi-point, and non-contact monitoring, which offers a new possibility for the structure-safety identification of power transmission towers. However, transmission towers are generally located in the field environment, and the background is complicated, resulting in the ROI key point method for vibration data acquisition encountering various types of noise. Thus, the key point in practice was clearing the noise and reducing the impact of noise on identification accuracy. The subpixel corner method was used to detect a minor error with the research object of pixel sets. The dilation + erosion method could reduce image noise. Under white noise with a variance of 0.05, the dilation + erosion could reduce average error (Emae) and mean square error (Emse) by 27% and 23% and increase percentages of data with absolute error less than 5 mm and 10 mm in the total number of data (σ5 and σ10) by 8% and 4.3%, respectively, which was compared to median filter + sharpen. The histogram equalization method was used to balance background lighting conditions and reduce identification errors from non-uniform illumination. Emae and Emse were reduced by 92% and 99%, and σ5 and σ10 were increased by 5 and 3 times, respectively, and the identification time was cut by 62% with the histogram equalization method. Under white noise with a variance of 0.15 or lower, the three methods combined increased the numerical stability of Emae, Emse, σ5, and σ10, which indicated that the combination of the three methods could improve the anti-noise performance, robustness, and identification accuracy of the ROI computer vision method for transmission tower displacement identification.

Resting state electroretinography: An innovative approach to intrinsic retinal function monitoring.

The electroretinogram (ERG) represents the biopotential evoked by the retina in response to a light stimulus. The flash evoked ERG (fERG) is the ERG modality most frequently used clinically to diagnose and monitor retinal disorders. We hereby present a new method to record spontaneous retinal activity, without the use of a flash stimulus, that we named the resting-state ERG (rsERG). The recordings were done in normal subjects under light- and dark-adaptation and with different background light conditions (i.e., variations of wavelength and intensity). Additionally, rsERG recordings were obtained in five patients with retinopathies. The signals were subsequently analyzed in the frequency domain, extracting both periodic (i.e., frequency peaks) and aperiodic (i.e., background trend) components of the signal. The later was further assessed through a multifractal analysis using Wavelet Leaders. Results show that, irrespective of the recording conditions used, the rsERG always includes the same 90 Hz component; a frequency component also present in the fERG response, suggesting a retinally-intrinsic origin. However, in addition, the fERGs also includes a low-frequency component which is absent in the rsERGs, a finding supporting a retinally-induced origin. Comparing rsERGs with fERGs in selected patients with various retinal disorders indicates that the two retinal signals are not always similarly affected (either as a result of underlying retinal pathology or otherwise), suggesting an added value in the assessment of retinal function. Thus, the rsERG could have a similar role in clinical visual electrophysiology as that of the resting-state EEG in neurology namely, to quantify changes in spontaneous activity that result from a given disease processes.

Real Time Indian Traffic Sign Detection using Image Processing and CNN

Driver Assistance and Monitoring System plays a very important role in traffic management especially in Indian roads. It eventually reduces the accidents and major injuries. DAMS (Driver Assistance and Monitoring System) give the safety and driving comfort. The main motto of our work is to design the effective methodology for the assistance and driver monitoring system which alerts the driver when it detects the road signs so that driver can take the appropriate action. The proposed methodology detects a road signs which is present in the dataset under cluttered background and different lighting conditions. The proposed work detecting the road sign based on colour and shape. The edge of the road sign is detected using canny edge operator. The images are enhanced and removed the noise using median filters. The images are classified as stop, no entry, speed limit using Convolutional Neural Network (CNN) classifier.

A 16-Channel Analog CMOS SiPM With On-Chip Front-End for D-ToF LiDAR

This article presents a 16-channel analog silicon photomultiplier (SiPM) with on-chip front-end for direct time-of-flight (D-ToF) LiDAR applications. The proposed receiver is mainly composed of 16-channel SiPM, variable gain amplifier (VGA) and time-to-digital converter (TDC). Each SiPM channel consists of 256 microcells, and their outputs are connected to a common output terminal in parallel. A novel active quenching circuit is adopted to reduce the long exponential tail in conventional SiPM and enable the capability of multi-echo detection. Current steering circuits are adopted within microcells to make the output current of SiPM immune to SPAD gain variations. The receiver was fabricated in 180-nm HV CMOS technology and integrated into the 16-line LiDAR prototype with optical components. Measurement results show that the sensor is capable of 20 m range imaging with 3 cm accuracy under 40 klux background light conditions. With the mechanical scanning system, a high-resolution image ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$240\times16$ </tex-math></inline-formula> ) can be obtained.

