Search

Despite significant progress has been made in image restoration under adverse weather conditions, these methods primarily focus on the quality of image reconstruction, leaving their impact on downstream object detection unknown. In this paper, we rethink all-in-one adverse weather removal for object detection. Specifically, we contribute the first multi-weather image restoration dataset tailored for autonomous driving scenarios, comprising 6000 image pairs along with object detection labels, named Multi-Weather6k. Based on this dataset, we conduct a benchmark study on existing methods for joint image restoration and object detection. Furthermore, we develop an effective MLP-based all-in-one image de-weathering framework to better solve this task. The proposed architecture consists of the feature mixing block and the feature prompt block. The former enhances feature modeling by exploiting global and local correlations, while the latter guides image restoration by modulating multi-degraded features using prompt learning. Experimental results show that our proposed method not only achieves consistently superior restoration performance across various weather degradation scenarios but also yields improved object detection results, outperforming the state-of-the-art approaches. The dataset will be available to the public. [ABSTRACT FROM AUTHOR]

In autonomous driving, capturing high-quality images with visual sensors in adverse weather conditions presents a significant challenge for object detection. This paper introduces a candid and effective preprocessing method called Contrast Enhancement through Mutual Entropy (CEME) to improve the visual quality of images. Unlike previous methods such as traditional image processing, image restoration, and deep learning techniques, CEME enhances image quality using simple filtering operations. CEME works by adjusting gray levels appropriately through the calculation of mutual entropy between adjacent gray levels in each plane of a color image. Experimental simulations were conducted on various images taken in weather conditions like snow, fog, sand, and rain. To evaluate performance, this study used two natural image quality assessment metrics: Novel Blind Image Quality Assessment (NBIQA) and Natural Image Quality Evaluator (NIQE). The proposed method achieved an average NBIQA for sandy, snowy, rainy, and foggy images of 28.1576, 35.7233, 29.8796, and 36.1944 respectively. [ABSTRACT FROM AUTHOR]

Roadway safety is immensely affected during adverse weather conditions. Therefore, this study seeks to quantify such effects on the injury severity of involved drivers in single-vehicle crashes on two-way highways. This should be done by identifying risk factors and accommodating the heterogeneous impacts of these factors by accounting for the heterogeneity in means and variances of random parameters in the estimated model using seven years of police-reported crash data from 2010 to 2016 in Oregon. The study findings confirm the superior performance of the mixed logit model with heterogeneity in the means and variances in terms of statistical fit comparable to the traditional mixed logit model and mixed logit model with heterogeneity in the means only. The estimation results reveal that some factors such as female drivers, fatigued drivers, crashes in the early morning (between 4:00 am and 8:00 am), and crashes that occurred in darkness with no streetlights were found to increase serious injury outcomes. The empirical findings can offer evidence-based insights to help in decision-making and countermeasure selection that is aimed at improving safety under adverse weather conditions. [ABSTRACT FROM AUTHOR]

With the expansion of power transmission line scale, the surrounding environment is complex and susceptible to foreign objects, severely threatening its safe operation. The current algorithm lacks stability and real-time performance in small target detection and severe weather conditions. Therefore, this paper proposes a method for detecting foreign objects on power transmission lines under severe weather conditions based on AdaptoMixNet. First, an Adaptive Fusion Module (AFM) is introduced, which improves the model's accuracy and adaptability through multi-scale feature extraction, fine-grained information preservation, and enhancing context information. Second, an Adaptive Feature Pyramid Module (AEFPM) is proposed, which enhances the focus on local details while preserving global information, improving the stability and robustness of feature representation. Finally, the Neuron Expansion Recursion Adaptive Filter (CARAFE) is designed, which enhances feature extraction, adaptive filtering, and recursive mechanisms, improving detection accuracy, robustness, and computational efficiency. Experimental results show that the method of this paper exhibits excellent performance in the detection of foreign objects on power transmission lines under complex backgrounds and harsh weather conditions. [ABSTRACT FROM AUTHOR]

In the context of autonomous driving, the augmentation of existing data through simulations provides an elegant solution to the challenge of capturing the full range of adverse weather conditions in training datasets. However, existing physics-based augmentation models typically rely on single scattering approximations to predict light propagation under unfavorable conditions, such as fog. This can prevent the reproduction of important signal characteristics encountered in a real-world environment. Consequently, in this work, Monte Carlo simulations are employed to assess the relevance of multiple-scattered light to the detected LiDAR signal in different types of fog, with scattering phase functions calculated from Mie theory considering real particle size distributions. Bidirectional path tracing is used within the self-developed GPU-accelerated Monte Carlo software to compensate for the unfavorable photon statistics associated with the limited detection aperture of the LiDAR geometry. To validate the Monte Carlo software, an analytical solution of the radiative transfer equation for the time-resolved radiance in terms of scattering orders is derived, thereby providing an explicit representation of the double-scattered contributions. The results of the simulations demonstrate that the shape of the detected signal can be significantly impacted by multiple-scattered light, depending on LiDAR geometry and visibility. In particular, double-scattered light can dominate the overall signal at low visibilities. This indicates that considering higher scattering orders is essential for improving AI-based perception models. [ABSTRACT FROM AUTHOR]

