Vehicle Counting System Research Articles

Analysis of the vehicle's flow based on the neural network and the SIFT method

The article presents a vehicle counting system based on TensorFlow neural network models and the SIFT machine vision method. An experimental comparison was made of five detectors consisting of metaarchitecture (Faster R-CNN, SSD) and neural networks extracting features (Resnet V1 100, Inception V2, Inception Resnet V2 and Mobilenet V1). The main aspects of these detectors are analyzed, such as accuracy, speed, memory consumption, the number of floating point operations per second and the number of trainable parameters of convolutional neural networks. The calculation of vehicles is carried out by an algorithm based on the SIFT method. This algorithm compares the descriptors of all vehicles in the frame at the current time with the descriptors at the previous time. Based on the maximum match of the descriptors, the algorithm assigns the vehicle identification number from the previous frame, and in the absence of matches creates a new identification number. This approach will make it possible to calculate vehicles more accurately and assess their trajectory and speed.

Vehicle Counting And Traffic Congestion Detection Using YOLOv3

The purpose of this project is to utilize Python modules and a sophisticated deep learning algorithm to identify, categorize, track, and tally moving vehicles from highway CCTV footage. Additionally, the system predicts traffic congestion by analyzing the number of vehicles in consecutive video frames. When congestion is detected, the application automatically notifies the traffic police who receive a message on their mobile, prompting them to address the existing traffic jam in the area. The project's core involves a vision-based vehicle detection and counting system that relies on the YOLOv3 model and openCv-python library to achieve its objectives.

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

Towards the next generation intelligent transportation system: A vehicle detection and counting framework for undisciplined traffic conditions

Modern development in deep learning and computer vision techniques, intelligent transportation system (ITS) has emerged as a useful tool for building a traffic infrastructure in smart cities. Previously, several computer vision techniques have been proposed for vehicle recognition, which were limited in handling undisciplined, dense and laneless traffic conditions. Moreover, these frameworks did not incorporate many of the local vehicle configurations common in South Asian countries such as Pakistan, Bangladesh, and India. Considering the limitations of previous frameworks, this paper presents efficient vehicle detection and counting model for undisciplined conditions including dense and laneless traffic, occulusion cases and diverse range of local vehicles. A dataset of more than 2400 images of vehicles has been collected comprising of six new categories of local vehicles, and considering undisciplined traffic conditions to ensure robustness in vehicle detection and counting system. Transfer learning based technique has been used, using faster R-CNN model with Inception V2 as underlying architecture. The experimental results show a precision of 86.14% in terms of mAP. The work finds its application in South Asian contexts as more smart cities are formed in this region. The proposed framework will enable traffic monitoring with higher reliability, accuracy and granularity, contributing in having next-generation ITS.

Video-Based Vehicle Counting and Analysis using YOLOv5 and DeepSORT with Deployment on Jetson Nano

In recent years, the advancements in deep learning and high-performance edge-computing systems have increased tremendously and have become the center of attention when it comes to the analysis of video-based systems on edge by making use of computer vision techniques. Intelligent Transportation Systems (ITS) is one area where deep learning can be used for several tasks including highway-based vehicle counting systems whereby making use of computer vision techniques, an edge computing device and cameras installed in specific locations on the road, we are able to obtain very accurate vehicle counting results and replace the use of traditional and laborious hardware devices with modern low-cost solutions. This paper proposes and implements a modern, compact, and reliable vehicle counting system based on the most recent and popular object detection algorithm as of writing this paper, known as the YOLOv5, combined with a state-of-the-art object tracking algorithm known as DeepSORT. The YOLOv5 will be used in the following system to detect and classify four different classes of vehicles, whereas DeepSORT will be used to track those vehicles across different frames in the video sequence. Finally, a unique and efficient vehicle counting method will be implemented and used to count tracked vehicles across the highway scenes. A new highway vehicle dataset consisting of four vehicle classes, namely: car, motorcycle, bus, and truck, was collected, cleaned, and annotated with a total of 11,982 images published in the following study and used for the training of our robust vehicle detection model. From the results obtained over real-world highway surveillance videos, the following system was able to obtain an average vehicle detection mAP score of 96.1% and a vehicle counting accuracy of 95.39%, all while being able to be deployed on a compact Nvidia Jetson Nano edge-computing device with an average speed of 15 FPS which outperforms other previously proposed tools in terms of both accuracy and speed.

