Vehicle Counting Research Articles

FlowOptix : A Traffic Signal Control and Management System

The innovation in the field of vehicles has led to the access of vehicles in high reach, thus increasing the number of vehicle counts. But this increase count has created a need of managing the congestion of vehicles on road in a more efficient way. The traditional system and approach of the traffic signal systems isn’t adequate enough to tackle the increasing congestion. The traditional system tends to be efficient where the count is sparse, as the density of vehicles on a particular side of road increases or if the traffic is comparatively larger on one side than other side in such case the approach fails. Hence, the introduced system redesigns the traffic signal system that is static switching to signal switching based on real-time traffic management. So, in this project the switching time of signal will be decided based on real time image detection with good accuracy in dense traffic. This practice can prove its most effectiveness in releasing the congested traffic at an efficient and faster rate.

Sustainable Product Design Strategy: A Comparative Analysis on the M113

This empirical study investigates the relationship between the inventory trends of M113 armored vehicles and sustainable design strategies in the defense sectors of Türkiye and the USA with the perspective of industrial design. Utilizing ARIMA modeling and linear correlation analysis, data collected up to 2022 reveals distinct patterns in vehicle inventory dynamics. The ARIMA analysis produced reliable coefficients despite limited data availability, suggesting feasible numerical assessments. Results indicate that in the USA, the introduction of alternative vehicles such as the Bradley, designed with sustainable principles, led to the phased reduction of M113s. Conversely, Türkiye's inventory trends reflect a linear relationship between the absence of vehicles with design integrity and sustained M113 usage, with modernization efforts prolonging its presence. The study underscores the economic advantages of implementing sustainable product design strategies in armored vehicle development, particularly evident in the USA's production of the Abrams tank and Bradley tracked armored carrier. Despite Türkiye's prolonged reliance on M113s, it highlights the necessity of comprehensive feedback mechanisms and professional units to perform sustainable design strategies. Moreover, it reveals the inefficiency of solely relying on modernization for operational vehicle counts in developing countries, emphasizing the importance of balancing technological advancements with vehicle design integrity. This study sheds light on the evolving nature of sustainable design strategies in defense sectors, urging countries to integrate comprehensive feedback mechanisms and design integrity principles into their armored vehicle development processes for long-term effectiveness and economic viability.

Vehicle Classification and Counting for Traffic Analysis based on Single-stage YOLOv8 Model

Intelligent traffic systems are emerging and becoming part of smart city infrastructure that requires computer vision applications to provide traffic information like vehicle classification and counting in real-time. Vehicle counting helps detect heavy traffic on roads, and vehicle classification helps enforce further processes like speed estimation to enforce speed limit laws based on the vehicle class. Deep learning computer vision-based systems provide automatic feature extractions that are robust to changes in lighting, shadows, and occlusions. This paper proposes a software solution for a real-time traffic monitoring system based on a cutting-edge single-stage deep learning model through the state-of-the-art YOLOv8 algorithm. YOLOv8 is the most recent model of the YOLO family, which provides object detection and classification through its CNN architecture. The proposed work detects vehicles and counts them based on their class. The four common vehicle classes are sedan cars, buses, trucks, and motorcycles, and a counter for each class is displayed on the system’s output screen in real-time and recorded in a log file. The results of the proposed system running on the Nvidia GTX 1070 GPU show an average accuracy of 96.58% with an average error of 3.42% for vehicle detection and an average accuracy of 97.54% with a 2.46% average error for vehicle counting. For vehicle classification, the results for the four vehicle classes (car, bus, truck, and motorcycle) show an accuracy of (94.7%, 94.7%, 96.2%, 99.7%), precision (95%, 100%, 81.4%, 100%), recall (97.9%, 36.3%, 100%, 66.6%), and the f1-score (96.3%, 53.2%, 89.7%, 79.9%), respectively. Index Terms— Computer Vision, Deep Learning, Vehicle Detection, Traffic Analysis, YOLO.