Visibility classification and influencing-factors analysis of airport: A deep learning approach

This paper discusses the visibility classification and influencing-factor analysis of an airport, which were carried out through a data-driven deep learning approach and multiple nonlinear regression analysis. First, a deep integrated model for airport visibility classification was developed, and the relationship between runway visual range (RVR) and surface meteorological elements for different reasons was analyzed. To extract more low-level features from nighttime images, the original images were transformed into pseudo-color images, and the image pairs were input into the classification model. The proposed deep integrated model combined two popular convolutional neural network (CNN) models: VGG-16 and Xception. The results showed that the accuracy of the proposed model was 87.64%, with the F1-score being 88.58%; it achieved the best performance among other well-known experimental CNNs. Afterward, the relationships between RVR and meteorological optical range (MOR), source light intensity (I), and background light (BL) were analyzed, and the results showed that RVR increased with increasing I under the same MOR and BL conditions; however, it decreased with increasing log (BL) values under the same I and MOR conditions. RVR increased as MOR increased when other conditions remained unchanged. Subsequently, the multivariate regression analysis was conducted to fit the relationship between MOR and surface meteorological elements, and the results showed that the cubic curve was the best-fit curve with R-square values of 0.937 and 0.860 in December 2019 and March 2020, respectively. Finally, combined with the analysis of the factors influencing the RVR, a significant negative correlation was observed with relative humidity, along with a significant positive correlation with temperature and a positive correlation with average wind speed in the winter of 2019 and spring of 2020. However, the pressure factor showed the opposite correlation, possibly because the arrival of cold air in winter increases the ground pressure, which is conducive for the dissipation of pollutants. Meanwhile, the increase in temperature and decrease in pressure in spring increases the chance of disturbances in the atmosphere, thereby increasing the likelihood of adverse visibility factors. ◆ Pseudo-color images were found beneficial for improving the accuracy of visibility identification. ◆ An integrated model combined VGG-16 and Xception achieved the best performance compared to that of other popular models. ◆ The relationship between RVR and MOR, I, and BL was found. ◆ The multivariate regression analysis between MOR and surface meteorological elements in different seasons was conducted. ◆ There is a correlational relationship between RVR and surface meteorological elements.

Improvement of Accuracy and Precision of the LiDAR System Working in High Background Light Conditions

Background light noise is one of the major challenges in the design of Light Detection and Ranging (LiDAR) systems. In this paper, we build a single-beam LiDAR module to investigate the effect of light intensity on the accuracy/precision and success rate of measurements in environments with strong background noises. The proposed LiDAR system includes the laser signal emitter and receiver system, the signal processing embedded platform, and the computer for remote control. In this study, two well-known time-of-flight (ToF) estimation methods, which are peak detection and cross-correlation (CC), were applied and compared. In the meanwhile, we exploited the cross-correlation technique combined with the reduced parabolic interpolation (CCP) algorithm to improve the accuracy and precision of the LiDAR system, with the analog-to-digital converter (ADC) having a limited resolution of 125 mega samples per second (Msps). The results show that the CC and CCP methods achieved a higher success rate than the peak method, which is 12.3% in the case of applying emitted pulses 10 µs/frame and 8.6% with 20 µs/frame. In addition, the CCP method has the highest accuracy/precision in the three methods reaching 7.4 cm/10 cm and has a significant improvement over the ADC’s resolution of 1.2 m. This work shows our contribution in building a LiDAR system with low cost and high performance, accuracy, and precision.

Time-gated Raman spectroscopy for biomedical application under ambient or strong background light conditions

Many biomedical applications require measurements of Raman spectra of tissue under ambient lighting conditions. However, the background light often swamps the weaker Raman signal. The use of time-gated (TG) Raman spectroscopy based on a single photon avalanche diode (SPAD) operating in time-correlated single photon counting and near-infrared laser excitation was investigated for acquisition of Raman spectra and spectral images of biological tissue. The results obtained using animal tissue samples (adipose tissue and muscle) show that the time gating modality enables measurement of Raman spectra under background light conditions of similar quality as conventional continuous wave Raman spectroscopy in the absence of background light. Optimal suppression of the background light was observed for time gate widths of 300–1000 ps. The results also showed that TG Raman spectroscopy was able to detect subtle spectral differences required for medical diagnostics, such as differences in Raman spectra of cancer and normal tissue. While the current instrument required scanning of the grating in order to obtain full Raman spectra, leading to impractical times for multi-wavenumber Raman mapping, imaging time could be drastically reduced by spectral multiplexing (compressed detection) using digital micromirror devices or by using SPAD arrays.

