Vehicle Density Research Articles

Vehicle Detection in High Density Traffic Surveillance Data using YOLO.v5

Abstract: Computer vision is one of the prime domains that enable to derive meaningful and crisp information from digital media, such as images, videos, and other visual inputs. Background: Detection and correctly tracking the moving objects in a video streaming is still a challenging problem in India. Due to the high density of vehicles, it is difficult to identify the correct objects on the roads. Methods: In this work, we have used a YOLO.v5 (You Only Look Once) algorithm to identify the different objects on road, such as trucks, cars, trams, and vans. YOLO.v5 is the latest algorithm in the family of YOLO. To train the YOLO.v5, KITTY dataset was used having 11682 images having different objects in a traffic surveillance system. After training and validating the dataset, three different models have been constructed setting various parameters. To further validate the proposed approach, results have also been evaluated on the Indian traffic dataset DATS_2022. Results: All the models have been evaluated using three performance metrics, such as precision, recall, and mean average precision (MAP). The final model has attained the best performance on KITTY dataset as 93.5% precision, 90.7% recall, and 0.67 MAP for different objects. The results attained on the Indian traffic dataset DATS_2022 included 0.65 precision, 0.78 recall value, and 0.74 MAP for different objects. Conclusion: The results depict the proposed model to have improved results as compared to stateof-the-art approaches in terms of performance and also reduce the computation time and object loss.

Traffic Stream Models on Road Section in Samarinda City (Case Study on AW. Syahranie Street)

The interaction of loads in the transportation system is called traffic flow. Traffic flow interactions are used in transportation facility planning, design, and operation. This quantitative study focuses on Jalan Abdul Wahab Syahranie in Samarinda City. It employs the Greenshield method, which analyzes numerical data generated by the linear equation method, to find a mathematical relationship between vehicle speed and density, volume and density, and volume and velocity. According to the analysis findings, the higher the vehicle volume, the slower the vehicle speed, and the higher the density value

Analisis Pengaruh Kendaraan Yang Melakukan Putar Balik Terhadap Kinerja Ruas Jalan (Studi Kasus Pada U–Turn Jl. Bypass Padang)

Transportation has an important role in human life, because transportation has a big influence on society, economic and social political development of a country. research discusses analysis of influence of vehicles making a U-turn on Bypass No. KM 15, Aie Pacah, Tangah City, Padang City, West Sumatra. Research purposes is to determine level of service that occurs in traffic flow, to obtain this aim PKJI 2014 is used. This research obtains average travel time for vehicles making a U-Turn, length of queue when making a U-Turn, average travel time average number of vehicles disturbed and not disturbed by U-Turns and knowing level of service on that road section. From data processing it can be concluded that peak hour vehicle speeds are slower than non-peak hour vehicle speeds due to high traffic flow. Meanwhile, waiting time when a vehicle is about to turn around, during peak hours vehicles wait longer than during non-peak hours because volume of vehicles is denser during peak hours. Average queue length in opposite direction during peak hours is longer than during non-peak hours due to the density of vehicles during peak hours, it can be concluded that level of service C.

The Implication of Different Transmission Protocols for Vehicular Networks using NS-2

A vehicular network, categorized as an ad-hoc network, operates without fixed base station infrastructure or centralized management. In this setup, each network entity can serve as a router or a host, facilitating communication via multiple links. Unlike a mobile ad-hoc network, a vehicular network allows nodes to freely join or leave the network. For data transmission, various network layers are involved in delivering packets, with TCP and UDP protocols commonly employed. However, prior research has highlighted the limitations of Vehicular Ad-Hoc Networks (VANETs), particularly due to the surge in vehicular numbers on roads. This situation can trigger issues such as network congestion, leading to increased packet delivery delays and potential packet drops, ultimately compromising network performance. Moreover, when vehicles travel at high speeds on highways, quick message transmission is crucial, often without waiting for acknowledgments from both the transmitter and receiver. To address these challenges, some of the benefits of the User Datagram Protocol (UDP) can be integrated into vehicular network technologies. Consequently, this study aims to assess the data transfer performance between Transmission Control Protocol (TCP) and UDP, focusing on metrics like packet delivery ratio, packet loss, and packet drop, while varying vehicle density. The research location was Persiaran Permai, Seksyen 7, Shah Alam, Malaysia, and simulation was conducted using tools such as JOSM, MOVE, and NS-2. The findings reveal noteworthy differences: TCP exhibits a superior average packet delivery ratio (99.44% vs. 83.56%) and lower packet loss (0.56% vs. 16.45%) compared to UDP. Conversely, UDP demonstrates better performance in terms of average packet drop (0 compared to 6.75) when compared to TCP.