Evaluating the Performance of ETSI-ITS Multi-Stack Protocols for V2V Communication in VANETs: A Simulation Study

The research evaluates various multi-stack protocols for Vehicular Ad-hoc Networks (VANETs), focusing on Vehicle-to-Vehicle (V2V) communication scenarios with Emergency Vehicle (EV) simulations. The study uses the ns-3 network and SUMO (Simulation of Urban MObility) traffic simulators to test these protocols in diverse scenarios, including fluctuating data rates and dense network conditions. By implementing the IEEE 802.11p protocol alongside vehicular message dissemination stacks compliant with ETSI (European Telecommunications Standards Institute) ITS (Intelligent Transport Systems) standards, the study performs simulation experiments with varying vehicle counts, ranging from 20 to 35. It employs two distinct data rate configurations while maintaining a constant transmission power of 23 dBm. The results indicate a decline in the average Packet Reception Ratio (PRR) as vehicle density increases, indicating heightened contention and interference. At the same time, there is an observed increase in average latency, contributing to increased message transmission and reception delays. The quantitative analysis demonstrates an inverse relationship between the average PRR and the total vehicle count when the SEND_CAM message is enabled. On the other hand, disabling SEND_CAM maintains a relatively consistent average PRR across scenarios. Additionally, a positive correlation between vehicle count and average latency underlines the impact of network congestion and interference on communication efficacy within VANETs. Despite suboptimal PRR values falling between 41% and 47%, latency performance remains satisfactory, with average latency durations ranging from 0.154 s to 0.187 s. Notably, the SEND_CAM parameter status shows negligible impact on protocol performance, suggesting that network density plays a more pivotal role. Finally, this study offers valuable insights into the trade-offs and challenges of multi-stack protocols in V2V communication within VANETs. Further optimization efforts are recommended to improve packet reception ratios, especially in high-vehicle-density environments, while maintaining acceptable latency levels. These findings contribute to the ongoing efforts to enhance the reliability and efficiency of communication protocols in VANETs, thus advancing the development of intelligent transportation systems. The study's quantitative protocol performance analysis under varying network conditions provides valuable guidance for optimizing V2V communication deployments in VANETs.

Computing‐efficient video analytics for nighttime traffic sensing

AbstractThe training workflow of neural networks can be quite complex, potentially time‐consuming, and require specific hardware to accomplish operation needs. This study presents a novel analytical video‐based approach for vehicle tracking and vehicle volume estimation at nighttime using a monocular traffic surveillance camera installed over the road. To build this approach, we employ computer vision‐based algorithms to detect vehicle objects, perform vehicle tracking, and vehicle counting in a predefined detection zone. To address low‐illumination conditions, we adapt and employ image noise reduction techniques, image binary conversion, image projective transformation, and a set of heuristic reasoning rules to extract the headlights of each vehicle, pair them belonging to the same vehicle, and track moving candidate vehicle objects continuously across a sequence of video frames. The robustness of the proposed method was tested in various scenarios and environmental conditions using a publicly available vehicle dataset as well as own labeled video data.

TSANet: Forecasting traffic congestion patterns from aerial videos using graphs and transformers

