Vehicle Counting Research Articles

A machine learning pipeline for extracting decision-support features from traffic scenes1

Traffic systems play a key role in modern society. However, these systems are increasingly suffering from problems, such as congestions. A well-known way to efficiently reduce this kind of problem is to perform traffic light control intelligently through reinforcement learning (RL) algorithms. In this context, extracting relevant features from the traffic environment to support decision-making becomes a central concern. Examples of such features include vehicle counting on each queue, identification of vehicles’ origins and destinations, among others. Recently, the advent of deep learning has paved to way to efficient methods for extracting some of the aforementioned features. However, the problem of identifying vehicles and their origins and destinations within an intersection has not been fully addressed in the literature, even though such information has shown to play a role in RL-based traffic signal control. Building against this background, in this work we propose a deep learning pipeline for extracting relevant features from intersections based on traffic scenes. Our pipeline comprises three main steps: (i) a YOLO-based object detector fine-tuned using the UAVDT dataset, (ii) a tracking algorithm to keep track of vehicles along their trajectories, and (iii) an origin-destination identification algorithm. Using this pipeline, it is possible to identify vehicles as well as their origins and destinations within a given intersection. In order to assess our pipeline, we evaluated each of its modules separately as well as the pipeline as a whole. The object detector model obtained 98.2% recall and 79.5% precision, on average. The tracking algorithm obtained a MOTA of 72.6% and a MOTP of 74.4%. Finally, the complete pipeline obtained an average error rate of 3.065% in terms of origin and destination counts.

MSCNet: Dense vehicle counting method based on multi-scale dilated convolution channel-aware deep network

MSCNet: Dense vehicle counting method based on multi-scale dilated convolution channel-aware deep network

МЕТОДИКА ОЦЕНКИ ИНТЕНСИВНОСТИ ДВИЖЕНИЯ НА ОСНОВЕ ДАННЫХ ВИДЕОНАБЛЮДЕНИЯ

The paper presents an approach to intelligent transport systems based on advanced machine learning algorithms, the purpose of which is to estimate the traffic flow on the road network. Data is obtained from traffic cameras located in a limited number of places. The approach includes two main algorithms. The first is a probabilistic algorithm for counting vehicles from low-quality images, which belongs to the category of unsupervised learning

Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model.

Different techniques are being applied for automated vehicle counting from video footage, which is a significant subject of interest to many researchers. In this context, the You Only Look Once (YOLO) object detection model, which has been developed recently, has emerged as a promising tool. In terms of accuracy and flexible interval counting, the adequacy of existing research on employing the model for vehicle counting from video footage is unlikely sufficient. The present study endeavors to develop computer algorithms for automated traffic counting from pre-recorded videos using the YOLO model with flexible interval counting. The study involves the development of algorithms aimed at detecting, tracking, and counting vehicles from pre-recorded videos. The YOLO model was applied in TensorFlow API with the assistance of OpenCV. The developed algorithms implement the YOLO model for counting vehicles in two-way directions in an efficient way. The accuracy of the automated counting was evaluated compared to the manual counts, and was found to be about 90 percent. The accuracy comparison also shows that the error of automated counting consistently occurs due to undercounting from unsuitable videos. In addition, a benefit-cost (B/C) analysis shows that implementing the automated counting method returns 1.76 times the investment.

Turning traffic surveillance cameras into intelligent sensors for traffic density estimation

AbstractAccurate traffic density plays a pivotal role in the Intelligent Transportation Systems (ITS). The current practice to obtain the traffic density is through specialized sensors. However, those sensors are placed in limited locations due to the cost of installation and maintenance. In most metropolitan areas, traffic surveillance cameras are widespread in road networks, and they are the potential data sources for estimating traffic density in the whole city. Unfortunately, such an application is challenging since surveillance cameras are affected by the 4L characteristics: Low frame rate, Low resolution, Lack of annotated data, and Located in complex road environments. To the best of our knowledge, there is a lack of holistic frameworks for estimating traffic density from traffic surveillance camera data with 4 L characteristics. Therefore, we propose a framework for estimating traffic density using uncalibrated traffic surveillance cameras. The proposed framework consists of two major components: camera calibration and vehicle detection. The camera calibration method estimates the actual length between pixels in the images and videos, and the vehicle counts are extracted from the deep-learning-based vehicle detection method. Combining the two components, high-granular traffic density can be estimated. To validate the proposed framework, two case studies were conducted in Hong Kong and Sacramento. The results show that the Mean Absolute Error (MAE) for the estimated traffic density is 9.04 veh/km/lane in Hong Kong and 7.03 veh/km/lane in Sacramento. The research outcomes can provide accurate traffic density without installing additional sensors.