Pencarian Rute Terpendek menggunakan Algoritma Genetika (Studi Kasus : Pengoptimalan Mobilitas Kota Salatiga Terhadap Kota-Kota Tetangga)

The increase in population in an area has a significant impact on vehicle density in that area. The problem that often arises is traffic jams that occur on several routes at once. This factor is a common problem, which is quite disturbing to the public and road users. To overcome this problem, the genetic algorithm method is used as a solution method. This case study was set at the regional or city level around Salatiga City, including Ambarawa City, Semarang City, Boyolali City, Solo City and Magelang City. By using the genetic algorithm method, the fastest route with the shortest distance can be found. The Genetic Algorithm used in this research allows optimal shortest route search results. Apart from that, this research can also minimize the distance and travel time of several alternative routes obtained, thus providing significant benefits in developing the transportation system in the region.

The Effectiveness of Traffic Flow Scenarios during Eid Al-Fitr at The Sidoarjo Tollgates Based on Microsimulation Modeling

On the eve of Eid al-Fitr 2023, there was an increase in the number of vehicles heading eastbound of Java Island through the Transjawa Toll Road from the normal traffic flow. The drastic increase in vehicle volume resulted in congestion at the Sidoarjo Tollgate. An effort to unravel the existing traffic congestion was to implement diversion and contraflow scenarios. This study was conducted to prove the most effective scenario to overcome transportation problems during the homecoming flow through microscopic simulations using PTV VISSIM software. In the diversion scenario, 35% of vehicles heading south will be diverted to exit through Sidoarjo 1 Tollgate. This scenario caused an increase in queue length by 34.66% and a delay of 28 seconds at Sidoarjo 1 Tollgate. On the other hand, with the same scenario, there is a decrease in queue length of 16.84% and a decrease in delay time of 58 seconds at Sidoarjo 2 Tollgate. Regarding average speed, there is a decrease of 18.24% on the road section after Sidoarjo 2 Tollgate due to merging. Under the contraflow scenario, there is no significant change in queue length and delay time at both gates, but there is an increase in the average speed of 62.22% at Sidoarjo 2 Tollgate. The simulation showed that the diversion scenario only moves the density of vehicles. In contrast, the contraflow scenario was an effective alternative to break down the density in the 2023 homecoming flow, as evidenced by the increased average speed.

Big data vehicle density management in vehicular ad-hoc network

<span>Smart city project is today a domain of interest to community research which play well-known role in road traffic management. Data exchange became complicated in terms of capacity in the intelligent transport system (ITS), and without the raise of big data, the treatment is very difficult to manage. vehicular ad-hoc network (VANETs) faces many challenges mainly the voluminous data generated by different actors of VANET environment. <br /> We propose a real time anomalies detection system in an instantaneous way with parallel data treatment. The system method intends to compute precisely vehicle density at each section on each road, which help to handle the traffic and forward to vehicles information about the road and the best safe path to reach their destination. Also, we build anomalies prediction system based on machine learning framework, it is a good solution for avoiding traffic congestion and limiting the risk of accidents. The simulation results demonstrate that the proposed system method reduces congestion greatly by taking into account the load balancing and therefore avoids saturation and reduces accidents. It should also be noted that the results obtained show that the system is characterized by low latency and high accuracy.</span>

An Anti-Collision Algorithm for Self-Organizing Vehicular Ad-Hoc Network Using Deep Learning

