Blind Detection Research Articles

A Cost-Effective Blind Spot Detection System with High Recall Rate using Deep Learning and a Comparative Analysis of Implementation Hardware Platforms

A Cost-Effective Blind Spot Detection System with High Recall Rate using Deep Learning and a Comparative Analysis of Implementation Hardware Platforms

Tracing gaseous filaments connected to galaxy clusters: The case study of Abell 2744

Filaments connected to galaxy clusters are crucial environments for studying the build up of cosmic structures as they funnel matter towards the clusters' deep gravitational potentials. Identifying gas in filaments is a challenge, due to their lower density contrast, which produces faint signals. Therefore, the best opportunity to detect these signals is in the outskirts of galaxy clusters. We revisited the X-ray observation of the cluster Abell 2744, using statistical estimators of the anisotropic matter distribution to identify filamentary patterns around it. We report, for the first time, the blind detection of filaments connected to a galaxy cluster from X-ray emission using a filament-finder technique and a multipole decomposition technique. We compare this result with filaments extracted from the distribution of spectroscopic galaxies using the same two approaches. This allowed us to demonstrate the robustness and reliability of our techniques in tracing the filamentary structure of three and five filaments connected to Abell 2744, in two and three dimensions, respectively.

Required Field of View of a Sensor for an Advanced Driving Assistance System to Prevent Heavy-Goods-Vehicle to Bicycle Accidents

Accidents involving cyclists and trucks are among the most severe road accidents. In 2021, 199 cyclists were killed in accidents involving a truck in the EU. The main accident situation is a truck turning right and a cyclist going straight ahead. A large proportion of these accidents are caused by the inadequate visibility in an HGV (Heavy Goods Vehicle). The blind spot, in particular, is a significant contributor to these accidents. A BSD (Blind Spot Detection) system is expected to significantly reduce these accidents. There are only a few studies that estimate the potential of assistance systems, and these studies include a combined assessment of cyclists and pedestrians. In the present study, accident simulations are used to assess a warning and an autonomously intervening assistance system that could prevent truck to cyclist accidents. The main challenges are local sight obstructions such as fences, hedges, etc., rule violations by cyclists, and the complexity of correctly predicting the cyclist’s intentions, i.e., detecting the trajectory. Taking these accident circumstances into consideration, a BSD system could prevent between 26.3% and 65.8% of accidents involving HGVs and cyclists.

Research on target detection and recognition system of autonomous driving based on deep learning

Abstract. Autonomous driving technology relies heavily on advanced target detection and recognition systems to ensure safety and efficiency. This essay explores how deep learning has revolutionized these systems in four key areas: lane detection, detection of obscured vehicle parts, blind spot detection, and multi-target detection. Traditional methods often struggle under challenging conditions, but deep learning approaches, including Convolutional Neural Networks (CNNs) and Fully Convolutional Networks (FCNs), offer superior performance by analyzing complex features from raw data. Techniques like the Detection of Incomplete Vehicles using Deep Learning and Image Inpainting (DIDA) enhance safety by reconstructing obscured vehicle parts. In blind spot detection, models such as Sep-Res-SE blocks provide an effective, cost-efficient alternative to radar systems. The Adaptive Perceive SSD (AP-SSD) framework improves multi-target detection accuracy and real-time tracking by incorporating advanced feature extraction and temporal analysis. The essay concludes with future research directions aimed at refining real-time capabilities, expanding datasets, and exploring collaborative learning to further enhance autonomous driving technology.

Multiwavelength Optical Rotation Detection: An Effective Approach for the Recognition of Analytical and Semi‐Preparative HPLC Enantioseparation of the Chiral Pheromone Olean and Its Stereochemical Characterization

ABSTRACTOlean is the chiral spiroacetal sex pheromone of the female olive fruit fly Bactrocera oleae. Laboratory tests have demonstrated that the (R)‐(−)‐olean enantiomer is active on males, whereas females respond to (S)‐(+)‐olean. Here we present the first HPLC enantioseparation of olean using polysaccharide derivatives as chiral stationary phases and a polarimetric detector equipped with a micro‐flow cell capable of detecting optical rotation at six different wavelengths. Unlike blind UV detection, the polarimetric detector allows the chiral spiroacetal, which lacks a chromophore, to be detected as bisegnate peaks, indicating the opposite sign of the optical rotation. The HPLC enantioseparation was optimized on the coated type amylose‐based Chiralpak AS‐H CSP using a mobile phase consisting of n‐hexane‐2‐propanol 99.99:0.01 (v/v). These conditions were scaled up to a semi‐preparative level and allowed resolution of 2.5 mg of racemic sample in 5 min. Multiwavelength optical rotation detection during HPLC enantioseparation of racemic samples provides a direct readout of the stereochemistry of olean and allows tracking of virtual optical rotation dispersion curves without the need for preliminary collection of enantiomeric samples by semi‐preparative HPLC.