Big-Data Driven Framework to Estimate Vehicle Volume Based on Mobile Device Location Data

Vehicle volume serves as a critical metric and the fundamental basis for traffic signal control, transportation project prioritization, road maintenance planning, and more. Traditional methods of quantifying vehicle volume rely on manual counting, video cameras, and loop detectors at a limited number of locations. These efforts require significant labor and cost for expansions. Researchers and private sector companies have also explored alternative solutions, such as probe vehicle data, although this still suffers from a low penetration rate. In recent years, along with the technological advancement in mobile sensors and mobile networks, the quantity of mobile device location data (MDLD) has been growing dramatically in spatiotemporal coverage of the population and its mobility. This paper presents a big-data driven framework that can ingest terabytes of MDLD and estimate vehicle volume over a larger geographical area with a larger sample size. The proposed framework first employs a series of cloud-based computational algorithms to extract multimodal trajectories and trip rosters. A scalable map matching and routing algorithm is then applied to snap and route vehicle trajectories to the roadway network. The observed vehicle counts on each roadway segment are weighted and calibrated against ground truth control totals, that is, annual vehicle-miles traveled and annual average daily traffic. The proposed framework is implemented on the all-street network in the State of Maryland using MDLD for the entire year of 2019. The results demonstrate that our proposed framework produces reliable vehicle volume and also its transferability and generalization ability.

The effect of traffic at speed bumps in residential areas on noise and air pollution.

Although transportation systems are an increasing necessity in today's connected world, the over-reliance on internal combustion engine vehicles has caused an increase in air and noise pollution. Air and noise pollutions are among the negative environmental factors that contribute to disease occurrence due to their negative health consequences. Literature has showed that air and noise pollutions were responsible for thousands of premature deaths in Europe. This has pushed scientists to search for models to calculate the effect of traffic on air and noise pollution, to help predict future scenarios, and to work on ways to mitigate that increase in pollution. In this paper, a statistical model is done by using data measured for 25 speed bump locations in Kuwait, which included traffic flow data in the form of vehicle count and classification, as well as noise level measurements taken through an Amprobe SM20 sound meter, in addition to air pollutant data obtained from the Environment Public Authority (EPA) in Kuwait. The results of the multivariate linear regression model showed that high traffic counts resulted in significantly higher noise levels, reaching more than 70 decibels in certain locations, which is considered unhealthy for extended time periods. The model also showed that sulfur dioxide levels were impacted by both light and heavy vehicles, while particulate matter less than 10µm was affected mainly by heavy vehicles. An online survey on speed bumps was completed by 803 participants to understand the behavior of people at speed bumps in Kuwait and understand if age and gender might be a predictor of how people would behave, and this was done by doing Pearson's chi-squared correlation tests on the results obtained from the survey.

Automated Approach for Computer Vision-Based Vehicle Movement Classification at Traffic Intersections

Movement-specific vehicle classification and counting at traffic intersections is a crucial component of various traffic management activities. In this context, with recent advancements in computer-vision-based techniques, cameras have emerged as a reliable data source for extracting vehicular trajectories from traffic scenes. However, classifying these trajectories by movement type is quite challenging, as characteristics of motion trajectories obtained this way vary depending on camera calibrations. Although some existing methods have addressed such classification tasks with decent accuracies, the performance of these methods significantly relied on the manual specification of several regions of interest. In this study, we proposed an automated classification method for movement-specific classification (such as right-turn, left-turn and through movements) of vision-based vehicle trajectories. Our classification framework identifies different movement patterns observed in a traffic scene using an unsupervised hierarchical clustering technique. Thereafter, a similarity-based assignment strategy is adopted to assign incoming vehicle trajectories to identified movement groups. A new similarity measure was designed to overcome the inherent shortcomings of vision-based trajectories. Experimental results demonstrated the effectiveness of the proposed classification approach and its ability to adapt to different traffic scenarios without any manual intervention.

