Automatic Vehicle Classification Research Articles

VEHICLE DETECTION AND CLASSIFICATION USING FORWARD SCATTER RADAR (FSR) FOR TRAFFIC MANAGEMENT USING CONVOLUTIONAL NEURAL NETWORK

The importance of automatic vehicle detection and classification has grown significantly in recent years, as it has become a crucial component of traffic management and monitoring systems. To overcome the limitations of traditional video vehicle detection, this paper proposes the use of forward scatter radar (FSR) technology. The FSR system is tested for the classification of four different vehicle types, each with distinct sizes. To improve the classification accuracy of the FSR system, the paper utilizes a well-established neural network known as a convolutional neural network (CNN). Two time-frequency analyses, continuous wavelet transform (CWT) and short-time Fourier transform (STFT), are used to evaluate the classification performance of the FSR system. The study demonstrates that the CNN classifier significantly improves the classification accuracy of the FSR system in vehicle detection and classification. This finding is supported by the evaluation of the time-frequency analyses, CWT and STFT. Overall, the proposed approach has the potential to enhance traffic management and monitoring systems, thereby improving road safety and traffic efficiency.

VIDEO CAMERA TECHNOLOGY FOR VEHICLE COUNTING IN TRAFFIC CENSUS: ISSUES, STRATEGIES AND OPPORTUNITIES

This study provides an overview of the sensor technologies commonly used for automated vehicle classification and counting, with a focus on non-intrusive sensors. Video cameras are found to be the most feasible solution for data collection in traffic census as it can operate in portable mode and used at any location. Several factors must be considered to ensure accurate counting. These involve optimum placement of the camera to ensure that all vehicles can be observed, and the lighting conditions must be considered to ensure good video quality. These further contributes to accurate classification and counting of vehicles by dedicated deep learning algorithm. As the data collection may involve location with poor access to cloud computing and storage, offline processing is therefore recommended. The study also revealed opportunities for solving issues related to strategic placement of video cameras, and development of dedicated deep learning algorithms.

Patent review and novel design of vehicle classification system with TRIZ

The classification and counting of vehicles play a crucial role in transportation engineering. With the growth of technology, the automated vehicle classification system has improved over the last few decades. To avoid reinventing the wheel, a patent review is a must. In many engineering disciplines, the TRIZ method is used to guide further inventive improvement. This article studies the development trend of the vehicle classification system and the appropriateness of the TRIZ tool. Twenty-two relevant patents have been selected for the investigation. Through the proposed solutions documented in related patents, their contradicting parameters and inventive principles are identified. Inventive principles are also predicted from TRIZ contradiction matrices from both Altshuller and Mann and it is found that using Mann's contradiction matrix is more accurate. The development direction is reviewed with the TRIZ evolution trend and is presented visually as an evolution potential radar plot. Finally, a novel design of vehicle classification system is proposed.

Automatic Vehicle Identification and Classification Model Using the YOLOv3 Algorithm for a Toll Management System

Vehicle identification and classification are some of the major tasks in the areas of toll management and traffic management, where these smart transportation systems are implemented by integrating various information communication technologies and multiple types of hardware. The currently shifting era toward artificial intelligence has also motivated the implementation of vehicle identification and classification using AI-based techniques, such as machine learning, artificial neural network and deep learning. In this research, we used the deep learning YOLOv3 algorithm and trained it on a custom dataset of vehicles that included different vehicle classes as per the Indian Government’s recommendation to implement the automatic vehicle identification and classification for use in the toll management system deployed at toll plazas. For faster processing of the test videos, the frames were saved at a certain interval and then the saved frames were passed through the algorithm. Apart from toll plazas, we also tested the algorithm for vehicle identification and classification on highways and urban areas. Implementing automatic vehicle identification and classification using traditional techniques is a highly proprietary endeavor. Since YOLOv3 is an open-standard-based algorithm, it paves the way to developing sustainable solutions in the area of smart transportation.