Forecasting traffic congestion patterns in lane-less traffic scenarios is a complex task because of the combination of high & irregular vehicle densities, fluctuating speeds, and the presence of environmental obstacles. Existing techniques like vehicle counting and density prediction, which successfully estimate congestion in lane-based traffic, are unsuitable for lane-less traffic scenarios due to the irregular and unpredictable nature of traffic density patterns. To overcome these challenges, we propose traffic states to measure congestion patterns in lane-less traffic scenarios. Each traffic state is characterized by the spatio-temporal distribution of neighbouring road users, including vehicles and motorcyclists. We employ traffic graphs to capture the spatial distribution of neighbouring road users. Also, we propose a novel method for the automated construction of traffic graphs by leveraging the detection and tracking of individual road users in aerial videos. Further, in order to incorporate the temporal distribution, we utilize a transformer model to capture the evolution of spatial traffic graphs over time. This enables us to forecast future spatio-temporal distributions and their associated traffic states. Our proposed model, named Traffic State Anticipation Network (TSANet), can effectively forecast future traffic states by analysing sequences of current traffic graphs, thereby enhancing our understanding of evolving traffic patterns in lane-less scenarios. Also, to address the lack of publicly available lane-less traffic datasets, we introduce EyeonTraffic (EoT), a large-scale lane-less traffic dataset containing three hours of aerial videos captured at three busy intersections in Ahmedabad city, India. Experimental results on the EoT dataset demonstrate the efficacy of our proposed TSANet in effectively anticipating traffic states across diverse spatial regions within an intersection. In addition, we also show that TSANet generalizes well for previously unseen intersections, making it suitable for analysing various traffic scenarios without the need for explicit training, thereby enhancing its practical applicability.

Neural Network based Route Guidance Strategy in intelligent transportation systems

Traffic congestion in urban areas presents a significant challenge to efficient transportation and sustainable urban development. This paper introduces a Neural Network based Route Guidance Strategy to address the non-linear complexities of urban traffic flow. The strategy demonstrates its capability to optimize traffic flow in real-time by predicting the travel times of candidate routes. A comprehensive simulation study compares the performance of the Neural Network Strategy with traditional traffic management strategies, focusing on traffic flow efficiency, vehicle count stability, and route choice optimization. The results indicate that the Neural Network Strategy significantly enhances traffic management by stabilizing vehicle counts, reducing fluctuations in traffic flux, and achieving a more uniform distribution of vehicles. The paper concludes with an analysis of the experimental results, highlighting the integration of neural networks into traffic management systems as a promising approach to mitigating urban traffic congestion. Future research directions are discussed, emphasizing the potential for real-world implementation and the exploration of advanced neural network models.

An intelligent FL-based vehicle route optimization protocol for green and sustainable IoT connected IoV

The intelligent Internet of Vehicles (IoV) provides superior results in effectively addressing complex transportation challenges. Predicting vehicle traffic, crashes, demand, location, communication, and travel safety are all critical issues in today’s transportation systems. The proposed paper optimizes vehicle traffic by incorporating reroute recommendations, increasing the use of public transportation, and providing onboard vehicle drivers with intelligent health assistance using Federated Learning (FL). This research also focuses on resolving complex transportation issues such as a vehicle’s current location, exact vehicle count information on each route, and onboard vehicle vacant seat information. Furthermore, vehicle communication contributes to the proposed system’s efficiency by avoiding communication delays or information loss to registered users and the cloud server. An intelligent FL-based scheme for vehicle route optimization has been proposed as part of this research to prevent vehicle traffic in a real-time Internet of Things (IoT) connected IoV transportation system. The vehicle detection approach determines the number of vehicles traveling on each route to recommend the best route to registered users. The effective implementation of cluster-based vehicle communication and location estimation models enhances the efficiency of the proposed system.

Association of Vehicle Count Data Obtained Via Image Processing Techniques Compared with Microsimulation Program Analysis Results

Association of Vehicle Count Data Obtained Via Image Processing Techniques Compared with Microsimulation Program Analysis Results

Machine Learning Approaches for Vehicle Counting on Bridges Based on Global Ground-Based Radar Data

Abstract. This study introduces a novel data-driven approach for classifying and estimating the number of vehicles crossing a bridge solely on non-invasive ground-based radar time series data (GBR data). GBR is used to measure the bridge displacement remotely. It has recently been investigated for remote bridge weigh-in-motion (BWIM). BWIM mainly focuses on single-vehicle events. However, events with several vehicles should be exploited to increase the amount of data. Therefore, extracting the number of involved vehicles in the first step would be beneficial. Acquiring such information from global bridge responses such as displacement can be challenging. This study indicates that a data-driven machine learning approach can extract the vehicle count from GBR time series data. When classifying events according to the number of vehicles, we achieve a balanced accuracy of up to 80 % on an imbalanced dataset. We also try to estimate the number of cars and trucks separately via regression and acquire a R2 of 0.8. Finally, we show the impact of the data augmentation methods we apply to the GBR data to tackle the skew in the dataset using the feature importance of Random Forests.