Automated Traffic Surveillance Using Existing Cameras on Transit Buses.

Millions of commuters face congestion as a part of their daily routines. Mitigating traffic congestion requires effective transportation planning, design, and management. Accurate traffic data are needed for informed decision making. As such, operating agencies deploy fixed-location and often temporary detectors on public roads to count passing vehicles. This traffic flow measurement is key to estimating demand throughout the network. However, fixed-location detectors are spatially sparse and do not cover the entirety of the road network, and temporary detectors are temporally sparse, providing often only a few days of measurements every few years. Against this backdrop, previous studies proposed that public transit bus fleets could be used as surveillance agents if additional sensors were installed, and the viability and accuracy of this methodology was established by manually processing video imagery recorded by cameras mounted on transit buses. In this paper, we propose to operationalize this traffic surveillance methodology for practical applications, leveraging the perception and localization sensors already deployed on these vehicles. We present an automatic, vision-based vehicle counting method applied to the video imagery recorded by cameras mounted on transit buses. First, a state-of-the-art 2D deep learning model detects objects frame by frame. Then, detected objects are tracked with the commonly used SORT method. The proposed counting logic converts tracking results to vehicle counts and real-world bird's-eye-view trajectories. Using multiple hours of real-world video imagery obtained from in-service transit buses, we demonstrate that the proposed system can detect and track vehicles, distinguish parked vehicles from traffic participants, and count vehicles bidirectionally. Through an exhaustive ablation study and analysis under various weather conditions, it is shown that the proposed method can achieve high-accuracy vehicle counts.

Applying Enhanced Real-Time Monitoring and Counting Method for Effective Traffic Management in Tashkent.

This study describes an applied and enhanced real-time vehicle-counting system that is an integral part of intelligent transportation systems. The primary objective of this study was to develop an accurate and reliable real-time system for vehicle counting to mitigate traffic congestion in a designated area. The proposed system can identify and track objects inside the region of interest and count detected vehicles. To enhance the accuracy of the system, we used the You Only Look Once version 5 (YOLOv5) model for vehicle identification owing to its high performance and short computing time. Vehicle tracking and the number of vehicles acquired used the DeepSort algorithm with the Kalman filter and Mahalanobis distance as the main components of the algorithm and the proposed simulated loop technique, respectively. Empirical results were obtained using video images taken from a closed-circuit television (CCTV) camera on Tashkent roads and show that the counting system can produce 98.1% accuracy in 0.2408 s.

Estimating the Measurement Uncertainty of the Number of Vehicles in a Car Park Using an Indirect Method

The main problem with counting vehicles in rest areas in Europe and America is the overflowing of parking lots in the rest areas. Thus it is impossible to count parked vehicles with traditional, direct methods, which use cameras and Lidar (light detection and ranging) to detect the presence of vehicles in individual parking spots. The solution to this problem may be an indirect method which uses cameras to count the vehicles entering and leaving the rest area and which sorts the vehicles into categories. This article introduces a method for determining car park occupancy in rest areas using indirect measurement and evaluates the uncertainty of this method for determining the occupancy. This indirect method counts the vehicles entering and leaving the car park and sorts the vehicles into categories. The difference between the number of vehicles that entered and the number of vehicles that left in a given time gives the number of vehicles occupying the car park, i.e., the parking space demand for a given time. This demand will vary over time. In order to register the vehicles entering and leaving, mains-free supply video cameras were installed next to the entrance and exit. The counting and categorizing could be conducted organoleptically, semi-automatically, or using an image computer analysis using artificial intelligence networks. Because the difference between the number of vehicles entering and leaving is calculated over a long period, a relative error (regarding car park capacity) might be grave even when the counting errors are minor. The authors will show how the certainty of this indirect counting method can be improved.