Smart Parking Solution for Multi Building Campus

Abstract: Locating parking space is becoming a serious problem as more and more employees prefer to switch to personal commute due to prevailing pandemic situation across globe in office campus. Particularly, where there is multiple building inside main campus, and it is quite challenging to keep track of car parking inside a given building. Without parking availability information, commuter must shuttle around builds to find parking space during peak hours, and this will be a loss of time as well as frustration to the commuter. There are few options companies follow like physically counting cars at certain interval and update the dashboard, install badge reader at entry and exit and people must punch card at both the places, sensors have been installed in certain parking lots, allowing management to track when cars enter and exit, install Radio Frequency Identification (RFID) and reader at entry and exit in order to track the capacity. All these methods will bring in burden on additional resource and high cost of installation of reader & necessary barricade systems respectively. Also, will add to regular maintenance of overall system. This project details DL implementation to create a vehicle counting system by using video from camera installed at the entry and exit path for vehicle. Pretrained model of YOLOv4 is used for object detection, vehicle tracking with Euclidean distance and counting. Since vehicle movement is considerably slow in pathway, performance of the model tested is 96.8% to 100% for varied frame rate of the video in parking capacity tracking

Development of a low-cost traffic counter for assessing likelihood of impact for tree risk assessment

ABSTRACT Most tree risk assessment methods task the assessor with the evaluation of a tree’s likelihood of impact (i.e. likelihood a target is present during failure) when determining the probability that an adverse event will occur. While this is generally accomplished qualitatively based on visual cues; during the 15 to 20 minutes an assessor is at a location, site occupancy, a key component of likelihood of impact, is most accurately measured using traffic counters. The use of traffic counters reduces risk assessment bias and increases reproducibility, though commercially-available devices may be cost-prohibitive. This work addresses one potential barrier to traffic counter adoption through the creation of a low-cost vehicle and pedestrian counting system. The study compares the accuracy and consistency of our homemade traffic counting system to estimates derived from a commercially available system, as well as vehicle and pedestrian counts tallied with a hand clicker. Vehicle and pedestrian counts from the commercially available systems (p = 0.004 and p < 0.001, respectively) correlated well (r = 0.846 and r = 0.896, respectively) with the hand-tallied counts, but the homemade counters were not correlated with either. However, pedestrian counts from the homemade counter became inaccurate as afternoon temperatures went above 31.7°C.

Object Detection and Tracking Algorithms for Vehicle Counting: A Comparative Analysis

The rapid advancement in the field of deep learning and high performance computing has highly augmented the scope of video-based vehicle counting system. In this paper, the authors deploy several state-of-the-art object detection and tracking algorithms to detect and track different classes of vehicles in their regions of interest (ROI). The goal of correctly detecting and tracking vehicles’ in their ROI is to obtain an accurate vehicle count. Multiple combinations of object detection models coupled with different tracking systems are applied to access the best vehicle counting framework. The models’ addresses challenges associated to different weather conditions, occlusion and low-light settings and efficiently extracts vehicle information and trajectories through its computationally rich training and feedback cycles. The automatic vehicle counts resulting from all the model combinations are validated and compared against the manually counted ground truths of over 9 h’ traffic video data obtained from the Louisiana Department of Transportation and Development. Experimental results demonstrate that the combination of CenterNet and Deep SORT, and YOLOv4 and Deep SORT produced the best overall counting percentage for all vehicles.