Traffic emissions before and after development based on traffic impact assessment

Abstract Traffic impact assessment evaluates the traffic conditions in the vicinity before and after the completion of a new development as new development will generate additional vehicle trips on the road and contribute to a rise in traffic emission. Thus, this study aims to evaluate the impact of the proposed development in Nibong Tebal, Penang, on the existing road network and identify the necessary improvements to ensure all intersections perform satisfactorily. Additionally, the impact of the proposed intersection’s design on fuel consumption and traffic emissions will also be investigated. During morning and evening rush hours, six hours manual vehicle counts were conducted at ten intersections. The collected data is then analyzed to determine the performance of the intersection. The level of service, based on the delay and ratio of volume over capacity of a turning movement, is used as the performance indicator for intersections. This study revealed that the reduction of delay time of more than 100 seconds at signalized intersections can significantly reduce fuel consumption and traffic emissions. In conclusion, a well-designed intersection will facilitate traffic movement and reduce traffic emissions which will eventually reduce the quantity of greenhouse gases released into the atmosphere that contribute to global climate change.

Implementation of Multi Extension in Blockchain-Based IoT Platform for Industrial IoT Devices

The rise of the Internet of Things (IoT) has led to the creation of technologies to improve human life. IoT involves integrating the Internet with the physical world, spanning applications like smart homes, industries, supply chains, academia, and more. By the end of 2020, around 212 billion IoT devices were globally deployed, presenting substantial opportunities for manufacturers and diverse applications. There have been numerous implementations of IoT across various fields, including Blockchain IoT (B-IoT), Artificial Intelligence of Things (AIoT), Digital Twin, and new communication protocols like the Matter protocol. We conducted a comprehensive testing of the blockchain (B-IoT) extension system on various bandwidths and scenarios, such as blockchain API execution time, speed, retention performance, and smart contract vulnerability testing. Our testing has been successful, and several messaging systems were used. Kafka was recommended to overcome the pending transaction problem caused by unprocessed messages. Our smart contract exhibited high severity. The Artificial Intelligence of Things extension, tested on real environments for person and vehicle counters, has shown successful results. Digital Twin, integrated into the IoT platform to perform and control 3D assets such as the postgraduate PENS building, has demonstrated efficient performance. Matter protocol achieved an average task execution speed of 0.48 tasks per second. Matter P2P communication was also successfully tested in this research by implementing the Access Control List (ACL) command.

Accident Detection and Nearby Patrol Alert System Using AI &ML

Abstract: Intelligent communities are utilizing different creative ideas to improve the quality of human life. Due to fast growing sizes of our cities, need of travelling is constantly increasing, which in turn has increased count of vehicles on the roads. Increasing number of vehicles on the roads has brought about numerous difficulties for Street Traffic Management Authorities. Amongst different traffic related issues, road accidents are something worth giving attention to and have to be on the priority list. This project describes various automatic road accident detection techniques, which automatically detect accidents using surveillance videos in real-time and intimates the event scenario to control room and the main uniqueness of the system is it automatically estimates the crash value of the incident and intimates to the user. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure.