Implementasi Sistem Penghitung Kendaraan Otomatis Berbasis Computer Vision

The development of computer technology today is very helpful for humans in completing their work in various fields. One application of computer technology i.e., in the field of computer vision which has a very important role for object recognition. In this study, we designed a computer vision-based automatic vehicle counting system. The system that we created uses the MobileNetV2 Single Shot Multibox Detector (SSD) which is placed on the Raspberry Pi 4 to carry out the process of classifying cars and motorcycles and the raspberry pi 4 also functions as a system controller. This automatic vehicle counter system has been integrated between Raspberry Pi 4 and a mobile application on a smartphone where the smartphone functions to display information such as day, date, month, year and together with the number of cars and motorcycles. We tested this automatic vehicle counting system on steam services (car and motorcycle washing) for 3 days where 10 vehicles were collected every day. The test results show that the system is capable of detecting cars and motorcyles with an average accuracy rate of 46.6%.

Vehicle Detection and COUNTING System Using YOLOv7

Vehicle Detection and COUNTING System Using YOLOv7

A mini review on the catalytic technology development for the mitigation of various air pollutants

The contamination of the air is a significant threat to the environment, which includes both Animalia and plant kingdoms. According to the Central Pollution Control Board of India, the noteworthy contribution to pollution was due to the incidence of particulate matter, oxides of carbon, nitrogen, sulphur, and ozone. Sadly, a few of the world's most polluted cities are situated in India due to several factors, such as a high vehicle count and industrial emissions. In order to reduce these pollutants, various technologies, such as catalytic technology are employed to monitor and control harmful emissions. Catalysis causes no or few secondary pollutants emissions and a high potential for emission reduction. The properties of catalyst materials depend on factors such as synthesis methods and operating parameters. Various catalyst materials and their properties, mechanisms of different catalytic convertors, different kinds of emissions in vehicles, applications of catalysts, and alternatives for noble metals as catalysts are the factors considered in this review paper.

Vehicle Counting, Classification and Detection using OpenCV

Abstract: Vehicle Counting, Classification and Detection are turning out to be progressively significant in the field of Highway management. In any case, because of the various sizes of vehicles, their identification stays a test that straight forwardly influences the exactness of vehicle counts. To resolve this issue, we propose a vehicle Counting, Classification and Detection framework. In the proposed system we uses Yolov3 for vehicle detection and counting of vehicles from still images that can detect, classify and count numerous vehicles from CCTV footage.

A Hybrid Univariate Traffic Congestion Prediction Model for IoT-Enabled Smart City

IoT devices collect time-series traffic data, which is stochastic and complex in nature. Traffic flow prediction is a thorny task using this kind of data. A smart traffic congestion prediction system is a need of sustainable and economical smart cities. An intelligent traffic congestion prediction model using Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and Bidirectional Long Short-Term Memory (Bi-LSTM) is presented in this study. The novelty of this model is that the proposed model is hybridized using a Back Propagation Neural Network (BPNN). Instead of traditionally presuming the relationship of forecasted results of the SARIMA and Bi-LSTM model as a linear relationship, this model uses BPNN to discover the unknown function to establish a relation between the forecasted values. This model uses SARIMA to handle linear components and Bi-LSTM to handle non-linear components of the Big IoT time-series dataset. The “CityPulse EU FP7 project” is a freely available dataset used in this study. This hybrid univariate model is compared with the single ARIMA, single LSTM, and existing traffic prediction models using MAE, MSE, RMSE, and MAPE as evaluation indicators. This model provides the lowest values of MAE, MSE, RMSE, and MAPE as 0.499, 0.337, 0.58, and 0.03, respectively. The proposed model can help to predict the vehicle count on the road, which in turn, can enhance the quality of life for citizens living in smart cities.

Traffic Prediction for Intelligent Transportation System using Deep Learning

The most important challenge to sustainable mobility is persistent congestions of differing strength and duration in the dense transport networks. The standard Adaptive Traffic Signal Control cannot properly address this kind of congestion. Deep learning-based mechanisms have proved their significance to anticipate in adjective outcomes to improve the decision making on the predictions of traffic length. The deep learning models have long been used in many application domains which needed the identification and prioritization of adverse factors for a simplifying human life. Several methods are being popularly used to handle real time problems occurring from traffic congestion. This study demonstrates the capability of DL models to overcome the traffic congestion by simply allowing the vehicles through a signal depending on the length of vehicles. Our proposed method integrates a numeral of approach, intended to advance the cooperativeness of the explore operation. In this work, we implement the application to detect the number of vehicles in the images from the user and gives vehicles counts. To detect the vehicles count here we are using the YOLO pretrained weights.