The rapid increase of the number of motor vehicles over the last several decades has driven a corresponding increase in the severity of traffic congestion, which has exhibited a considerable human impact. Intelligent anti-collision control via inter-vehicle communication technology can facilitate vehicles adhering to spacing speed standards and improve road utilization and traffic efficiency. In this paper, we apply a deep learning image estimation model based on joint attention mechanism. The network framework uses a deep estimation network Yolov5 and a location based VANET information fast transmission strategy to work together. This paper mainly considers vehicle distance measurement technology as a point of entry to study multi-sensor information fusion for vehicle collision prevention technology based on the self-organizing vehicular ad-hoc network (VANET). This paper also proposes a solution based on the strategy of one-way transmission of shared information and dynamic valuation of a cluster distance threshold with vehicle density. The proposed vehicle anti-collision control algorithm is designed to realize dynamic vehicle control via inter-vehicle communication. In this paper, the two-way coupling of traffic flow and network simulator is used to randomly generate vehicle nodes on the road, and the behavior of the anti-collision system is simulated. The experimental results show that the predetermined control goal is achieved, which demonstrates the effectiveness of the proposed algorithm.

Temperature fields analysis and heat dissipation structure design of an film capacitor in new energy vehicle

The high-temperature resistance performance of film capacitors in motor controllers faces greater challenges with the development of high voltage and high power density of new energy vehicles (NEVs). In this study, a typical film capacitor is taken as the object of research; simulations of temperature fields and experiments on temperature rises are conducted. Additionally, a heat dissipation structure is designed to enhance the high-temperature resistance performance of the capacitor. Firstly, the temperature field distributions of the capacitor under different ripple currents and ambient temperatures are analyzed using ANSYS electro-thermal coupling simulation. Then, under the same operating conditions, experiments on the temperature rises are conducted on the capacitor, which is installed with K-type thermocouples to verify the accuracy of the electro-thermal coupling simulation. Furthermore, an external heat dissipation structure consisting of a micro-channel liquid cold plate is designed for the capacitor, and the effectiveness of the external cold plate is verified through electro-thermal coupling and FLUENT simulations. It is found that under the operating conditions of 85 ?C ambient temperature and 175 A ripple current, the maximum temperature of the capacitor with the external cold plates decreases by 46.08% compared to the original capacitor. The results indicate that the external cold plates effectively improve the high-temperature resistance capability of the film capacitors in electric vehicles.

Prediction of Traffic Congestion in Vehicular Ad-Hoc Networks Employing Extreme Deep Learning Machines (Edrlm)

Vehicular Ad-Hoc Networks (VANETs) represent a crucial component of intelligent transportation systems (ITS), enabling vehicles to communicate with each other and with roadside infrastructure. Predicting traffic congestion in VANETs is essential for enhancing road safety, optimizing traffic flow, and improving overall transportation efficiency. Traditional machine learning methods have shown promise in this domain; however, they often fall short in handling the complex, high-dimensional data typical of VANETs. To address these challenges, this study employs Extreme Deep Learning Machines (EDRLM), an advanced deep learning technique, for traffic congestion prediction. The EDRLM framework leverages the strengths of deep neural networks and extreme learning machines, offering a robust and scalable solution for processing the dynamic and heterogeneous data in VANETs. By integrating feature extraction, selection, and prediction into a unified model, EDRLM can capture intricate patterns and temporal dependencies within traffic data. The proposed model is trained and validated using real-world VANET datasets, incorporating various traffic parameters such as vehicle speed, density, and inter-vehicular distances. Our experimental results demonstrate that EDRLM outperforms conventional machine learning algorithms in terms of prediction accuracy, computational efficiency, and robustness to noise and missing data. The model's ability to provide timely and precise congestion predictions can facilitate proactive traffic management strategies, including dynamic routing and adaptive traffic signal control, ultimately leading to reduced travel times and enhanced road safety. This study underscores the potential of EDRLM in transforming traffic management in VANETs, paving the way for more intelligent and adaptive ITS solutions. Future research directions include exploring hybrid models combining EDRLM with other advanced machine learning techniques and expanding the framework to accommodate emerging vehicular communication technologies such as 5G and Internet of Things (IoT) devices.