A multiple directions turning vehicle counting method at intersections based on arbitrary-oriented detection and stack Long Short-Term Memory

The traffic flow parameters of turning vehicles at urban road intersections play an important role in the intelligent traffic system. Traffic road monitoring is difficult to cover large intersection scenes. With the application of unmanned aerial vehicles in traffic, drone-based intersection monitoring has great potential due to the large perspective. But there is rarely research on multiple turning vehicle counting at intersections based on drones. A few existing multiple turning vehicle counting methods are based on vehicle detection and tracking methods. However, the vehicles at the intersection have various orientations, the accurate information of the vehicle cannot be obtained by detection, and the tracking process is complicated and redundant for the counting task. Based on the traffic video at intersections taken by unmanned aerial vehicles, we propose a eight turnings vehicle counting model without complex tracking. Firstly, a spatial attention and channel adaptive attention model net is proposed for arbitrary-oriented vehicle detection to get the orientation and position of vehicles. Secondly, a turning spatio-temporal counting feature for different turning vehicles and its extraction method are proposed. Finally, the stack Long Short-Term Memory net based counting model is designed to process the turning spatio-temporal counting feature and counting eight different turnings vehicles at intersection. The experiments show that the proposed method can realize counting eight different turnings vehicles simultaneously in drone-based traffic video at the intersection without relying on complex multi-target tracking. The average counting accuracy has reached 98.18%.

Training Vehicle Detection and Classification Models with Less Data: An Active Learning Approach

The application of computer vision in transportation engineering has facilitated real-time traffic flow optimization, vehicle counting, anomaly detection, and ameliorated transportation safety. Most vision systems are, however, developed through a supervised learning process, which can be data hungry and costly because it requires manual annotation of objects from a variety of sources. The general rule of thumb for building accurate and transferrable vision models has been to increase the quality, diversity, and quantity of the annotated datasets used in model training. This paper presents a simple, yet efficient active learning framework that significantly reduces the number of annotations needed to build a state-of-the-art vehicle detection and classification model. To achieve this, we first leverage a vision transformer that generates embeddings rich with information needed to quantify the similarity and diversity between images in a two-dimensional embedding space. To select which images from the embedding space should be annotated, we propose a scoring and sampling strategy that minimizes class imbalance and model uncertainty through an iterative process. The latest iteration of the You Only Look Once (YOLO) model, YOLOv8, is used as the active learner. We compare the efficacy of our proposed active learning methods with models developed at much higher sampling rates using the mean average precision. The models developed were also integrated with tracking algorithms to evaluate differences in accuracy for vehicle counts and their practical implications for direction counts.

Vehicle counting in drone images: An adaptive method with spatial attention and multiscale receptive fields

Vehicle counting in drone images: An adaptive method with spatial attention and multiscale receptive fields

Counting dense object of multiple types based on feature enhancement.

Accurately counting the number of dense objects in an image, such as pedestrians or vehicles, is a challenging and practical task. The existing density map regression methods based on CNN are mainly used to count a class of dense objects in a single scene. However, in complex traffic scenes, objects such as vehicles and pedestrians usually exist at the same time, and multiple classes of dense objects need to be counted simultaneously. To solve the above issues, we propose a new multiple types of dense object counting method based on feature enhancement, which can enhance the features of dense counting objects in complex traffic scenes to realize the classification and regression counting of dense vehicles and people. The counting model consists of the regression subnet and the classification subnet. The regression subnet is primarily used to generate two-channel predicted density maps, mainly including the initial feature layer and the feature enhancement layer, in which the feature enhancement layer can enhance the classification features and regression counting features of dense objects in complex traffic scenes. The classification subnet mainly supervises classifying dense vehicles and people into two feature channels to assist the regression counting task of the regression subnets. Our method is compared on VisDrone+ datasets, ApolloScape+ datasets, and UAVDT+ datasets. The experimental results show that the method counts two kinds of dense objects simultaneously and outputs a high-quality two-channel predicted density map. The counting performance is better than the state-of-the-art counting network in dense people and vehicle counting. In future work, we will further improve the feature extraction ability of the model in complex traffic scenes to classify and count a variety of dense objects such as cars, pedestrians, and non-motor vehicles.