On-orbit spectral characteristics analysis of the greenhouse gases monitoring instrument: Spectral wavelength stability and instrumental line shape stability

The Greenhouse Gases Monitoring Instrument (GMI) is a carbon satellite payload developed based on the principle of spatial heterodyne spectroscopy technology, which is specifically designed for the global analysis of greenhouse gases (CO2 and CH4) “sources” and “sinks”. Due to the low concentration and minimal gradient variations of CO2 and CH4 in the atmosphere, higher precision is required for their retrieval. Vibrations during satellite launch and harsh space environments during on-orbit operation may cause changes in the performance of various payload components, resulting in decreased quality of spectrum products and retrieval precision. This paper proposes a set of on-orbit spectral characteristic evaluation methods tailored for the GMI to monitor the quality of its spectrum. It also develops an adaptive blind pixel detection and correction algorithm specifically for the GMI and optimizes the interferogram processing flow algorithm. On-orbit spectral calibration is performed, and methods to evaluate spectral characteristic parameters have been established. The analysis focuses on the variations of the spectral characteristics in the CO2-1 bands (1.575 μm) of the GMI during one-year of on-orbit calibration spectrum. The initial spectral wavenumber offset is 0.133 cm−1 after entering orbit, and the average spectral wavenumber offset is 0.0313 cm−1 during stable operation. During the one-year period, the maximum variation in the instrumental line shape function of the GMI is 0.006 cm−1. The observed spectrum obtained in nadir observation mode, underwent to accuracy verification. The results demonstrate consistency between the spectral peak wavenumbers and the relative trend changes of the observed and theoretical spectrum, with an average relative residual of 0.987%.

Ego-Vehicle Speed Correction for Automotive Radar Systems Using Convolutional Neural Networks.

The development of autonomous driving vehicles has increased the global demand for robust and efficient automotive radar systems. This study proposes an automotive radar-based ego-vehicle speed detection network (AVSD Net) model using convolutional neural networks for estimating the speed of the ego vehicle. The preprocessing and postprocessing methods used for vehicle speed correction are presented in detail. The AVSD Net model exhibits characteristics that are independent of the angular performance of the radar system and its mounting angle on the vehicle, thereby reducing the loss of the maximum detection range without requiring a downward or wide beam for the elevation angle. The ego-vehicle speed is effectively estimated when the range-velocity spectrum data are input into the model. Moreover, preprocessing and postprocessing facilitate an accurate correction of the ego-vehicle speed while reducing the complexity of the model, enabling its application to embedded systems. The proposed ego-vehicle speed correction method can improve safety in various applications, such as autonomous emergency braking systems, forward collision avoidance assist, adaptive cruise control, rear cross-traffic alert, and blind spot detection systems.

Implementation of Wide Angle FoV Radar Module for ADAS Systems

In this study, we propose the wide field of view (FoV) radar module for autonomous vehicles. The proposed wide FoV radar (WFR) module was constructed using of an RF module comprising wide beamwidth microstrip patch antennas, an AWR1642 radar sensor chip, and a control module. To achieve a wide FoV of 150° using the fabricated radar module, the 3-dB beamwidth characteristic of the applied microstrip patch antenna had to wider than 150°. The patch antenna was designed using a comb-line structure along 10-by-1 array structure, each radiator characterized by a shorted patch structure, such as a planar inverted-F antenna. The designed antenna was then fabricated on the same board surface as the sensor chip. To identify the characteristics of the implemented radar module, a trihedral corner reflector with a radar-cross-section of 180 m2 was used as the reflector target, and the CA-CFAR (cell averaging constant false alarm rate) target detection algorithm was applied. The measurement results, showed good detection performance of the radar in the view angle of 150°, from -75° to +75°, and a broad bandwidth of 4 GHz in the 77–81 GHz millimeter band. Therefore, the proposed WFR is applicable for used in blind spot detection sensors in autonomous vehicles.

Analysis of Advanced Driver-Assistance Systems for Safe and Comfortable Driving of Motor Vehicles.