Robust object detection and weather classification are essential for the safe operation of autonomous vehicles (AVs) in adverse weather conditions. While existing research often treats these tasks separately, this paper proposes a novel multi objectives model that treats weather classification and object detection as a single problem using only the AV camera sensing system. Our model offers enhanced efficiency and potential performance gains by integrating image quality assessment, Super-Resolution Generative Adversarial Network (SRGAN), and a modified version of You Only Look Once (YOLO) version 5. Additionally, by leveraging the challenging Detection in Adverse Weather Nature (DAWN) dataset, which includes four types of severe weather conditions, including the often-overlooked sandy weather, we have conducted several augmentation techniques, resulting in a significant expansion of the dataset from 1027 images to 2046 images. Furthermore, we optimize the YOLO architecture for robust detection of six object classes (car, cyclist, pedestrian, motorcycle, bus, truck) across adverse weather scenarios. Comprehensive experiments demonstrate the effectiveness of our approach, achieving a mean average precision (mAP) of 74.6%, underscoring the potential of this multi objectives model to significantly advance the perception capabilities of autonomous vehicles' cameras in challenging environments. [ABSTRACT FROM AUTHOR]

The presence of fog in the background can prevent small and distant objects from being detected, let alone tracked. Under safety-critical conditions, multi-object tracking models require faster tracking speed while maintaining high object-tracking accuracy. The original DeepSORT algorithm used YOLOv4 for the detection phase and a simple neural network for the deep appearance descriptor. Consequently, the feature map generated loses relevant details about the track being matched with a given detection in fog. Targets with a high degree of appearance similarity on the detection frame are more likely to be mismatched, resulting in identity switches or track failures in heavy fog. We propose an improved multi-object tracking model based on the DeepSORT algorithm to improve tracking accuracy and speed under foggy weather conditions. First, we employed our camera-radar fusion network (CR-YOLOnet) in the detection phase for faster and more accurate object detection. We proposed an appearance feature network to replace the basic convolutional neural network. We incorporated GhostNet to take the place of the traditional convolutional layers to generate more features and reduce computational complexities and costs. We adopted a segmentation module and fed the semantic labels of the corresponding input frame to add rich semantic information to the low-level appearance feature maps. Our proposed method outperformed YOLOv5 + DeepSORT with a 35.15% increase in multi-object tracking accuracy, a 32.65% increase in multi-object tracking precision, a speed increase by 37.56%, and identity switches decreased by 46.81%. [ABSTRACT FROM AUTHOR]

With current advances in automated driving, optical sensors like cameras and LiDARs are playing an increasingly important role in modern driver assistance systems. However, these sensors face challenges from adverse weather effects like fog and precipitation, which significantly degrade the sensor performance due to scattering effects in its optical path. Consequently, major efforts are being made to understand, model, and mitigate these effects. In this work, the reverse research question is investigated, demonstrating that these measurement effects can be exploited to predict occurring weather conditions by using state-of-the-art deep learning mechanisms. In order to do so, a variety of models have been developed and trained on a recorded multiseason dataset and benchmarked with respect to performance, model size, and required computational resources, showing that especially modern vision transformers achieve remarkable results in distinguishing up to 15 precipitation classes with an accuracy of 84.41% and predicting the corresponding precipitation rate with a mean absolute error of less than 0.47 mm/h, solely based on measurement noise. Therefore, this research may contribute to a cost-effective solution for characterizing precipitation with a commercial Flash LiDAR sensor, which can be implemented as a lightweight vehicle software feature to issue advanced driver warnings, adapt driving dynamics, or serve as a data quality measure for adaptive data preprocessing and fusion. [ABSTRACT FROM AUTHOR]

Travelers often change their behavior in reaction to adverse weather conditions. This paper seeks to conduct an empirical evaluation of both ordered and unordered discrete outcome frameworks for examining the adaptive behavior decisions of intercity travelers and investigate the varying effects of explanatory factors on different alternatives of adaptive behavior during adverse weather. The data from 754 respondents in the Beijing-Tianjin-Hebei urban agglomeration, China are collected by a two-phase survey instrument. To capture the unobserved heterogeneity more effectively, this paper develops three advanced models to investigate the variations in intercity travel behavior during adverse weather. Four alternative adaptive behaviors are determined as outcome variables: maintaining original travel plans, changing only the intercity mode, changing the departure date, and canceling the trip, while potential influencing factors including adverse weather conditions, trip-related characteristics, individual attributes and urban agglomeration attributes are statistically assessed. The results indicate that the unordered models consistently outperform their ordered counterparts, and the incorporation of multilayer heterogeneity enhances the model fit. Furthermore, significant factors and their coefficient values vary across the different adaptive behavior alternatives. Intercity travelers demonstrate a higher probability of changing departure dates or canceling trips during snowy and windy days compared to rainy and foggy days. Trains exhibit higher flexibility and reliability during adverse weather, and access attributes significantly affect intercity travel adaptive behavior. Additionally, the analysis of individual and urban agglomeration attributes uncovers variations in adaptive behavior among individuals and cities. These findings provide profound insights into the complexities and variations of intercity travel behavior during adverse weather, and propose practical strategies to mitigate the detrimental impacts of adverse weather on intercity travelers. • Adaptive behavior of intercity travelers during adverse weather is investigated. • Unordered framework outperforms ordered counterparts in adaptive behavior study. • Multilayer unobserved heterogeneity in the adaptive behavior is accounted for. • The varying effects of explanatory factors on different adaptive alternatives are examined. • Practical strategies are proposed to mitigate negative impacts of adverse weather. [ABSTRACT FROM AUTHOR]