A Simple Vehicle Counting System Using Deep Learning with YOLOv3 Model

Deep Learning is a popular Machine Learning algorithm that is widely used in many areas in current daily life. Its robust performance and ready-to-use frameworks and architectures enables many people to develop various Deep Learning-based software or systems to support human tasks and activities. Traffic monitoring is one area that utilizes Deep Learning for several purposes. By using cameras installed in some spots on the roads, many tasks such as vehicle counting, vehicle identification, traffic violation monitoring, vehicle speed monitoring, etc. can be realized. In this paper, we discuss a Deep Learning implementation to create a vehicle counting system without having to track the vehicles movements. To enhance the system performance and to reduce time in deploying Deep Learning architecture, hence pretrained model of YOLOv3 is used in this research due to its good performance and moderate computational time in object detection. This research aims to create a simple vehicle counting system to help human in classify and counting the vehicles that cross the street. The counting is based on four types of vehicle, i.e. car, motorcycle, bus, and truck, while previous research counts the car only. As the result, our proposed system capable to count the vehicles crossing the road based on video captured by camera with the highest accuracy of 97.72%.

Vision-based vehicle detection and counting system using deep learning in highway scenes

Intelligent vehicle detection and counting are becoming increasingly important in the field of highway management. However, due to the different sizes of vehicles, their detection remains a challenge that directly affects the accuracy of vehicle counts. To address this issue, this paper proposes a vision-based vehicle detection and counting system. A new high definition highway vehicle dataset with a total of 57,290 annotated instances in 11,129 images is published in this study. Compared with the existing public datasets, the proposed dataset contains annotated tiny objects in the image, which provides the complete data foundation for vehicle detection based on deep learning. In the proposed vehicle detection and counting system, the highway road surface in the image is first extracted and divided into a remote area and a proximal area by a newly proposed segmentation method; the method is crucial for improving vehicle detection. Then, the above two areas are placed into the YOLOv3 network to detect the type and location of the vehicle. Finally, the vehicle trajectories are obtained by the ORB algorithm, which can be used to judge the driving direction of the vehicle and obtain the number of different vehicles. Several highway surveillance videos based on different scenes are used to verify the proposed methods. The experimental results verify that using the proposed segmentation method can provide higher detection accuracy, especially for the detection of small vehicle objects. Moreover, the novel strategy described in this article performs notably well in judging driving direction and counting vehicles. This paper has general practical significance for the management and control of highway scenes.

Contour Based Tracking for Driveway Entrance Counting System

Managing vehicle in free-flow entrance is tiring to do manually by a guard control especially due to the increase in transportation demand. Providing an accurate vehicle counting approach is vital for traffic management and it will surely be an essential part in tomorrow's smart cities. Therefore, the main objective of this paper is to propose a more accurate vehicle counter by using the tracking and heuristic rules approaches. EzCam v1.0 is a vehicle surveillance system for a free-flow entrance where a module of vehicle counting based on proposed idea has been applied. The proposed method does not require high computational resources more than any relatively affordable non task specific hardware. It employs single threshold, contour extraction and sequential frame analysis and finally, vehicle counting process subsequently. The tracking-based method employs foreground object detection method and a mechanism for object filtering approach as compared to Chris Dahms approach which does not consider any object rejection and accept all contour information as relevant to be counted as vehicles. As a result, EzCam v1.0 which utilizes the exploited contour-based approach is able to achieve up to 94 percent of accuracy rate and outperforms the classic Chris Dahms method which obtained an accuracy of 88 percent. Therefore, the Exploited Contour based tracking method helps vehicle counting system to perform better accuracy in comparison to Chris Dahms approach.