Development of a dynamic intelligent recognition system for a real-time tracking robot

&lt;p&gt;Nowadays, the development of computer vision technology help to overcome track and identify humans within a location in the complex environment through mobile robots, which gives the motivation to presents a vision-based approach to a mobile security robot. The proposed system utilizes a wireless camera to detect the objects in the field of robot view. Principle component analysis (PCA) algorithm and filters are used to implement and demonstrate the process of the images. This gives the designed system the ability to recognize objects independently from current light conditions. Frame tracking in the images uses an attention system to get an estimate of the position of a person. This estimate helps the applied camera to identify objects with changing background lighting conditions such as a fire inside a building. By using this estimate, the applied camera could identify objects with changing background lighting conditions such as a fire inside premises. The system has been tested using the MATLAB environment, and the empirical performance explains the efficiency and strongness of the suggested device.&lt;/p&gt;

A Deep Convolutional Neural Network Approach to Sign Alphabet Recognition

In this paper, we present an application that has been developed to be used as a tool for the purposes of learning sign language for beginners that utilizes hand detection as part of the process. It uses a skin-color modelling technique, such as explicit thresholding in the skin-color space, which is based on modeling skin-color spaces. This predetermined range of skin-colors is used to determine how pixels (hand) will be extracted from non-pixels (background). To classify the images, convolutional neural networks (CNN) were fed the images for the creation of the classifier. The training of the images was done using Keras. A uniform background and proper lighting conditions enabled the system to achieve a test accuracy of 93.67%, of which 90.04% was attributed to ASL alphabet recognition, 93.44% for number recognition and 97.52% recognition of static words, surpassing other studies of the type. An approach which is based on this technique is used for fast computation as well as real-time processing. Deaf-dumb people face a number of social challenges as the communication barrier prevents them from accessing basic and essential services of the life that they are entitled to as members of the hearing community. In spite of the fact that a number of factors have been incorporated into the innovations in the automatic recognition of sign language, an adequate solution has yet to be reached because of a number of challenges. As far as I know, the vast majority of existing works focus on developing vision based recognizers by deriving complex feature descriptors from captured images of the gestures and applying a classical pattern analysis technique. Although utilizing these methods can be effective when dealing with small sign vocabulary captures with a complex and uncontrolled background, they are very limited when dealing with large sign vocabulary. This paper proposes a method for analyzing and representing hand gestures, which acts as the core component of the vocabulary for signing languages, using a deep convolutional neural networks (CNN) architecture. On two publicly accessible datasets (the NUS hand posture dataset and the American fingerspelling A dataset), the method was demonstrated to be more accurate in recognizing hand postures.

Wavelet-Based Optical Flow Analysis for Background-Oriented Schlieren Image Processing

A wavelet-based optical flow analysis (wOFA) method for processing background-oriented schlieren (BOS) images is presented and demonstrated on synthetic and experimental data. Optical flow is inherently well suited to BOS, because the background pattern and lighting conditions are specified and controlled by the user and can be chosen to play to the strengths of optical flow processing. Analysis of the synthetic BOS data show that a two-dimensional sinusoidal background produces the highest reconstruction accuracy for both wOFA and iterative least squares (ILS) algorithms. wOFA outperforms ILS in terms of overall accuracy for displacement fields with sufficiently high spatial frequency content. In addition, wOFA provides higher spatial resolution, about an order of magnitude in terms of the total number of pixels in the final BOS image. Finally, wOFA is demonstrated on two sets of experimental data: a heat gun plume experiment with nearly ideal imaging characteristics, and experiments in a supersonic wind tunnel flow with more realistic restrictions on the acquisition of images. BOS images computed with wOFA are shown to have higher spatial resolution and sensitivity than ILS, without introducing additional noise. Therefore, wOFA of BOS images are able to reveal flow features not detected by ILS analysis.