With the emergence of autonomous functions in road vehicles, there has been increased use of Advanced Driver Assistance Systems comprising various sensors to perform automated tasks. Light Detection and Ranging (LiDAR) is one of the most important types of optical sensor, detecting the positions of obstacles by representing them as clusters of points in three-dimensional space. LiDAR performance degrades significantly when a vehicle is driving in the rain as raindrops adhere to the outer surface of the sensor assembly. Performance degradation behaviors include missing points and reduced reflectivity of the points. It was found that the extent of degradation is highly dependent on the interface material properties. This subsequently affects the shapes of the adherent droplets, causing different perturbations to the optical rays. A fundamental investigation is performed on the protective polycarbonate cover of a LiDAR assembly coated with four classes of material—hydrophilic, almost-hydrophobic, hydrophobic, and superhydrophobic. Water droplets are controllably dispensed onto the cover to quantify the signal alteration due to the different droplets of various sizes and shapes. To further understand the effects of droplet motion on LiDAR signals, sliding droplet conditions are simulated using numerical analysis. The results are validated with physical optical tests, using a 905 nm laser source and receiver to mimic the LiDAR detection mechanism. Comprehensive explanations of LiDAR performance degradation in rain are presented from both material and optical perspectives. These can aid component selection and the development of signal-enhancing strategies for the integration of LiDARs into vehicle designs to minimize the impact of rain. [ABSTRACT FROM AUTHOR]

Recognizing and categorizing items in weather-adverse environments poses significant challenges for autonomous vehicles. To improve the robustness of object-detection systems, this paper introduces an innovative approach for detecting objects at different levels by leveraging sensors and deep learning-based solutions within a traffic circle. The suggested approach improves the effectiveness of single-stage object detectors, aiming to advance the performance in perceiving autonomous racing environments and minimizing instances of false detection and low recognition rates. The improved framework is based on the one-stage object-detection model, incorporating multiple lightweight backbones. Additionally, attention mechanisms are integrated to refine the object-detection process further. Our proposed model demonstrates superior performance compared to the state-of-the-art method on the DAWN dataset, achieving a mean average precision (mAP) of 99.1%, surpassing the previous result of 84.7%. [ABSTRACT FROM AUTHOR]

To investigate the effects of various government subsidies on the decision of agricultural products supply chain under adverse weather, this paper depicts the random profit function of adverse weather affecting the output of fresh agricultural products. Then, both the centralised and decentralised decision-making models are set with various government subsidies, i.e. no subsidy, output subsidy, procurement subsidy, one-time subsidy to company and one-time subsidy to farmer. Through comparative analysis and numerical analysis, we explore the effects of adverse weather and different government subsidies on the supply chain decisions including planting effort, procurement price and retail price. [ABSTRACT FROM AUTHOR]

We present an assessment of simulated lidar point clouds based on different phenomenological range-reflectivity models. In sensor model development, the validation of individual model features is favorable. For lidar sensors, range limits depend on surface reflectivities. Two phenomenological feature models are derived from the lidar range equation, for clear and adverse weather conditions. The underlying parameters are the maximum ranges for best environment conditions, based on sensor datasheets, and a maximum range measurement for attenuation conditions. Furthermore, an assessment of different feature models is needed, similar to unit tests. Therefore, resulting point clouds are compared with respect to the total number of corresponding points and the number of points with no correspondences for pair-wise cloud comparison. Applications are presented using a point cloud lidar model. Results of the point cloud comparison are demonstrated for a single scene or time step and an entire scenario of 40 time steps. When a reference point cloud is provided by the sensor manufacturer, feature validation becomes possible.

Visible light communication (VLC) can be a promising alternative to radio-based communication for underwater applications. However, VLC suffers from limited range and coverage due to the absorption and scattering of light in water. The purpose of this research is to construct and assess a VLC's performance in turbid, turbulence, and typical ocean water. Utilizing Optisystem simulation software, we design and optimize a hybrid VLC underwater communication system, where a ship can communicate from water surface to inside and internal link between two submarines. The system's performance is measured in terms of bit error rate, data rate, and range under various water conditions, including turbid, normal ocean water, and turbulence water. Instead of implementing higher order modulation or achieving high data rates, the emphasis was on maximizing the simplicity of underwater light communication (ULC) in a variety of weather conditions. We observed BER 5.84x10-9 in the clear water within 500m and BER was 2.8x10-4 in the turbulence water by using OOK modulation scheme. Moreover, this system can transmit data maximum 500m in clear water 230m, and 210 m in turbid and turbulence water simultaneously. By systematically evaluating system performance under various types of water conditions, this model has the potential of effective communication solutions for underwater applications, with implications for various sectors including marine exploration, underwater surveillance, and environmental monitoring. [ABSTRACT FROM AUTHOR]

This paper presents an approach for integrating uncertainty information in air traffic flow management at the tactical phase. In particular, probabilistic methodologies to predict sector demand and sector congestion under adverse weather in a time horizon of 1.5 h are developed. Two sources of uncertainty are considered: the meteorological uncertainty inherent to the forecasting process and the uncertainty in the take-off time. An ensemble approach is adopted to characterize both uncertainty sources. The methodologies rely on a trajectory predictor able to generate an ensemble of 4D trajectories that provides a measure of the trajectory uncertainty, each trajectory avoiding the storm cells encountered along the way. The core of the approach is the statistical processing of the ensemble of trajectories to obtain probabilistic entry and occupancy counts of each sector and their congestion status when the counts are compared to weather-dependent capacity values. A new criterion to assess the risk of sector overload, which takes into account the uncertainty, is also defined. The results are presented for a historical situation over the Austrian airspace on a day with significant convection. [ABSTRACT FROM AUTHOR]