This paper aims to thoroughly examine and compare advanced driver-assistance systems (ADASs) in the context of their impact on safety and driving comfort. It also sought to determine the level of acceptance and trust drivers have in these systems. The first chapter of this document describes the sensory detectors used in ADASs, including radars, cameras, LiDAR, and ultrasonics. The subsequent chapter presents the most popular driver assistance systems, including adaptive cruise control (ACC), blind spot detection (BSD), lane keeping systems (LDW/LKS), intelligent headlamp control (IHC), and emergency brake assist (EBA). A key element of this work is the evaluation of the effectiveness of these systems in terms of safety and driving comfort, employing a survey conducted among drivers. Data analysis illustrates how these systems are perceived and identified areas requiring improvements. Overall, the paper shows drivers' positive reception of ADASs, with most respondents confirming that these technologies increase their sense of safety and driving comfort. These systems prove to be particularly helpful in avoiding accidents and hazardous situations. However, there is a need for their further development, especially in terms of increasing their precision, reducing false alarms, and improving the user interface. ADASs significantly contribute to enhancing safety and driving comfort. Yet, they are still in development and require continuous optimization and driver education to fully harness their potential. Technological advancements are expected to make these systems even more effective and user-friendly.

A novel comprehensive method for weak signal blind detection based on adaptive quasi-periodic potential stochastic resonance and its application in bearing fault detection

In order to solve the common output saturation of stochastic resonance systems and the limitation of classical index SNR for blind detection, a novel adaptive quasi-periodic potential stochastic resonance blind detection method is proposed. First, a model of quasi-periodic potential stochastic resonance (QPPSR) possessing infinite steady state is constructed and analyzed for its structure change pattern. The superior performance of the model is verified by using the fourth-order Runge–Kutta algorithm. Secondly, the mechanism of QPPSR is analyzed using the probability flow method, which reveals the relationship between system parameters and performance. Again, a novel comprehensive blind detection index (CBDI) is exquisitely constructed to make up for the shortcomings of each indicator. Finally, CBDI and QPPSR are constructed into an adaptive blind detection system and applied to bearing fault detection. The results analyzed by experiments verify the good engineering application prospect of CBDI-QPPSR.

AI‐Assisted Design of Printed Edge‐Fed Non‐Uniform Zig‐Zag Antenna for mm‐Wave Automotive Radar

AbstractIn this paper, the design of a novel horizontally polarized single‐layer antenna for 77 (GHz) automotive radar applications is4 addressed. An innovative non‐uniform zig‐zag parametrization of the antenna layout is considered to enable a more flexible control on both the impedance matching in the working frequency band and the shaping of the radiated beam pattern with respect to a standard (uniform) one without compromising the linear (horizontal) polarization of the radiated field. Such a polarization guarantees a lower back‐scattering from road pavements, resulting in a reduced amount of clutter and thus allowing a more robust target detection. Moreover, the single‐layer layout has several advantages in terms of fabrication simplicity/costs and mechanical robustness to vibrations. The design of the proposed non‐uniform zig‐zag antenna (NZA) is performed through a customized implementation of the System‐by‐Design (SbD) approach that fruitfully combines machine learning and evolutionary optimization to efficiently deal with the computational complexity at hand. An extensive numerical validation, dealing with designs of different lengths, verifies the high performance of the NZA in terms of beam direction deviation (e.g., BDD < 1 (deg)), sidelobe level (e.g., SLL < −18.2 (dB)), and polarization ratio (e.g., PR > 20 (dB)) within the working frequency band (GHz), as well as its superiority over competitive designs. Finally, the realization of a prototype and its experimental test, validate the proposed NZA concept for automotive mm‐wave radar applications in advanced driver assistance systems and autonomous vehicles such as, for instance, adaptive cruise control, collision avoidance, and blind spot detection.

High gain NiO/ZnO heterojunction photodiodes operated in Deep-ultraviolet region

Epitaxially matched (0001) Al2O3 single substrates are utilized to design p-n heterojunctions (p-NiO/n-ZnO) as they offer low defect density for device fabrication due to small lattice mismatches. Using the radio frequency sputtering technique, the NiO/ZnO thin film-based heterojunction has been fabricated by varying the n-type film's (ZnO) thickness for ultra-violet (UV) photodiode application. It has been investigated how different ZnO film thicknesses affect junction parameters and photoresponse properties. The high photosensitivity (∼ 104), enhanced current gain (∼ 105) and fast response obtained at very low UV intensity (0.62μW/cm2) at 300 nm wavelength are attributed to the internal gain mechanism (recombination tunnelling and space-charge limited current conduction with the remarkable effect of the presence of excess free oxygen) in these devices. The prepared heterojunction photodiode with high speed and deep-UV sensitivity can be a potential solution for visible blind UV detection.