DETEKSI RODA KENDARAAN DENGAN CIRCLE HOUGH TRANSFORM (CHT) DAN SUPPORT VECTOR MACHINE (SVM)

In the digital image processing, many methods have been developed, the purpose of developing these methods is how computers can detect and recognize objects in an image with a precisely and process them in a relatively short time. Wheels are components that are always present in every vehicle, whether the vehicle is a bus, car or truck, it must have wheels with the same shape. If a wheel can be detected and recognized then the vehicle recognition and classification can be determined. This research focuses on capturing circle images, detecting wheel circles by applying Circle Hough Transformation (CHT). This transformation is able to recognize the object based on its boundaries and is resistant to noise. After obtaining the image of the circle, the next step is to classify it into Wheels and Non Wheels using the Support Vector Machine (SVM) method. The development of the wheel circle detection model on the side view image of this vehicle can be used as one of the first steps in research on wheel-based automatic vehicle recognition and classification systems.

Robust Real-Time Traffic Surveillance with Deep Learning.

Real-time vehicle monitoring in highways, roads, and streets may provide useful data both for infrastructure planning and for traffic management in general. Even though it is a classic research area in computer vision, advances in neural networks for object detection and classification, especially in the last years, made this area even more appealing due to the effectiveness of these methods. This study presents TrafficSensor, a system that employs deep learning techniques for automatic vehicle tracking and classification on highways using a calibrated and fixed camera. A new traffic image dataset was created to train the models, which includes real traffic images in poor lightning or weather conditions and low-resolution images. The proposed system consists mainly of two modules, first one responsible of vehicle detection and classification and a second one for vehicle tracking. For the first module, several neural models were tested and objectively compared, and finally, the YOLOv3 and YOLOv4-based network trained on the new traffic dataset were selected. The second module combines a simple spatial association algorithm with a more sophisticated KLT (Kanade–Lucas–Tomasi) tracker to follow the vehicles on the road. Several experiments have been conducted on challenging traffic videos in order to validate the system with real data. Experimental results show that the proposed system is able to successfully detect, track, and classify vehicles traveling on a highway on real time.

Deep Ensemble Neural Network Approach for Federal Highway Administration Axle-Based Vehicle Classification Using Advanced Single Inductive Loops

The Federal Highway Administration (FHWA) vehicle classification scheme is designed to serve various transportation needs such as pavement design, emission estimation, and transportation planning. Many transportation agencies rely on Weigh-In-Motion and Automatic Vehicle Classification sites to collect these essential vehicle classification counts. However, the spatial coverage of these detection sites across the highway network is limited by high installation and maintenance costs. One cost-effective approach has been the use of single inductive loop sensors as an alternative to obtaining FHWA vehicle classification data. However, most data sets used to develop such models are skewed since many classes associated with larger truck configurations are less commonly observed in the roadway network. This makes it more difficult to accurately classify under-represented classes, even though many of these minority classes may have disproportionately adverse effects on pavement infrastructure and the environment. Therefore, previous models have been unable to adequately classify under-represented classes, and the overall performance of the models is often masked by excellent classification accuracy of majority classes, such as passenger vehicles and five-axle tractor-trailers. To resolve the challenge of imbalanced data sets in the FHWA vehicle classification, this paper constructed a bootstrap aggregating deep neural network model on a truck-focused data set using single inductive loop signatures. The proposed method significantly improved the model performance on several truck classes, especially minority classes such as Classes 7 and 11 which were overlooked in previous research. The model was tested on a distinct data set obtained from four spatially independent sites and achieved an accuracy of 0.87 and an average F1 score of 0.72.