The global GDP has witnessed a significant upswing, majorly due to the growth of the construction industry. Embracing the whole-life costing (WLC) approach, the construction sector strategically manages expenses across a construction project's life cycle. However, despite its widespread adoption, accurate cost forecasting remains a major challenge. The intricate interplay of various influencing factors has not been fully explored, leading to inaccurate cost estimations. A comprehensive understanding of specific factors and their interrelationships is crucial to address this issue. Therefore, it is imperative to conduct further research to identify and explore the subtle nuances of these factors that impact whole-life cost estimation. Our study fills this gap, analysing 51 factors from 84 papers across prominent repositories. We assess interrelationships using a systematic literature review and pairwise comparison as in the analytical hierarchy process. The International Construction Measurement Standards (ICMS) framework structures these relationships and is represented in the causal loop diagrams (CLDs). The pioneering CLDs are a notable contribution, illustrating interrelationships and polarities among the 51 WLC factors. Six reinforcing loops and one balancing loop provide valuable insights into their dynamic nature. Importantly, lower-level factors do not always directly connect with upper-level factors. Instead, they interact within the same level before linking to top-level factors. These findings are significant for professionals, such as cost estimators, quantity surveyors and scholars, offering a comprehensive understanding of the WLC system. [ABSTRACT FROM AUTHOR]

Adverse weather conditions at night are very fatal to drivers, causing serious traffic accidents. Road lighting is a facility that can alleviate these dangerous situations. Nevertheless, road lighting has only rarely been studied during adverse weather. The reason is that the current road lighting performance evaluation method is presented based on normal weather. The current road lighting performance evaluation method uses a luminance meter to measure the road surface, which is not suitable due to scattering during adverse weather such as rain and fog. Therefore, this study proposes obstacle recognition distance as a measure of effectiveness to evaluate the performance of road lighting during adverse weather. There is a lack of actual research on whether obstacle recognition distance can be used as a measure of effectiveness for road lighting during adverse weather. Therefore, in this study, 30 subjects were used to measure the subjects' obstacle recognition distance according to changes in weather conditions, road lighting grade, and road lighting color temperature. As a result, it was analyzed that there was a clear trend of change in obstacle recognition distance depending on the change in each condition. It was found that, under the same road lighting performance conditions, there was a difference of up to 72.86% by weather condition; under the same weather conditions, there was a difference of up to 22.75% by road lighting grade; and by color temperature, there was a difference of up to 21.87%. In addition, a statistical significance test was performed to support the existence of a difference, and the results were synthesized to suggest that obstacle recognition distance can be used as a performance measure of effectiveness of road lighting in adverse weather. [ABSTRACT FROM AUTHOR]

Clear images are crucial for the optimal performance of various high-level vision-based tasks. However, some inevitable causes, such as bad weather and underwater conditions degrade scene visibility. The tiny particles present in the air absorb and scatter light, causing severe attenuation that results in unclear, low-brightness, and poor-contrast images. Several techniques have been introduced to restore the degradation. However, no model exists to date that can restore multiple degradations using a single model. Therefore, to improve the scene visibility, a unified model called a Multidomain Contextual Conditional Generative Adversarial Network (MCCGAN) is designed, which uses the same parameters across the domains to restore multiple degradations such as fog, haze, rain streaks, snowflakes, smoke, shadows, underwater, and muddy underwater. The proposed model has a novel addition of multiple 1 × 1 convolutional context encoding bottleneck layers between a simple lightweight eight-block encoder and decoder with skip connections which learns the context of each input domain thoroughly, thus generating better-restored images. The MCCGAN is qualitatively and quantitatively compared to various state-of-the-art image-to-image translation models and tested on a few real unseen image domains such as smog, dust, and lightning, and the obtained results successfully improved scene visibility, proving the generalizability of MCCGAN. Moreover, the MS-COCO 2017 validation dataset is used for comparing the performance of object detection, instance segmentation, and image captioning on (1) weather-degraded images, (2) restored images by MCCGAN, and (3) ground truth images, and the results demonstrated the success of our model. An ablation study is also carried out to check the significance of the discriminator, skip connections, and bottleneck layers in MCCGAN, and the analysis suggests that MCCGAN performs better by adding a discriminator, skip connections, and four bottleneck layers in the generator architecture. [ABSTRACT FROM AUTHOR]

An efficient model to detect and track the objects in adverse weather is proposed using Tanh Softmax (TSM) EfficientDet and Jaccard Similarity based Kuhn-Munkres (JS-KM) with Pearson-Retinex in this paper. The noises were initially removed using Differential Log Energy Entropy adapted Wiener Filter (DLE-WF). The Log Energy Entropy value was calculated between the pixels instead of calculating the local mean of a pixel in the normal Wiener filter. Also, the segmentation technique was carried out using Fringe Binarization adapted K-Means Algorithm (FBKMA). The movement of segmented objects was detected using the optical flow technique, in which the optical flow was computed using the Horn-Schunck algorithm. After motion estimation, the final step in the proposed system is object tracking. The motion-estimated objects were treated as the target that is initially in the first frame. The target was tracked by JS-KM algorithm in the subsequent frame. At last, the experiential evaluation is conducted to confirm the proposed model's efficacy. The outcomes of Detection in Adverse Weather Nature (DAWN) dataset proved that in comparison to the prevailing models, a better performance was achieved by the proposed methodology. [ABSTRACT FROM AUTHOR]

