Efficient and Cost-Effective Vehicle Detection in Foggy Weather for Edge/Fog-Enabled Traffic Surveillance and Collision Avoidance Systems

Vision-based vehicle detection in adverse weather conditions such as fog,haze,and mist is a challenging research area in the fields of autonomous vehicles,collision avoidance,and Internet of Things(IoT)-enabled edge/fog computing traffic surveillance and monitoring systems.Efficient and cost-effective vehicle detection at high accuracy and speed in foggy weather is essential to avoiding road traffic collisions in real-time.To evaluate vision-based vehicle detection performance in foggy weather conditions,state-of-the-art Vehicle Detection in Adverse Weather Nature(DAWN)and Foggy Driving(FD)datasets are self-annotated using the YOLO LABEL tool and customized to four vehicle detection classes:cars,buses,motorcycles,and trucks.The state-of-the-art single-stage deep learning algorithms YOLO-V5,and YOLO-V8 are considered for the task of vehicle detection.Furthermore,YOLO-V5s is enhanced by introducing attention modules Convolutional Block Attention Module(CBAM),Normalized-based Attention Module(NAM),and Simple Attention Module(SimAM)after the SPPF module as well as YOLO-V5l with BiFPN.Their vehicle detection accuracy parameters and running speed is validated on cloud(Google Colab)and edge(local)systems.The mAP50 score of YOLO-V5n is 72.60%,YOLOV5s is 75.20%,YOLO-V5m is 73.40%,and YOLO-V5l is 77.30%;and YOLO-V8n is 60.20%,YOLO-V8s is 73.50%,YOLO-V8m is 73.80%,and YOLO-V8l is 72.60%on DAWN dataset.The mAP50 score of YOLO-V5n is 43.90%,YOLO-V5s is 40.10%,YOLO-V5m is 49.70%,and YOLO-V5l is 57.30%;and YOLO-V8n is 41.60%,YOLO-V8s is 46.90%,YOLO-V8m is 42.90%,and YOLO-V8l is 44.80%on FD dataset.The vehicle detection speed of YOLOV5n is 59 Frame Per Seconds(FPS),YOLO-V5s is 47 FPS,YOLO-V5m is 38 FPS,and YOLO-V5l is 30 FPS;and YOLO-V8n is 185 FPS,YOLO-V8s is 109 FPS,YOLO-V8m is 72 FPS,and YOLO-V8l is 63 FPS on DAWN dataset.The vehicle detection speed of YOLO-V5n is 26 FPS,YOLO-V5s is 24 FPS,YOLO-V5m is 22 FPS,and YOLO-V5l is 17 FPS;and YOLO-V8n is 313 FPS,YOLO-V8s is 182 FPS,YOLO-V8m is 99 FPS,and YOLO-V8l is 60 FPS on FD dataset.YOLO-V5s,YOLO-V5s variants and YOLO-V5l_BiFPN,and YOLO-V8 algorithms are efficient and cost-effective solution for real-time vision-based vehicle detection in foggy weather.

FISS GAN:A Generative Adversarial Network for Foggy Image Semantic Segmentation

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their texture.No method has previously been developed to directly explore the relationship between foggy images and semantic segmentation images.We investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation GAN.The edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation GAN.The semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation images.Experiments on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

MULTI-SCALE CHARACTERISTICS STUDY ON THE FREQUENCY OF FOGGY DAYS OCCURRING IN NANJING IN DECEMBER 2007

Based on the number of foggy days in Nanjing in December from 1980 to 2011, we analyzed the surface temperature and atmospheric circulation characteristics of foggy years and less-foggy years. Positive anomalies of the Arctic Oscillation(AO) were found to weaken the East Asian trough, which is not conducive to the southward migration of cold air. Simultaneously, this atmospheric condition favors stability as a result of a high-pressure anomaly from the middle Yangtze River Delta region. A portion of La Nia events increases the amount of water vapor in the South China Sea region, so this phenomenon could provide the water vapor condition required for foggy days in Nanjing.Based on the data in December 2007, which contained the greatest number of foggy days for the years studied, the source of fog vapor in Nanjing was primarily from southern China and southwest Taiwan Island based on a synoptic scale study. The water vapor in southern China and in the southwestern flow increased, and after a period of 2-3 days,the humidity in Nanjing increased. Simultaneously, the water vapor from the southwestern of Taiwan Island was directly transported to Nanjing by the southerly wind. Therefore, these two areas are the most important sources of water vapor that results in heavy fog in Nanjing. Using the bivariate Empirical Orthogonal Function(EOF) mode on the surface temperature and precipitable water vapor, the first mode was found to reflect the seasonal variation from early winter to late winter, which reduced the surface temperature on a large scale. The second mode was found to reflect a large-scale,northward, warm and humid airflow that was accompanied by the enhancement of the subtropical high, particularly between December 15-21, which is primarily responsible for the consecutive foggy days in Nanjing.

Single foggy image restoration based on spatial correlation analysis of dark channel prior

Focusing on the degradation of foggy images, a restora- tion approach from a single image based on spatial correlation of dark channel prior is proposed. Firstly, the transmission of each pixel is estimated by the spatial correlation of dark channel prior. Secondly, a degradation model is utilized to restore the foggy image. Thirdly, the final recovered image, with enhanced contrast, is obtained by performing a post-processing technique based on just-noticeable difference. Experimental results demonstrate that the information of a foggy image can be recovered perfectly by the proposed method, even in the case of the abrupt depth changing scene.