Fast single shot multibox detector and its application on vehicle counting system

Real-time vehicle detection and counting of multiple types is a difficult problem. To solve this problem, this study presents an efficient method based on single shot detection (SSD) to construct a vehicle detection and counting system. The proposed method named Fast-SSD first combines the Slim ResNet-34 with Single Shot MultiBox Detector. Then the authors limit the location prediction at each cell in the feature map and modify the detection network. When the input size of the picture is 300 × 300, Fast-SSD achieves the accuracy of 76.7 mAP on the PASCAL visual object classes 2007 test set. The network can be implemented at the speed of 20.8 FPS based on the GTX650Ti. Furthermore, they obtain the centre point of each type of vehicle which is detected by the Fast-SSD model in the image and set the virtual loop detectors to specify the detection range. The number of vehicles is calculated when the centre of the vehicle passes the virtual loop detector. Results show that the vehicle detection accuracy achieves 99.3% and the classification accuracy is 98.9%.

Vehicle Detection and Counting in High-Resolution Aerial Images Using Convolutional Regression Neural Network

Vehicle detection and counting in aerial images have become an interesting research focus since the last decade. It is important for a wide range of applications, such as urban planning and traffic management. However, this task is a challenging one due to the small size of the vehicles, their different types and orientations, and similarity in their visual appearance, and some other objects, such as air conditioning units on buildings, trash bins, and road marks. Many methods have been introduced in the literature for solving this problem. These methods are either based on shallow learning or deep learning approaches. However, these methods suffer from relatively low precision and recall rate. This paper introduces an automated vehicle detection and counting system in aerial images. The proposed system utilizes convolution neural network to regress a vehicle spatial density map across the aerial image. It has been evaluated on two publicly available data sets, namely, Munich and Overhead Imagery Research Data Set. The experimental results show that our proposed system is efficient and effective, and produces higher precision and recall rate than the comparative methods.

Real‐time vehicle detection and counting in complex traffic scenes using background subtraction model with low‐rank decomposition

Real-time vehicle counting can efficiently improve traffic control and management. Aiming to efficiently collect the real-time traffic information, the authors propose an effective vehicle counting system for detecting and tracking vehicles in complex traffic scenes. The proposed algorithm detects moving vehicles based on background subtraction method with ‘low-rank + sparse’ decomposition. For accurately counting vehicles, an online Kalman filter algorithm is used to track the multiple moving objects and avoid counting one vehicle repeatedly. The proposed method is evaluated on three publicly available datasets, which include seven video sequences with various challenging scenes for detection performance evaluation, and another two video sequences for vehicle counting evaluation. The experimental results demonstrate a good performance of the proposed method in terms of both qualitative and quantitative evaluations.

Kendali Lampu Lalu Lintas dengan Deteksi Kendaraan Menggunakan Metode Blob Detection

Traffic jam is a major traffic problem often found in big cities of Indonesia. It is because the number of vehicles increases annually. Therefore, a simulation to detect the number of vehicles in every lane of traffic is needed to monitor the traffic. Traffic control is also required in order to reduce traffic jam. This paper develops a vehicle detection and counting system using image processing. Detection is carried out using image segmentation which is processed by object filtering and blob extraction. Morphological operators are employed for blob extraction. Testing is conducted using a video obtained from the ATCS Bandung. The video is taken at the Laswi - A. Yani intersection Bandung. Software prototypes are created in C++, using Windows Forms Application as a programming library for Windows and Open CV for image processing module. The result shows that blob detection method can give good results if there is no intersection between blobs of each car. The performance is poor when this method is used for heavy traffic conditions, where the cars are close to each other. The performance level of sensitivity is 91.67%, precision is 61.11%, specificity is 80.55%, f-Measure is 73.33%, and accuracy is 83.33%. The accuracy for vehicles detection on sunny condition is 82.11% and reduced by 76.50% on rainy condition. This method works better in quiet condition, with accuracy of 83.07%, and is reduced by 67.70% in crowded condition. The average processing time is 0.042 seconds when using video, and 0.033 seconds using real camera.