LIDAR is central to the perception systems of autonomous vehicles, but its performance is sensitive to adverse weather. An object detector trained by deep learning with the LIDAR point clouds in clear weather is not able to achieve satisfactory accuracy in adverse weather. Considering the fact that collecting LIDAR data in adverse weather like dusty storms is a formidable task, we propose a novel data augmentation framework based on physical simulation. Our model takes into account finite laser pulse width and beam divergence. The discrete dusty particles are distributed randomly in the surrounding of LIDAR sensors. The attenuation effects of scatters are represented implicitly with extinction coefficients. The coincidentally returned echoes from multiple particles are evaluated by explicitly superimposing their power reflected from each particle. Based on the above model, the position and intensity of real point clouds collected from dusty weather can be modified. Numerical experiments are provided to demonstrate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Adverse weather conditions impact mobility, safety, and the behavior of drivers on roads. In an average year, approximately 21% of U.S. highway crashes are weather-related. Collectively, these crashes result in over 5300 fatalities each year. As a proof-of-concept, analyzing weather information in the context of traffic mobility data can provide unique insights into driver behavior and actions transportation agencies can pursue to promote safety and efficiency. Using 2019 weather and traffic data along Colorado Highway 119 between Boulder and Longmont, this research analyzed the relationship between adverse weather and traffic conditions. The data were classified into distinct weather types, day of the week, and the direction of travel to capture commuter traffic flows. Novel traffic information crowdsourced from smartphones provided metrics such as volume, speed, trip length, trip duration, and the purpose of travel. The data showed that snow days had a smaller traffic volume than clear and rainy days, with an All Times volume of approximately 18,000 vehicles for each direction of travel, as opposed to 21,000 vehicles for both clear and wet conditions. From a trip purpose perspective, the data showed that the percentage of travel between home and work locations was 21.4% during a snow day compared to 20.6% for rain and 19.6% for clear days. The overall traffic volume reduction during snow days is likely due to drivers deciding to avoid commuting; however, the relative increase in the home–work travel percentage is likely attributable to less discretionary travel in lieu of essential work travel. In comparison, the increase in traffic volume during rainy days may be due to commuters being less likely to walk, bike, or take public transit during inclement weather. This study demonstrates the insight into human behavior by analyzing impact on traffic parameters during adverse weather travel.

Autonomous vehicles are at the forefront of future transportation solutions, but their success hinges on reliable perception. This review paper surveys image processing and sensor fusion techniques vital for ensuring vehicle safety and efficiency. The paper focuses on object detection, recognition, tracking, and scene comprehension via computer vision and machine learning methodologies. In addition, the paper explores challenges within the field, such as robustness in adverse weather conditions, the demand for real-time processing, and the integration of complex sensor data. Furthermore, we examine localization techniques specific to autonomous vehicles. The results show that while substantial progress has been made in each subfield, there are persistent limitations. These include a shortage of comprehensive large-scale testing, the absence of diverse and robust datasets, and occasional inaccuracies in certain studies. These issues impede the seamless deployment of this technology in real-world scenarios. This comprehensive literature review contributes to a deeper understanding of the current state and future directions of image processing and sensor fusion in autonomous vehicles, aiding researchers and practitioners in advancing the development of reliable autonomous driving systems.

In the context of autonomous driving, the augmentation of existing data through simulations provides an elegant solution to the challenge of capturing the full range of adverse weather conditions in training datasets. However, existing physics-based augmentation models typically rely on single scattering approximations to predict light propagation under unfavorable conditions, such as fog. This can prevent the reproduction of important signal characteristics encountered in a real-world environment. Consequently, in this work, Monte Carlo simulations are employed to assess the relevance of multiple-scattered light to the detected LiDAR signal in different types of fog, with scattering phase functions calculated from Mie theory considering real particle size distributions. Bidirectional path tracing is used within the self-developed GPU-accelerated Monte Carlo software to compensate for the unfavorable photon statistics associated with the limited detection aperture of the LiDAR geometry. To validate the Monte Carlo software, an analytical solution of the radiative transfer equation for the time-resolved radiance in terms of scattering orders is derived, thereby providing an explicit representation of the double-scattered contributions. The results of the simulations demonstrate that the shape of the detected signal can be significantly impacted by multiple-scattered light, depending on LiDAR geometry and visibility. In particular, double-scattered light can dominate the overall signal at low visibilities. This indicates that considering higher scattering orders is essential for improving AI-based perception models.

Adverse weather conditions impact mobility, safety, and the behavior of drivers on roads. In an average year, approximately 21% of U.S. highway crashes are weather-related. Collectively, these crashes result in over 5300 fatalities each year. As a proof-of-concept, analyzing weather information in the context of traffic mobility data can provide unique insights into driver behavior and actions transportation agencies can pursue to promote safety and efficiency. Using 2019 weather and traffic data along Colorado Highway 119 between Boulder and Longmont, this research analyzed the relationship between adverse weather and traffic conditions. The data were classified into distinct weather types, day of the week, and the direction of travel to capture commuter traffic flows. Novel traffic information crowdsourced from smartphones provided metrics such as volume, speed, trip length, trip duration, and the purpose of travel. The data showed that snow days had a smaller traffic volume than clear and rainy days, with an All Times volume of approximately 18,000 vehicles for each direction of travel, as opposed to 21,000 vehicles for both clear and wet conditions. From a trip purpose perspective, the data showed that the percentage of travel between home and work locations was 21.4% during a snow day compared to 20.6% for rain and 19.6% for clear days. The overall traffic volume reduction during snow days is likely due to drivers deciding to avoid commuting; however, the relative increase in the home–work travel percentage is likely attributable to less discretionary travel in lieu of essential work travel. In comparison, the increase in traffic volume during rainy days may be due to commuters being less likely to walk, bike, or take public transit during inclement weather. This study demonstrates the insight into human behavior by analyzing impact on traffic parameters during adverse weather travel. [ABSTRACT FROM AUTHOR]