A method to generate foggy optical images based on unsupervised depth estimation

For traffic object detection in foggy environment based on convolutional neural network(CNN),data sets in fog-free environment are generally used to train the network directly.As a result,the network cannot learn the object characteristics in the foggy environment in the training set,and the detection effect is not good.To improve the traffic object detection in foggy environment,we propose a method of generating foggy images on fog-free images from the perspective of data set construction.First,taking the KITTI objection detection data set as an original fog-free image,we generate the depth image of the original image by using improved Monodepth unsupervised depth estimation method.Then,a geometric prior depth template is constructed to fuse the image entropy taken as weight with the depth image.After that,a foggy image is acquired from the depth image based on the atmospheric scattering model.Finally,we take two typical object-detection frameworks,that is,the two-stage object-detection Fster region-based convolutional neural network(Faster-RCNN)and the one-stage object-detection network YOLOv4,to train the original data set,the foggy data set and the mixed data set,respectively.According to the test results on RESIDE-RTTS data set in the outdoor natural foggy environment,the model under the training on the mixed data set shows the best effect.The mean average precision(mAP)values are increased by 5.6%and by 5.0%under the YOLOv4 model and the Faster-RCNN network,respectively.It is proved that the proposed method can effectively improve object identification ability foggy environment.

Intelligent Speed Limit System for Safe Expressway Driving in Rainy and Foggy Weather Based on Internet of Things

The feature bends and tunnels of mountainous expressways are often affected by bad weather,specif-ically rain and fog,which significantly threaten expressway safety and traffic efficiency.In order to solve this problem,a vehicle–road coordination system based on the Internet of Things(IoT)is developed that can share vehicle–road information in real time,expand the environmental perception range of vehicles,and realize vehicle–road collaboration.It helps improve traffic safety and efficiency.Further,a vehicle–road cooperative driving assistance system model is introduced in this study,and it is based on IoT for improving the driving safety of mountainous expressways.Considering the influence of rain and fog on driving safety,the interaction between rainfall,water film,and adhesion coefficient is analyzed.An intelligent vehicle–road coordination assistance system is constructed that takes in information on weather,road parameters,and vehicle status,and takes the stopping sight distance model as well as rollover and sideslip model as boundary constraints.Tests conducted on a real expressway demonstrated that the assistance system model is helpful in bad weather conditions.This system could promote intelligent development of mountainous expressways.

Performance Analysis and Prediction for a Free-Space Optical Communication System under Foggy Absorption

We analyzed the performance of a freespace optical(FSO)system in this study,considering the combined effects of atmospheric turbulence,fog absorption,and pointing errors.The impacts of atmospheric turbulence and foggy absorption were modeled using the Fisher-Snedecor F distribution and the Gamma distribution,respectively.Next,we derived the probability density function(PDF)and cumulative probability density function of the optical system under these combined effects.Based on these statistical findings,closed-form expressions for various system metrics,such as outage probability,average bit error rate(BER),and ergodic capacity,were derived.Furthermore,we used a deep neural network(DNN)to predict the ergodic capacity of the system,achieving reduced running time and improved accuracy.Finally,the accuracy of the prediction results was validated by comparing them with the analytical results.

Objective measurement for image defogging algorithms

Since there is lack of methodology to assess the performance of defogging algorithm and the existing assessment methods have some limitations,three new methods for assessing the defogging algorithm were proposed.One was using synthetic foggy image simulated by image degradation model to assess the defogging algorithm in full-reference way.In this method,the absolute difference was computed between the synthetic image with and without fog.The other two were computing the fog density of gray level image or constructing assessment system of color image from human visual perception to assess the defogging algorithm in no-reference way.For these methods,an assessment function was defined to evaluate algorithm performance from the function value.Using the defogging algorithm comparison,the experimental results demonstrate the effectiveness and reliability of the proposed methods.

Impact of climate variation on fog in China

Using foggy days and mean temperature and relative humidity data of 602 stations from January to December in the period 1961-2003 in China, the relationship between variations of foggy days and temperature and its possible reason for the 43 years were analyzed by regression, correlation and contrastive analysis methods. The results show that the higher （lower） the mean temperature and the lower （higher） the relative humidity correspond to less （more） foggy days, the relationship is the best in the western, northern and eastern Sichuan, Yunnan-Guizhon Plateau, and southeast highland in China. This induces a decrease in relative humidity when the climate becomes warmer, and eventually brings about a decrease in foggy days in China.

Seasonal variations and size distributions of water-soluble ions in atmospheric aerosols in Beijing, 2012

The characteristics of water-soluble ions in airborne particulate matter in Beijing were investigated using ion chromatography. The results showed that the total concentrations of ions were 83.7 ± 48.9 μg/m3 in spring, 54.0 ± 17.0 μg/m3 in summer, 54.1 ± 42.9 μg/m3 in autumn, and 88.8 ± 47.7 μg/m3 in winter, respectively. Furthermore, out of all the ions, NO3-,SO42-and NH4＋accounted for 81.2% in spring, 78.5% in summer, 74.6% in autumn, and 76.3%in winter. Mg2＋and Ca2＋were mainly associated with coarse particles, with a peak that ranged from 5.8 to 9.0 μm. Na＋, NH4＋and Cl-had a multi-mode distribution with peaks that ranged from 0.43 to 1.1 μm and 4.7 to 9.0 μm. K＋, NO3-, and SO42-were mainly associated with fine particles, with a peak that ranged from 0.65 to 2.1 μm. The concentrations of Na＋, K＋,Mg2＋, Ca2＋, NH4＋, Cl-, NO3-and SO42-were 2.69, 2.32, 1.01, 4.84, 16.9, 11.8, 42.0, and 44.1 μg/m3 in particulate matter（PM） on foggy days, respectively, which were 1.4 to 7.3 times higher than those on clear days. The concentrations of these ions were 2.40, 1.66, 0.92, 4.95, 17.5,7.00, 32.6, and 34.7 μg/m3 in PM on hazy days, respectively, which were 1.2–5.7 times higher than those on clear days.