Multi-Agent Attention Double Actor-Critic Framework for Intelligent Traffic Light Control in Urban Scenarios With Hybrid Traffic

In real-world urban environments, hybrid and disorder traffic brings new challenges for the intelligent traffic light control system (ITLCS). Apart from coordinating traffic flows around intersections, the ITLCS is responsive to ensuring high priority vehicles pass through intersections quickly. To this end, we formulate the multiple intersections' decision-making problem as a Semi-Markov game and propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-agent attention double actor-critic (MAADAC)</i> framework to solve this game, integrating the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">options framework</i> with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">graph attention networks (GATs)</i> . Specifically, the options framework empowers agents to learn to make a long sequence of satisfactory decisions, such as keeping a reasonable phase for a short period to ensure high priority vehicles pass through intersections quickly. Besides, we adopt GATs to capture graph-structure mutual influences among agents. We set up a simulator based on real-world city road networks and conduct extensive experiments to evaluate the performance of MAADAC. The experimental results show that MAADAC can reduce high priority vehicles' waiting time in the interval of 18.16%-38.14% versus the density of vehicles in real-world urban scenarios over several state-of-the-art approaches. Also, our framework can guarantee the passing efficiency of high priority vehicles under various traffic conditions with the change in the proportion of high priority vehicles.

Research on controlling intelligent traffic light systems based on artificial intelligence algorithms

Intelligent traffic light systems are becoming an important application in traffic coordination. Artificial intelligence with deep learning models effectively recognizes vehicles participating in traffic from extracted images or real-time videos with high speed and accuracy. This paper presents an intelligent traffic light system based on real-time image analysis using the YOLOv8 artificial intelligence method to determine the density of vehicles participating in traffic at intersections. Consequently, the system automatically controls the timing of the traffic lights on the roads to align with the actual traffic flow. Through this method, the operation of traffic lights is continuously adjusted, ensuring efficient and safe traffic flow.

Airspace Congestion, flow Relations, and 4-D fundamental Diagrams for advanced urban air mobility

This paper develops theoretical macroscopic air traffic flow models that relate vehicle density and spacing to traffic flow (throughput) measures under different operational parameters for unstructured airspace in the Advanced Air Mobility (AAM) context. Recognizing the role of conflicts in air traffic flow, we relate vehicle density to the frequency of conflict occurrence in airspace using a gas-kinetic analogy. The number of conflicts is then related to vehicle speeds using an average speed loss per conflict. The effects of the speed reductions are coupled with density to explore the fundamental diagram between flow rate and density. The theoretical models are tested and validated with simulated results for a number of parameter levels. The models can be applied for quick predictions of future traffic flow conditions, which will be especially useful for operators or air traffic flow management systems. The theoretical and simulated findings also provide operational and policy insights for AAM operators, planners, and modelers. Notable insights include the critical role of aircraft density in air traffic flow and the variable impact of that density on traffic flow behavior. AAM operators and planners will need to closely manage the airspace density to avoid large numbers of conflicts simultaneously and maintain acceptable travel times and throughputs. Key operational parameters such as aircraft spacing requirements and maximum aircraft speeds were also found to have significant impacts on traffic flow behavior, and offer policy avenues for managing air traffic.

Machine Learning-Based Risk-Aware Congestion Control Scheme for Minimization of Information Loss in Dense VANET Environment

Vehicular Ad-Hoc Network is one of the most growing research fields and has become a promising topic for researchers. Day by day, vehicle density increases, causing very serious issues like road accidents and traffic jams. These issues can be minimized by a periodic exchange of awareness messages among the vehicles. Traffic density increases transmission of awareness messages, which causes channel congestion and degrades safety services, so congestion control schemes must ensure that the channel load should be below a particular threshold, boost the quality of services and minimize information loss and delay in the network. This paper proposes a machine learning-based risk-aware congestion control (MLB-RACC) scheme which is an efficient congestion control scheme based on the modified [Formula: see text] -means machine learning algorithms. MLB-RACC technique processes the input data and helps to improve the quality of services in the automotive industry. It works in three phases: detecting congestion, clustering of vehicles and controlling the broadcasting of awareness messages for decreasing the channel load. MLB-RACC scheme works by grouping the nearest vehicles and the number of groups or clusters is decided on the basis of transmission range/transmission power. The group member selects adaptive transmission rate by looking at the channel busy ratio (CBR). In this technique, message generation rate is controlled at two levels: first is at the clustering level and second is during the checking of CBR. The scheme is implemented through MATLAB, NS2 and the SUMO platform and provides evidence for the minimization of information loss by analyzing the throughput, packet loss and end-to-end delay in comparison to ordinary decentralized congestion control (DCC) technique.