This study presented an extensive assessment of risky driving behavior through Structural Equation Modeling (SEM) technique and explored the applicability of this method in identifying contributing factors influencing drivers' risk-taking behavior in clear and adverse weather. Drivers' questionnaire responses as well as vehicle trajectories of their completed trips in clear and adverse weather were utilized from the SHRP2 Naturalistic Driving Study (NDS). Factor analyses were conducted to identify the number of unobserved "latent" variables. Subsequently, two SEM models in clear and adverse weather were developed to attain the relationships between the observed and the latent variables. "Human Factors" and "Driving Skills" were determined as exogenous latent variables in both models to investigate their impacts on an endogenous latent variable (i.e., risky driving). The results suggested that "Human Factors" was the most significant latent variable affecting drivers' risk-taking behavior in clear and adverse weather conditions. Moreover, speeding was found to have a significant impact on risky behavior in adverse weather conditions. The findings could help safety practitioners with better understanding of the influencing factors affecting risky driving to improve safety through proper enforcement and necessary training programs, particularly targeting young and inexperienced drivers. [ABSTRACT FROM AUTHOR]

Maritime ship detection plays a crucial role in smart ships and intelligent transportation systems. However, adverse maritime weather conditions, such as rain streak and fog, can significantly impair the performance of visual systems for maritime traffic. These factors constrain the performance of traffic monitoring systems and ship-detection algorithms for autonomous ship navigation, affecting maritime safety. The paper proposes an approach to resolve the problem by visually removing rain streaks and fog from images, achieving an integrated framework for accurate ship detection. Firstly, the paper employs an attention generation network within an adversarial neural network to focus on the distorted regions of the degraded images. The paper also utilizes a contextual encoder to infer contextual information within the distorted regions, enhancing the credibility of image restoration. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to achieve rapid multi-scale feature fusion, enhancing the accuracy of maritime ship detection. The proposed GYB framework was validated using the SeaShip dataset. The experimental results show that the proposed framework achieves an average accuracy of 96.3%, a recall of 95.35%, and a harmonic mean of 95.85% in detecting maritime traffic ships under rain-streak and foggy-weather conditions. Moreover, the framework outperforms state-of-the-art ship detection methods in such challenging weather scenarios. [ABSTRACT FROM AUTHOR]

Accurate prediction of traffic demand and airport capacity plays a crucial role in minimising ground delays and airborne holdings. This paper focuses on the latter aspect. Adverse weather conditions present significant challenges to airport operations and can substantially reduce capacity. Consequently, any predictive model, regardless of its complexity, should account for weather conditions when estimating the airport capacity. At present, the sole shared platform for airport capacity information in Europe is the EUROCONTROL Public Airport Corner, where airports have the option to voluntarily report their capacities. These capacities are presented in tabular form, indicating the maximum number of hourly arrivals and departures for each possible runway configuration. Additionally, major airports often provide a supplementary table showing the impact of adverse weather in a somewhat approximate manner (e.g., if the visibility is lower than 100 m, then arrival capacity decreases by 30%). However, these tables only cover a subset of airports, and their generation is not harmonised, as different airports may use different methodologies. Moreover, these tables may not account for all weather conditions, such as snow, strong winds, or thunderstorms. This paper presents a machine learning approach to learn mapping from weather conditions and runway configurations to the 99th percentile of the delivered throughput from historical data. This percentile serves as a capacity proxy for airports operating at or near capacity. Unlike previous attempts, this paper takes a novel approach, where a single model is trained for several airports, leveraging the generalisation capabilities of cutting-edge machine learning algorithms. The results of an experiment conducted using 2 years of historical traffic and weather data for the top 45 busiest airports in Europe demonstrate better alignment in terms of mean pinball error with the observed departure and arrival throughput when compared to the operational capacities reported in the EUROCONTROL Public Airport Corner. While there is still room for improvement, this system has the potential to assist airports in defining more reasonable capacity values, as well as aiding airlines in assessing the impact of adverse weather on their flights. [ABSTRACT FROM AUTHOR]

Vehicle active safety systems can improve vehicle security by avoiding collisions. An autonomous emergency braking (AEB) system's safety distance calculation is usually based on normal weather conditions. The AEB system's early warning capabilities decrease during adverse weather conditions. A multilayer perceptron (MLP) model is used to obtain data from accident and weather data sets. The MLP model is trained and the severity of accidents is predicted. The severity is used as a parameter to build an adaptive AEB system algorithm that considers adverse weather conditions. The adaptive AEB system algorithm increases safety and reliability under adverse weather conditions. Prescan and a driver-in-the-loop system are used to test the adaptive AEB model. Both tests show that the adaptive AEB model has better performance under adverse weather than the traditional AEB model. The experimental results demonstrate that the adaptive AEB system can increase the safety distance in rainy weather and avoid collisions under hazy conditions. [ABSTRACT FROM AUTHOR]