Traffic Flow Optimization at Toll Plaza Using Proactive Deep Learning Strategies

Global urbanization and increasing traffic volume have intensified traffic congestion throughout transportation infrastructure, particularly at toll plazas, highlighting the critical need to implement proactive transportation infrastructure solutions. Traditional toll plaza management approaches, often relying on manual interventions, suffer from inefficiencies that fail to adapt to dynamic traffic flow and are unable to produce preemptive control strategies, resulting in prolonged queues, extended travel times, and adverse environmental effects. This study proposes a proactive traffic control strategy using advanced technologies to combat toll plaza congestion and optimize traffic management. The approach involves deep learning convolutional neural network models (YOLOv7–Deep SORT) for vehicle counting and an extended short-term memory model for short-term arrival rate prediction. When projected arrival rates exceed a threshold, the strategy proactively activates variable speed limits (VSLs) and ramp metering (RM) strategies during peak hours. The novelty of this study lies in its predictive and adaptive capabilities, ensuring efficient traffic flow management. Validated through a case study at Ravi Toll Plaza Lahore using PTV VISSIMv7, the proposed method reduces queue length by 57% and vehicle delays by 47% while cutting fuel consumption and pollutant emissions by 28.4% and 34%, respectively. Additionally, by identifying the limitations of conventional approaches, this study presents a novel framework alongside the proposed strategy to bridge the gap between theory and practice, making it easier for toll plaza operators and transportation authorities to adopt and benefit from advanced traffic management techniques. Ultimately, this study underscores the importance of integrated and proactive traffic control strategies in enhancing traffic management, minimizing congestion, and fostering a more sustainable transportation system.

ESTUDO DE TRÁFEGO DE VEÍCULOS, INTERVENÇÕES DE SINALIZAÇÕES E URBANISMO TÁTICO NO ENTORNO DO HOSPITAL DA VIDA COMO POLO GERADOR DE VIAGENS

Trip Generating Developments (TGDs) have an influence on traffic in their location and are directly linked to the lack of control in the mobility of vehicles and pedestrians in the location, if their implementation is not properly planned. The objective of this work was to study traffic and conditions around Hospital da Vida (HV), located in the center Dourados-MS, as a Hospital PGV and propose safe mobility to the location. The study was developed with a bibliographical analysis of the topic, data relating to accidents and mobility in the region with local authorities, vehicle and pedestrian counts and on-site visits were also carried out. According to the data obtained, it was shown that HV has a high complexity/cost service, serving 33 municipalities in the region. According to data from counts carried out at the intersection of Toshinobu Katayama Street and Ciro Melo Street in Dourados-MS, a high flow of vehicles was noted, represented mainly by cars, as well as a high flow of pedestrians. In 500 meter radius studied had noticed the highest rate of accidents at the site in 2023, since 2020. Therefore, it was possible to note that the existing signs do not include safe mobility in the study site, with solutions being proposed using tactical urbanism and reinforcement of horizontal and vertical signs, with the aim of increasing safety and helping pedestrians stay and coexist.

Investigating heterogeneity in the price elasticity of traffic flow in Melbourne: Evidence from traffic volume data

AbstractThis paper leverages a rich dataset of 1.24 billion traffic flow observations across 36,666 vehicle detectors to estimate the price elasticity of traffic flow with respect to fuel prices in Melbourne, Australia. I find that a 1% increase in fuel prices leads to a 0.0556% decrease in traffic flow across Melbourne, where traffic flow is defined as the number of vehicles passing a vehicle counter per hour. I find significant regional heterogeneity across Melbourne, with evidence of positive own‐price elasticities in regions in the centre of the city, and in peak commute times on both weekdays and weekends, which I argue is evidence of a congestion‐speed effect. Moreover, regions near the CBD with high incomes tend to be less elastic than regions further away with reduced access to public transport. These findings can be used to determine the optimal tax or charge to internalise the externalities produced by motor vehicles.