Objects detection theory for evaluating the city environmental quality

IntroductionThe primary focus of this paper is to assess urban ecological environments by employing object detection on spatial-temporal data images within a city, in conjunction with other relevant information through data mining.MethodsFirstly, an improved YOLOv7 algorithm is applied to conduct object detection, particularly counting vehicles and pedestrians within the urban spatial-temporal data. Subsequently, the k-means superpixel segmentation algorithm is utilized to calculate vegetation coverage within the urban spatial-temporal data, allowing for the quantification of vegetation area. This approach involves the segmentation of vegetation areas based on color characteristics, providing the vegetation area’s measurements. Lastly, an ecological assessment of the current urban environment is conducted based on the gathered data on human and vehicle density, along with vegetation coverage.ResultsThe enhanced YOLOv7 algorithm employed in this study yields a one-percent improvement in mean AP (average precision) compared to the original YOLOv7 algorithm. Furthermore, the AP values for key categories of interest, namely, individuals and vehicles, have also improved in this ecological assessment.DiscussionSpecifically, the AP values for the ‘person’ and ‘pedestrian’ categories have increased by 13.9% and 9.3%, respectively, while ‘car’ and ‘van’ categories have seen AP improvements of 6.7% and 4.9%. The enhanced YOLOv7 algorithm contributes to more accurate data collection regarding individuals and vehicles in subsequent research. In the conclusion of this paper, we further validate the reliability of the urban environmental assessment results by employing the Recall-Precision curve.

Environment-Aware Adaptive Reinforcement Learning-Based Routing for Vehicular Ad Hoc Networks.

With the rapid development of the intelligent transportation system (ITS), routing in vehicular ad hoc networks (VANETs) has become a popular research topic. The high mobility of vehicles in urban streets poses serious challenges to routing protocols and has a significant impact on network performance. Existing topology-based routing is not suitable for highly dynamic VANETs, thereby making location-based routing protocols the preferred choice due to their scalability. However, the working environment of VANETs is complex and interference-prone. In wireless-network communication, the channel contention introduced by the high density of vehicles, coupled with urban structures, significantly increases the difficulty of designing high-quality communication protocols. In this context, compared to topology-based routing protocols, location-based geographic routing is widely employed in VANETs due to its avoidance of the route construction and maintenance phases. Considering the characteristics of VANETs, this paper proposes a novel environment-aware adaptive reinforcement routing (EARR) protocol aimed at establishing reliable connections between source and destination nodes. The protocol adopts periodic beacons to perceive and explore the surrounding environment, thereby constructing a local topology. By applying reinforcement learning to the vehicle network's route selection, it adaptively adjusts the Q table through the perception of multiple metrics from beacons, including vehicle speed, available bandwidth, signal-reception strength, etc., thereby assisting the selection of relay vehicles and alleviating the challenges posed by the high dynamics, shadow fading, and limited bandwidth in VANETs. The combination of reinforcement learning and beacons accelerates the establishment of end-to-end routes, thereby guiding each vehicle to choose the optimal next hop and forming suboptimal routes throughout the entire communication process. The adaptive adjustment feature of the protocol enables it to address sudden link interruptions, thereby enhancing communication reliability. In experiments, the EARR protocol demonstrates significant improvements across various performance metrics compared to existing routing protocols. Throughout the simulation process, the EARR protocol maintains a consistently high packet-delivery rate and throughput compared to other protocols, as well as demonstrates stable performance across various scenarios. Finally, the proposed protocol demonstrates relatively consistent standardized latency and low overhead in all experiments.