Autonomous vehicles are at the forefront of future transportation solutions, but their success hinges on reliable perception. This review paper surveys image processing and sensor fusion techniques vital for ensuring vehicle safety and efficiency. The paper focuses on object detection, recognition, tracking, and scene comprehension via computer vision and machine learning methodologies. In addition, the paper explores challenges within the field, such as robustness in adverse weather conditions, the demand for real-time processing, and the integration of complex sensor data. Furthermore, we examine localization techniques specific to autonomous vehicles. The results show that while substantial progress has been made in each subfield, there are persistent limitations. These include a shortage of comprehensive large-scale testing, the absence of diverse and robust datasets, and occasional inaccuracies in certain studies. These issues impede the seamless deployment of this technology in real-world scenarios. This comprehensive literature review contributes to a deeper understanding of the current state and future directions of image processing and sensor fusion in autonomous vehicles, aiding researchers and practitioners in advancing the development of reliable autonomous driving systems. [ABSTRACT FROM AUTHOR]

With current advances in automated driving, optical sensors like cameras and LiDARs are playing an increasingly important role in modern driver assistance systems. However, these sensors face challenges from adverse weather effects like fog and precipitation, which significantly degrade the sensor performance due to scattering effects in its optical path. Consequently, major efforts are being made to understand, model, and mitigate these effects. In this work, the reverse research question is investigated, demonstrating that these measurement effects can be exploited to predict occurring weather conditions by using state-of-the-art deep learning mechanisms. In order to do so, a variety of models have been developed and trained on a recorded multiseason dataset and benchmarked with respect to performance, model size, and required computational resources, showing that especially modern vision transformers achieve remarkable results in distinguishing up to 15 precipitation classes with an accuracy of 84.41% and predicting the corresponding precipitation rate with a mean absolute error of less than 0.47 mm/h, solely based on measurement noise. Therefore, this research may contribute to a cost-effective solution for characterizing precipitation with a commercial Flash LiDAR sensor, which can be implemented as a lightweight vehicle software feature to issue advanced driver warnings, adapt driving dynamics, or serve as a data quality measure for adaptive data preprocessing and fusion.

With the emergence of autonomous functions in road vehicles, there has been increased use of Advanced Driver Assistance Systems comprising various sensors to perform automated tasks. Light Detection and Ranging (LiDAR) is one of the most important types of optical sensor, detecting the positions of obstacles by representing them as clusters of points in three-dimensional space. LiDAR performance degrades significantly when a vehicle is driving in the rain as raindrops adhere to the outer surface of the sensor assembly. Performance degradation behaviors include missing points and reduced reflectivity of the points. It was found that the extent of degradation is highly dependent on the interface material properties. This subsequently affects the shapes of the adherent droplets, causing different perturbations to the optical rays. A fundamental investigation is performed on the protective polycarbonate cover of a LiDAR assembly coated with four classes of material—hydrophilic, almost-hydrophobic, hydrophobic, and superhydrophobic. Water droplets are controllably dispensed onto the cover to quantify the signal alteration due to the different droplets of various sizes and shapes. To further understand the effects of droplet motion on LiDAR signals, sliding droplet conditions are simulated using numerical analysis. The results are validated with physical optical tests, using a 905 nm laser source and receiver to mimic the LiDAR detection mechanism. Comprehensive explanations of LiDAR performance degradation in rain are presented from both material and optical perspectives. These can aid component selection and the development of signal-enhancing strategies for the integration of LiDARs into vehicle designs to minimize the impact of rain.

Climate change poses a significant threat to crop production and food security in North Africa and around the world. Intense heat, drought, and other climatic changes can significantly impact the yield of certain crops, such as cucurbits (e.g., melons, gourds, and pumpkins). Hence, the need to explore means to mitigate the adverse effect of change in climate on Cucurbits which are sensitive to heat stress and require a sufficient water supply to thrive. Cucurbits are plants mostly grown for their fruit or seeds, often eaten raw or pickled. Hence, providing economic incentives to farmers within North African countries such as Tunisia, Morocco and Egypt. This review aims to discuss the historical and current production trends of Cucurbitaceae species and the effect of climate change on Cucurbits in the northern region of Africa while also highlighting the significant role of Cucurbits as a source of food and nutritional security in the region. A literature search was conducted on electronic databases such as Scopus, Web of Science, Science Direct, Google Books and Google Scholar. Results showed that due to climate change, the production of cucurbit crops may decrease by up to 10-15%, leading to reduced food availability and increased prices in some areas. Thus, impacting negatively on household food security. Similarly, the climate change implications for different types of cucurbit crops can vary substantially depending on the unique growing conditions of each country within the region.

Effective and time-efficient aircraft assistance and guidance in severe weather environments remains a challenge for air traffic control. Air navigation service providers around the globe could greatly benefit from specific and adapted meteorological information for the controller position, helping to reduce the increased workload induced by adverse weather. The present work proposes a radar-based nowcasting algorithm providing compact meteorological information on convective weather near airports for introduction into the algorithms intended to assist in air-traffic management. The use of vertically integrated liquid density enables extremely rapid identification and short-term prediction of convective regions that should not be traversed by aircraft, which is an essential requirement for use in tactical controller support systems. The proposed tracking and nowcasting method facilitates the anticipation of the meteorological situation around an airport. Nowcasts of centroid locations of various approaching thunderstorms were compared with corresponding radar data, and centroid distances between nowcasted and observed storms were computed. The results were analyzed with Method for the Object-Based Evaluation from the Model Evaluation tools software (MET-10.0.1, Developmental Testbed Center, Boulder, CO, US) and later integrated into an assistance arrival manager software, showing the potential of this approach for automatic air traffic assistance in adverse weather scenarios. [ABSTRACT FROM AUTHOR]