Gesture Recognition Method Based on Attention Mechanism for Complex Background

Human-computer interaction technology is still an unaccomplished goal due to complex background and changeable lighting conditions. A two-stage gesture recognition method is proposed to improve the accuracy of gesture recognition. The first stage combines attention mechanism and atrous spatial pyramid pooling (ASPP) which aims to segment gesture from complex background. The second stage uses a two stream convolutional neural network, combines features from the original picture and the output of the first stage, aims to realize the classification of gestures. It can recognize gestures more accurately compared with other gesture recognition methods.

A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network

In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In this paper, a banana stalk segmentation method based on a lightweight multi-feature fusion deep neural network (MFN) is proposed. The proposed network is mainly composed of encoding and decoding networks, in which the sandglass bottleneck design is adopted to alleviate the information a loss in high dimension. In the decoding network, a different sized dilated convolution kernel is used for convolution operation to make the extracted banana stalk features denser. The proposed network is verified by experiments. In the experiments, the detection precision, segmentation accuracy, number of parameters, operation efficiency, and average execution time are used as evaluation metrics, and the proposed network is compared with Resnet_Segnet, Mobilenet_Segnet, and a few other networks. The experimental results show that compared to other networks, the number of network parameters of the proposed network is significantly reduced, the running frame rate is improved, and the average execution time is shortened.

Deep Learning-Based Sign Language Digits Recognition From Thermal Images With Edge Computing System

The sign language digits based on hand gestures have been utilized in various applications such as human-computer interaction, robotics, health and medical systems, health assistive technologies, automotive user interfaces, crisis management and disaster relief, entertainment, and contactless communication in smart devices. The color and depth cameras are commonly deployed for hand gesture recognition, but the robust classification of hand gestures under varying illumination is still a challenging task. This work presents the design and deployment of a complete end-to-end edge computing system that can accurately provide the classification of hand gestures captured from thermal images. A thermal dataset of 3200 images was created with each sign language digit having 320 thermal images. The solution presented here utilizes live images taken from a low-resolution thermal camera of 32×32 pixels, feeding into a novel light weight deep learning model based on bottleneck motivated from deep residual learning for classification of hand gestures. The edge computing system presented here utilizes Raspberry pi with a thermal camera making it highly portable. The designed system achieves an accuracy of 99.52% on the test data set with an added advantage of accuracy being invariable to background lighting conditions as it is based on thermal imaging.

Material and illumination model optimization of OPFET for visible light communication

Through material and illumination model optimization, we seek to investigate the potential of enhancing the performance of Optical Field Effect Transistor (OPFET)-based detector-cum-amplifier in Visible Light Communication (VLC) applications. This paper studies Si, InP, and GaAs materials and the buried-gate front-illuminated and generalized OPFET models. The detector metrics namely responsivity, 3-dB bandwidth, Signal-to-Noise Ratio, and the unity-gain cut-off frequency have been calculated. The results of the study confirm that on the whole, the generalized model has superior bandwidth performance to the buried-gate and back-illuminated models under low background lighting communication applications. GaAs generalized OPFET shows the largest detection/amplification bandwidth of 68.4/22.2 GHz at an intensity of 1019 /m2-s with a responsivity of 1×107 A/W. The findings point to potential use in VLC applications involving data rates of 100 Gb/s and above. Under high background lighting conditions, at an intensity of 1022 /m2-s, the InP generalized model exhibits the highest combined bandwidth of 22.1 MHz and a responsivity of 9.6×103 A/W. The detectors show Signal-to-Noise ratios exceeding 200 dB. The GaAs OPFETs exhibit a maximum 3 dB-cum-amplification bandwidth in the far gigahertz range, while the InP OPFET in the near gigahertz range, and the Si OPFET in the near megahertz range. These three OPFETs have applications respectively in high, medium, and low data rate VLC. All the device models exhibit significantly high responsivities. The results have been analyzed for photoconductive, photovoltaic, and series resistance effects. They provide the basis for further research.