Pilot study comparing a new virtual reality–based visual field test to standard perimetry in children

PurposeTo assess the feasibility and performance of Vivid Vision Perimetry (VVP), a new virtual reality (VR)–based visual field platform. MethodsChildren 7-18 years of age with visual acuity of 20/80 or better undergoing Humphrey visual field (HVF) testing were recruited to perform VVP, a VR-based test that uses suprathreshold stimuli to test 54 field locations and calculates a fraction seen score. Pearson correlation coefficients were calculated to evaluate correlation between HVF mean sensitivity and VVP mean fraction seen scores. Participants were surveyed regarding their experience. ResultsA total of 37 eyes of 23 participants (average age, 12.9 ± 3.1 years; 48% female) were included. All participants successfully completed VVP testing. Diagnoses included glaucoma (12), glaucoma suspect (7), steroid-induced ocular hypertension (3), and craniopharyngioma (1). Sixteen participants had prior HVF experience, and none had prior VVP experience, although 7 had previously used VR. Of the 23 HVF tests performed, 9 (39%) were unreliable due to fixation losses, false positives, or false negatives. Similarly, 35% of VVP tests were unreliable (as defined by accurate blind spot detection). Excluding unreliable HVF tests, the correlation between HVF average mean sensitivity and VVP mean fraction seen score was 0.48 (P = 0.02; 95% CI, 0.09-0.74). When asked about preference for the VVP or HVF examination, all participants favored the VVP, and 70% were “very satisfied” with VVP. ConclusionsIn our cohort of 23 pediatric subjects, VVP proved to be a clinically feasible VR-based visual field testing, which was uniformly preferred over HVF.

Synaptic properties of GaOx-based memristor with amorphous GaOx deposited by RF magnetic sputtering

GaOx devices have been extensively explored for applications such as power devices and solar blind detectors, based on their wide bandgap. In this study, we investigated the synaptic properties of the amorphous gallium oxide (a-GaOx)- based memristor with a W/WOx/a-GaOx/ITO structure, in which a-GaOx are deposited by RF magnetic sputtering at ambient temperature. The structure and components of a-GaOx are characterized by XRD, XPS, SEM, and EDS. The electrical test indicates that W/WOx/a-GaOx is ohmic due to the thin WOx layer with a high concentration of oxygen vacancies. Consequently, the synaptic characteristics of the W/WOx/a-GaOx/ITO memristor depend on both the a-GaOx layer itself and the a-GaOx/ITO junction. The fitting results indicate that the a-GaOx/ITO junction is Schottky with unidirectional conductive properties. However, the elevated defect density results in a larger current for the reverse-biased a-GaOx/ITO junction. Moreover, adjusting the thickness of a-GaOx allows the device to achieve almost symmetrical forward and reverse currents. We have successfully observed typical synaptic characteristics in W/WOx/a-GaOx/ITO when stimulated by consecutive spike signals. Clearly, through careful design considerations regarding the structure and parameters, we have realized superior synaptic performance in a-GaOx-based memristors. This achievement shows that amorphous GaOx has great potential applications in neuromorphic computation chips for artificial intelligence or the Internet of Things in the future.

Bolt load looseness detection for slip-critical blind bolt based on wavelet analysis and deep learning

Bolt preload is a crucial factor in high-strength bolt applications, particularly for the Slip-critical blind bolts (SCBBs). This study presents a novel nondestructive approach that leverages ultrasonic echo waves to accurately detect the state of bolt looseness, addressing a significant research gap in the field of blind bolt looseness detection. The proposed technique is uniquely suitable for blind bolted connections as it only necessitates access to a single side of the connection. Nine types of SCBBs were tested and obtained approximately 4000 ultrasonic echo signals with varying degrees of looseness. These signals have been transformed into image-based representations using wavelet analysis, and deep learning techniques were used to classify and predict the looseness level accurately. The performance of various damage assessment criteria, CNN models, and dataset sizes were evaluated and compared. The proposed method was validated by classifying 400 datasets with a validated accuracy of 97.30%.