The main focus of this study was to develop a robust prediction model based on deep learning capable of providing timely predictions of injury and fatal crashes in adverse weather on rural mountainous freeways. This study leveraged a promising deep learning technique named ResNet18. To apply the proposed deep learning model, the numeric crash data were converted to images utilizing a cutting-edge method, called DeepInsight. In addition, considering the imbalanced nature of the crash data, this study leveraged two data balancing techniques, namely Random Under Sampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE); and experimented with several data sampling ratios. The best prediction performance was found using a ratio of 1:2:2 (Fatal:Injury:PDO) coupled with both RUS and SMOTE, which produced an overall prediction accuracy of 99.3% and 80.5% for fatal and injury crashes, respectively. This study also investigated the importance of variables on crash severity, which revealed that driver residency, vehicle damage extent, airbag deployment, driver conditions, weather, and road surface conditions were the most important variables contributing to the severity of crashes. The proposed deep learning framework can provide an accurate prediction of fatal and injury crashes, which is crucial to ensuring effective traffic collision management. [ABSTRACT FROM AUTHOR]

AVs are affected by reduced maneuverability and performance due to the degradation of sensor performances in fog. Such degradation can cause significant object detection errors in AVs' safety-critical conditions. For instance, YOLOv5 performs well under favorable weather but is affected by mis-detections and false positives due to atmospheric scattering caused by fog particles. The existing deep object detection techniques often exhibit a high degree of accuracy. Their drawback is being sluggish in object detection in fog. Object detection methods with a fast detection speed have been obtained using deep learning at the expense of accuracy. The problem of the lack of balance between detection speed and accuracy in fog persists. This paper presents an improved YOLOv5-based multi-sensor fusion network that combines radar object detection with a camera image bounding box. We transformed radar detection by mapping the radar detections into a two-dimensional image coordinate and projected the resultant radar image onto the camera image. Using the attention mechanism, we emphasized and improved the important feature representation used for object detection while reducing high-level feature information loss. We trained and tested our multi-sensor fusion network on clear and multi-fog weather datasets obtained from the CARLA simulator. Our results show that the proposed method significantly enhances the detection of small and distant objects. Our small CR-YOLOnet model best strikes a balance between accuracy and speed, with an accuracy of 0.849 at 69 fps. [ABSTRACT FROM AUTHOR]

The article introduces and discusses the sensors used in autonomous cars. The reliability of these devices is crucial for the proper operation of autonomous driving systems. The research works related to the issue of the performance of autonomous sensors in adverse weather conditions is discussed and critically analysed. The negative effects caused by bad weather conditions are characterised. The paper presents the result of author's own research concern on the effects of rain, snow and fog on lidar measurements. The results obtained are presented, detailing the most important threats from each weather phenomenon. Attempts currently being made to address these issues are presented as well. The paper concludes with a summary of the research results, the current state of knowledge and suggestions for future developments. [ABSTRACT FROM AUTHOR]

Roadways in Wyoming are characterized by challenging horizontal profiles, vertical profiles, a combination of the two and adverse weather conditions, all of which affect vehicle stability. In this study, we investigated the impact of different operating speeds when negotiating combined horizontal and vertical curves under unfavorable environmental conditions on Wyoming's interstates via vehicle dynamics simulation software. The simulation tools provided the acting forces on each tire of the vehicle and the side friction (skidding) margins. This allowed for examining the interaction between vehicle dynamics and road geometry in such alignments. Also, linear regression analysis was implemented to investigate the skidding margins based on the simulation results to demonstrate when a vehicle is more likely to deviate from its desired trajectory. Specifically, this examines the contributing factors that significantly influence the skidding margins. The results indicated that: 1)the skidding margins are dramatically decreased by adverse weather conditions even with lower degree of curvature and gradient values of combined curves and more particularly at higher operating speeds conditions. Increasing the vehicle speed on the curve by 10%, the skidding margin dropped by 15%. 2) Compared to heavy trucks and sports utility vehicles (SUVs), passenger cars require the highest side friction demand. 3) The effect of applying brakes on vehicle stability depends on the road surface condition; applying the brakes on snowy road surfaces increases the potential of vehicle skidding especially for heavy trucks. This study assessed the curve speed limits and showed how important to assign safe and appropriate limits speed since the skidding likelihood is significantly sensitive to the vehicle speeds. This study is beneficial to Wyoming's roadway agencies since hazardous sections having combined horizontal and vertical curves are identified. Also, critical situations that require additional attention from law enforcement agencies are pinpointed. Finally, recommendations that are valuable to roadway agencies are made based on this study's findings.

Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. Existing techniques in the literature typically focus on restoring specific degradations using separate models, leading to computational inefficiency. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. To evaluate the effectiveness of MACGAN, extensive qualitative and quantitative comparisons are conducted with state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. The results highlight the superior performance of MACGAN in terms of scene visibility improvement and restoration quality. Additionally, MACGAN is tested on real-world unseen image domains, including smog, dust, fog, rain, snow, and lightning, further validating its generalizability and robustness. Furthermore, an ablation study is conducted to analyze the contributions of the discriminator and attention blocks within the MACGAN architecture. The results confirm that both components play significant roles in the effectiveness of MACGAN, with the discriminator ensuring adversarial training and the attention blocks effectively capturing and enhancing important image features.