Enhanced aerial vehicle system techniques for detection and tracking in fog, sandstorm, and snow conditions

Unmanned aerial vehicles are rapidly being utilized in surveillance and traffic monitoring because of their great mobility and capacity to cover regions at various elevations and positions. It is a challenging task to detect vehicles due to their various shapes, textures, and colors. One of the most difficult challenges is correctly detecting and counting aerial view vehicles in real time for traffic monitoring objectives using aerial images and videos. In this research, strategies are presented for improving the detection ability of self-driving vehicles in tough conditions, also for traffic monitoring, vehicle surveillance. We make classification, tracking trajectories, and movement calculation where fog, sandstorm (dust), and snow conditions are challenging. Initially, image enhancement methods are implemented to improve unclear images of roads. The improved images are then subjected to an object detection and classification algorithm to detect vehicles. Finally, new methods were evaluated (Corrected Optical flow/Corrected Kalman filter) to get the least error of trajectories. Also features like vehicle count, type, tracking trajectories by (Optical flow, Kalman Filter, Euclidean Distance) and relative movement calculation are extracted from the coordinates of the observed objects. These techniques aim to improve vehicle detection, tracking, and movement over aerial views of roads especially in bad weather. As a result, for aerial view vehicles in bad weather, our proposed method has an error of less than 5 pixels from the actual value and give the best results. This improves detection and tracking performance for aerial view vehicles in bad weather conditions.

Object detection analysis based on Machine Learning Algorithms

The branch of artificial intelligence known as computer vision focuses on developing and utilizing digital systems to process, examine, and interpret visual data. Computer vision aims to make it possible for computing equipment to accurately recognise an object's digital image and perform the necessary action.The field of transportation and artificial intelligence includes vehicle discovery, which is pivotal. Intelligent transport system (ITS) is a fashion used to produce an effective road transportation system. The Automated Driving System which has made significant advancements in recent times, heavily relies on vehicle identification in its armature. The fashion of detecting vehicles on the road is used for objects similar as vehicle shadowing, counts, and average speed of each vehicle, business analysis, and vehicle categorization and can be applied in a variety of settings. A wide, active, and grueling field of computer vision is real- time object discovery. This recognizes semantic objects of a particular class in digital prints and pictures. For face recognition, vehicle recognition, rambler counting, web image analysis, security systems, and tone- driving motorcars, object discovery is constantly employed. Key Words: Vehicle dataset, ITS, Vehicle detection, Highway management

Impacts of COVID-19's restriction measures on personal exposure to VOCs and aldehydes in Taipei City

The Coronavirus Disease 2019 (COVID-19) pandemic provided an unprecedented natural experiment, that allowed us to investigate the impacts of different restrictive measures on personal exposure to specific volatile organic compounds (VOCs) and aldehydes and resulting health risks in the city. Ambient concentrations of the criteria air pollutants were also evaluated. Passive sampling for VOCs and aldehydes was conducted for graduate students and ambient air in Taipei, Taiwan, during the Level 3 warning (strict control measures) and Level 2 alert (loosened control measures) of the COVID-19 pandemic in 2021–2022. Information on the daily activities of participants and on-road vehicle counts nearby the stationary sampling site during the sampling campaigns were recorded. Generalized estimating equations (GEE) with adjusted meteorological and seasonal variables were used to estimate the effects of control measures on average personal exposures to the selected air pollutants. Our results showed that ambient CO and NO2 concentrations in relation to on-road transportation emissions were significantly reduced, which led to an increase in ambient O3 concentrations. Exposure to specific VOCs (benzene, methyl tert-butyl ether (MTBE), xylene, ethylbenzene, and 1,3-butadiene) associated with automobile emissions were remarkably decreased by ~40–80 % during the Level 3 warning, resulting in 42 % and 50 % reductions of total incremental lifetime cancer risk (ILCR) and hazard index (HI), respectively, compared with the Level 2 alert. In contrast, the exposure concentration and calculated health risks in the selected population for formaldehyde increased by ~25 % on average during the Level 3 warning. Our study improves knowledge of the influence of a series of anti-COVID-19 measures on personal exposure to specific VOCs and aldehydes and its mitigations.