Cascade CenterNet: Robust Object Detection for Power Line Surveillance

The use of object detection methods is becoming increasingly important in the internet of smart energy. Accurate detection of power line region and suspicious objects can reduce the probability of accidents and save manpower. However, the noisy outdoor background and time-varying lighting conditions bring difficulties to those tasks. To address those challenges, this paper investigates mainstream methods of power line region surveillance and proposes a new method for improving the accuracy of power line region and risk object detection by modeling the heat map branch of CenterNet, which is the most representative of anchor-free detectors, with a cascade guiding structure and an improved loss function. Finally, comprehensive experiments are conducted to compare some state-of-the-art detectors and the proposed model on power line surveillance tasks. The test results demonstrate both the effectiveness and superiority of the proposed method.

Central Visual Field Sensitivity With and Without Background Light Given to the Nontested Fellow Eye in Glaucoma Patients.

This study showed the difference of monocular visual sensitivity between with and without background light given to the nontested fellow eyes in glaucoma patients. Monocular sensitivity measurements of the worse eyes with fellow eye's background light conditions should carefully be considered when assessing the impact of functional impairment in glaucoma patients. The purpose of this study was to investigate the difference between monocular sensitivities measured with and without background light given to the nontested fellow eye in glaucoma patients using a new perimeter named "imo." In this cross-sectional study, we examined 102 eyes of 51 patients (mean age, 65.1±14.9 y) with open-angle glaucoma who were affected with at least 1 significant point in the central 10 degrees. We conducted a routine ophthalmic examination and visual field testing using the Humphrey Field Analyzer 24-2 and 10-2 programs. The eyes were assigned to "better" and "worse" categories based on the visual acuity and central visual thresholding. Subsequently, we compared the central visual sensitivities with and without background light given to the nontested fellow eye. The mean sensitivity (MS) in the central 5 points of the visual field of the worse eyes was better when measured with background light than without background light (P=0.037) given to the nontested fellow eye. No significant difference was seen among the MS in the visual field of the better eyes. After dividing the patients into low (n=25) and high sensitivity (n=26) groups, only the low sensitivity group in worse eyes had higher MS with background light than without background light (P<0.05) given to the nontested fellow eye. Monocular sensitivities measured with background light given to the nontested fellow eye were higher than those without background light in the worse eye group of glaucoma patients. Monocular MS measurements of the worse eyes with fellow eye's background light conditions and their related indices should thus carefully be considered when assessing the impact of functional impairment in glaucoma patients.

Development of Willow Tree Yield-Mapping Technology.

With today’s environmental challenges, developing sustainable energy sources is crucial. From this perspective, woody biomass has been, and continues to be, a significant research interest. The goal of this research was to develop new technology for mapping willow tree yield grown in a short-rotation forestry (SRF) system. The system gathered the physical characteristics of willow trees on-the-go, while the trees were being harvested. Features assessed include the number of trees harvested and their diameter. To complete this task, a machine-vision system featuring an RGB-D stereovision camera was built. The system tagged these data with the corresponding geographical coordinates using a Global Navigation Satellite System (GNSS) receiver. The proposed yield-mapping system showed promising detection results considering the complex background and variable light conditions encountered in the outdoors. Of the 40 randomly selected and manually observed trees in a row, 36 were successfully detected, yielding a 90% detection rate. The correctly detected tree rate of all trees within the scenes was actually 71.8% since the system tended to be sensitive to branches, thus, falsely detecting them as trees. Manual validation of the diameter estimation function showed a poor coefficient of determination and a root mean square error (RMSE) of 10.7 mm.

Active-Reset for the N+P Single-Ended SPAD Used in the NIR LiDAR Receivers

A monolithic resistorless circuit has been designed for active reset of the N+P single-ended (common anode) single-photon avalanche diode (SPAD). This type of SPAD has enhanced the photon detection efficiency in the near-infrared (NIR) region relatively to the P+N (two-ended) SPAD. Due to this fact, the N+P SPAD is a better candidate for the light detection and range (LiDAR) working in the NIR region. The circuit is fabricated in a standard 0.18- $\mu \text{m}$ CMOS image sensor process. The dead time after each photon detection is adjustable; the minimum measured value is 4 ns. The maximum photon count rate corresponding to this dead time is ${2.5}\cdot {10}^{{8}}$ photons/s. This circuit guarantees precise repeatable response, short and well-controlled dead time, and after-pulsing effect reduction. All these are essential for many SPAD applications and crucial for increasing the saturation level of the silicon photo multiplier (SiPM)-based LiDAR systems working in strong background light conditions on sunny day.