BLACK BOX AND BLIND SPOT DETECTION SYSTEM IN AUTOMOBILES

This paper presents the development of an affordable Black Box and Blind Spot Detection System for automobiles, integrating various sensors and microcontrollers. The Black Box monitors crucial parameters such as speed, tilt, temperature, and alcohol presence, uploading data to a cloud-based Firebase database in real-time. The Blind Spot Detection System utilizes an ultrasonic sensor to alert drivers of objects in blind spots, aiming to prevent accidents. The system's user-friendly website allows easy data access and analysis, potentially enhancing road safety and facilitating crash investigations. Key words- Black box, Blind spot detection system, Firebase real time database.

Blind Channel Estimation and Data Detection With Unknown Modulation and Coding Scheme

Blind Channel Estimation and Data Detection With Unknown Modulation and Coding Scheme

A Deep Learning Based Framework for Blind Road Occupancy Detection

This research paper addresses the pressing concern of road safety for the visually impaired in densely populated regions, especially in China. While tactile paving exists to guide blind individuals, unexpected obstacles pose serious hazards. The study proposes an Artificial Intelligence (AI) system utilizing advanced machine learning techniques to identify obstacles on blind roads, providing real-time feedback for navigation. To overcome data limitations, a virtual environment using Pybullet is created for data generation, combining synthetic and real-world images for training. This study introduces a Convolutional Neural Network (CNN)-based model and integrates a Vision Transformer (ViT) model, comparing their efficacies. The progressive training approach yields a highly effective CNN model, outperforming ViT models. The practical application of the CNN model in real-world scenarios has proven its efficacy in detecting obstacles, underscoring its reliability and significant contribution to improving road safety for visually impaired individuals. This research extends beyond providing a safety enhancement measure; it also sheds light on the wider applicability of such methods in addressing issues like the scarcity of real-world data.

Enhancing Reliability of Advanced Driver-Assistance Systems through Predictive Maintenance and Data-Driven Insights

The advancement of Advanced Driver Assistance Systems (ADAS) marks a pivotal evolution in automotive technology, aiming to enhance road safety and driving efficiency through a wide array of functionalities like blind spot detection, emergency braking, and adaptive cruise control. This research paper delves into the operational integrity, performance metrics, and maintenance strategies of ADAS components, underpinned by a comprehensive methodology involving data collection, pre-processing, feature engineering, machine learning model development, and rigorous validation processes. Systematic inspection of ADAS components indicates their importance in vehicle safety and reliability. The visibility, distance, speed, and steering angle of front cameras, LiDAR, radar, and ultrasonic sensors are carefully evaluated. Maintenance logs show proactive error code management, boosting efficiency. SVM, Gradient Boosting, and Random Forest machine learning models predicted ADAS component failures during validation and testing. Random Forest scored 90% accuracy, 92% precision, 88% recall, and 90% F1. Gradient Boosting was the most accurate, with 93% accuracy, 94% precision, 91% recall, and 92% F1. SVM predicted ADAS component failures with 88% accuracy, 90% precision, 85% recall, and 87% F1 score. Machine learning helps shift from reactive to proactive maintenance. Modelling sensor signal quality, actuator reaction times, error code frequencies, and maintenance intervals enables predictive maintenance and failure detection. Feature engineering builds predictive models using maintenance logs and operational KPIs. The models predict ADAS component failures, boosting vehicle safety and dependability. Using external data improves predictive maintenance models. The maintenance model's adaptability and forecast accuracy are proved by ADAS operation after traffic, accident, and manufacturer upgrades. Predictive maintenance and machine learning improve ADAS dependability and safety, the study found. Advanced analytics and data-driven insights can reduce automotive system failures, improving safety and reliability.

Electronic transport and optical properties of five different phases (α, β, ε, δ and γ) of Ga2O3: A first-principles study

In the field of power and ultraviolet devices, Ga2O3 becomes an emerging semiconductor due to its large energy bandgap and suitable optical absorption wavelength at solar blind ultraviolet band. In this work, the electronic and optical properties of five Ga2O3 polymorphs are investigated by the first-principles calculations to study their potential in ultraviolet devices. The geometry structures, electronic structure, optical and electronic transport properties of five polymorphs have been investigated through GGA + U approach and deformation potential theory. Based on the deformation potential theory, the anisotropic electron mobility of five Ga2O3 polycrystals is obtained by analyzing the parameters obtained from the first-principles calculation. TCAD simulations using calculation results before show the spectral response of MSM solar-blind detectors based on five polymorphs, and indicating that ε-Ga2O3 is the best candidate material for solar blind UV detector. This work provides theoretical insights for the preparation of different phase gallium oxide materials and devices.