“Mass Centre” Vectorization Algorithm for Vehicle’s Counting Portable Video System

Abstract Vehicle counting is one of the most basic challenges during the development and establishment of Intelligent Transport Systems (ITS). The main reason for vehicle counting is the necessity of monitoring and maintaining the transport infrastructure, preventing different kind of faults such as traffic jams. The main applied solution to this problem is video surveillance, which is presented by different kind of systems. Some of these systems use a network of static traffic cameras, expensive for establish and maintain, or mobile units, fast for redeployment, but fewer in diversity. In this paper, one particular concept of a low-cost mobile vehicle counting system is investigated, which uses an object detection method based on calculating “mass centre” of detected features of possible object. A hypothesis of improvement of the basic algorithm was formulated and a modification was proposed. In order to prove the hypothesis, both basic and modified algorithms were tested and evaluated.

Automatic vehicle counting system for traffic monitoring

The article is dedicated to the presentation of a vision-based system for road vehicles counting and classification. The system is able to achieve counting with a very good accuracy even in difficult scenarios linked to occlusions and/or presence of shadows. The principle of the system is to use already installed cameras in road networks without any additional calibration procedure. We propose a robust segmentation algorithm that detects foreground pixels corresponding to moving vehicles. First, the approach models each pixel of the background with an adaptive Gaussian distribution. This model is coupled with a motion detection procedure which allows to correctly locate in space and time moving vehicles. The nature of trials carried out, including peak periods and various vehicle types, leads to an increase of occlusions between cars and between cars and trucks. A specific method for severe occlusion detection, based on the notion of solidity, has been carried out, and tested. Furthermore, the method developed in this work is capable of managing the shadows with high resolution. The related algorithm has been tested and compared to a classical method. Experimental results based on four large data-sets show that our method can count and classify vehicles in real-time with a high level of performance (more than 98%) under different environmental situations, thus performing better than the conventional inductive loop detectors.

Traffic volume estimation in a cable-stayed bridge using dynamic responses acquired in the structural health monitoring

This paper presents the traffic volume estimation by constructing a statistical model using dynamic response data acquired by a structural health monitoring system installed on an in-service cable-stayed bridge. The structural health monitoring system consists of various sensors, including accelerometers, tilt sensors, temperature sensors, and the vehicle counting system. In this paper, the correlations between the response features from dynamic data, peak frequencies and amplitudes of responses, and the temperature and the traffic volume were firstly investigated. The results revealed that the traffic volume was a dominant factor that influenced on variances of the extracted features, while the temperature showed low effects on them in the target bridge. Some of the response features that showed high correlations were then selected for constructing a linear regression model to estimate the total traffic volume per 5 min. The constructed model then showed the accurate fitting performance to the data, and it was also capable of predicting the traffic volume on the bridge. Copyright © 2016 John Wiley & Sons, Ltd.

EasiSee: Real-Time Vehicle Classification and Counting via Low-Cost Collaborative Sensing

In the field of traffic-information acquisition, one pervasive solution is to use wireless sensor networks (WSNs) to realize vehicle classification and counting. By adopting heterogeneous sensors in a WSN, we can explore the potential of using complementary physical information to perform more complicated sensing computation. However, the collaboration among heterogeneous sensors, such as the collaborative sensing mechanism (CSM), is not well studied in current state-of-the-art research. In this paper, we design and implement EasiSee, a real-time vehicle classification and counting system based on WSNs. Our contributions are as follows. First, we propose a CSM, which coordinates the power-hungry camera sensor and the power-efficient magnetic sensors, reducing the overall system energy consumption and maximizing system lifetime. Second, we propose a robust vehicle image-processing algorithm, i.e., a low-cost image processing algorithm (LIPA). LIPA reduces environment noise and interference with low computation complexity. In the verification section, the vehicle detection accuracy turned out to be 95.31%, which pave the way for CSM. The time of image processing is around 200 ms, which indicates that our LIPA is computationally economical. With the overall energy consumption reduced, EasiSee achieves classification accuracy of 93%. Based on these experiments and analysis, we conclude that EasiSee is a practical and low-cost affordable solution for traffic-information acquisition.