A Vehicle Density Estimation Traffic Light Control System Using a Two-Dimensional Convolution Neural Network

One of the world’s challenges is the amount of traffic on the roads. Waiting for the green light is a major cause of traffic congestion. Low throughput rates and eventual congestion come from many traffic signals that are hard coded, irrespective of the volume of the amount of traffic. Instead of depending on predefined time intervals, it is essential to build a traffic signal control system that can react to changing vehicle densities. Emergency vehicles, like ambulances, must be given priority at the intersection so as not to spend more time at the traffic light. Computer vision techniques can be used to improve road traffic signal control and reduce real-time traffic delays at intersections without the requirement for substantial infrastructure analysis. Long wait times and significant energy consumption are just two of the problems of the current traffic signal control system. To optimal efficiency, the traffic signal’s duration must be dynamically changed to account for current traffic volume. To lessen congestion, the approach taken in this research focuses on modifying traffic signal time determined by the density of vehicles at the crossroads. The main purpose of this article is to demonstrate heavy traffic and emergency vehicle prioritization from all directions at the traffic intersection for a speedy passage. Using the Pygame tool, the proposed method in this study, which includes a mechanism for estimating traffic density and prioritization by counting vehicles at a traffic junction, is demonstrated. The vehicle throughput for the adaptive traffic light built using Pygame is compared with the vehicle pass rate for the adaptive traffic light built using Simulation of Urban Mobility (SUMO). The simulation results show that the adaptive traffic light built using Pygame achieves 90% throughput compared to the adaptive traffic light built using SUMO. A Two-Dimensional Convolutional Neural Network (2D-CNN) is implemented using Tensorflow for vehicle classification. The 2D-CNN model demonstrated 96% accuracy in classifying vehicles using the test dataset. Additionally, emergency vehicles, such as ambulances, are given priority for quick passing.

An improved deep reinforcement learning routing technique for collision-free VANET

Vehicular Adhoc Networks (VANETs) is an emerging field that employs a wireless local area network (WLAN) characterized by an ad-hoc topology. Vehicular Ad Hoc Networks (VANETs) comprise diverse entities that are integrated to establish effective communication among themselves and with other associated services. Vehicular Ad Hoc Networks (VANETs) commonly encounter a range of obstacles, such as routing complexities and excessive control overhead. Nevertheless, the majority of these attempts were unsuccessful in delivering an integrated approach to address the challenges related to both routing and minimizing control overheads. The present study introduces an Improved Deep Reinforcement Learning (IDRL) approach for routing, with the aim of reducing the augmented control overhead. The IDRL routing technique that has been proposed aims to optimize the routing path while simultaneously reducing the convergence time in the context of dynamic vehicle density. The IDRL effectively monitors, analyzes, and predicts routing behavior by leveraging transmission capacity and vehicle data. As a result, the reduction of transmission delay is achieved by utilizing adjacent vehicles for the transportation of packets through Vehicle-to-Infrastructure (V2I) communication. The simulation outcomes were executed to assess the resilience and scalability of the model in delivering efficient routing and mitigating the amplified overheads concurrently. The method under consideration demonstrates a high level of efficacy in transmitting messages that are safeguarded through the utilization of vehicle-to-infrastructure (V2I) communication. The simulation results indicate that the IDRL routing approach, as proposed, presents a decrease in latency, an increase in packet delivery ratio, and an improvement in data reliability in comparison to other routing techniques currently available.

Air Quality Mapping and Urban Planning for Sustainable Urban Ecology: A Case Study of Chandigarh, India

In the fast urbanizing world, it has become vital to study urban ecology so as to understand where and how anthropogenic activities impair the urban environment, including air quality; and how living conditions can be improved by urban planning without mortifying urban ecology. This may require innovative technological ideas to efficiently and judiciously utilize the limited urban space. Air quality mapping using Geographic Information System (GIS) provides one such effective tool to urban planners to identify and target specific areas for air quality management in urban setting. In the present study, the air quality mapping of a well-planned city of Chandigarh (India) with proper environmental management zoning has revealed that the air quality index (AQI) of the city falls under “Moderately Polluted (101-200)” category primarily due to annual average concentrations of (range: 44.17-68.87; overall: 56.64) and (range: 99.32-129.39; overall: 111.92) being higher than the permissible levels of 40 and 60 respectively as per Indian standards at all locations as well as for overall city. The study has identified vehicular traffic as the primary reason responsible for the moderately polluted air quality of the city that has the highest vehicle density (878 per 1,000 population) in India. The paper has also suggested measures that may be incorporated during designing and developing the physical and social infrastructures in the city so as to judiciously and efficiently utilize the limited urban space.

DSNet: A vehicle density estimation network based on multi-scale sensing of vehicle density in video images

DSNet: A vehicle density estimation network based on multi-scale sensing of vehicle density in video images