VEHICLE CLASSIFICATION USING THE CONVOLUTION NEURAL NETWORK APPROACH

We present vehicle detection classification using the Convolution Neural Network (CNN) of the deep learning approach. The automatic vehicle classification for traffic surveillance video systems is challenging for the Intelligent Transportation System (ITS) to build a smart city. In this article, three different vehicles: bike, car and truck classification are considered for around 3,000 bikes, 6,000 cars, and 2,000 images of trucks. CNN can automatically absorb and extract different vehicle dataset’s different features without a manual selection of features. The accuracy of CNN is measured in terms of the confidence values of the detected object. The highest confidence value is about 0.99 in the case of the bike category vehicle classification. The automatic vehicle classification supports building an electronic toll collection system and identifying emergency vehicles in the traffic.

Moving Vehicle Detection and Classification Using Gaussian Mixture Model and Ensemble Deep Learning Technique

In recent decades, automatic vehicle classification plays a vital role in intelligent transportation systems and visual traffic surveillance systems. Especially in countries that imposed a lockdown (mobility restrictions help reduce the spread of COVID-19), it becomes important to curtail the movement of vehicles as much as possible. For an effective visual traffic surveillance system, it is essential to detect vehicles from the images and classify the vehicles into different types (e.g., bus, car, and pickup truck). Most of the existing research studies focused only on maximizing the percentage of predictions, which have poor real-time performance and consume more computing resources. To highlight the problems of classifying imbalanced data, a new technique is proposed in this research article for vehicle type classification. Initially, the data are collected from the Beijing Institute of Technology Vehicle Dataset and the MIOvision Traffic Camera Dataset. In addition, adaptive histogram equalization and the Gaussian mixture model are implemented for enhancing the quality of collected vehicle images and to detect vehicles from the denoised images. Then, the Steerable Pyramid Transform and the Weber Local Descriptor are employed to extract the feature vectors from the detected vehicles. Finally, the extracted features are given as the input to an ensemble deep learning technique for vehicle classification. In the simulation phase, the proposed ensemble deep learning technique obtained 99.13% and 99.28% of classification accuracy on the MIOvision Traffic Camera Dataset and the Beijing Institute of Technology Vehicle Dataset. The obtained results are effective compared to the standard existing benchmark techniques on both datasets.

Correction to: Sound measurement and automatic vehicle classification and counting applied to road traffic noise characterization

Correction to: Sound measurement and automatic vehicle classification and counting applied to road traffic noise characterization

Sound measurement and automatic vehicle classification and counting applied to road traffic noise characterization

Increase in population density in large cities has increased the environmental noise present in these environments, causing negative effects on human health. There are different sources of environmental noise; however, noise from road traffic is the most prevalent in cities. Therefore, it is necessary to have tools that allow noise characterization to establish strategies that permit obtaining levels that do not affect the quality of life of people. This research discusses the implementation of a system that allows the acquisition of data to characterize the noise generated by road traffic. First, the methodology for obtaining acoustic indicators with an electret measurement microphone is described, so that it adjusts to the data collection needs for road traffic noise analyses. Then, an approach for the classification and counting of automatic vehicular traffic through deep learning is presented. Results showed that there were differences of 0.2 dBA in terms of RMSE between a type 1 sound level meter and the measurement microphone used. With reference to vehicle classification and counting for four categories, the approximate error is between 3.3% and -15.5%.

The Channel as a Traffic Sensor: Vehicle Detection and Classification Based on Radio Fingerprinting

Ubiquitously deployed Internet of Things (IoT)- based automatic vehicle classification systems will catalyze data-driven traffic flow optimization in future smart cities and will transform the road infrastructure itself into a dynamically sensing Cyber-physical System (CPS). Although a wide range of different traffic sensing systems has been proposed, the existing solutions are not yet able to simultaneously satisfy the multitude of requirements, e.g., accuracy, robustness, cost-efficiency, and privacy preservation. In this paper, we present a novel approach, which exploits radio fingerprints - multidimensional attenuation patterns of wireless signals - for accurate and robust vehicle detection and classification. The proposed system can be deployed in a highly cost-efficient manner as it relies on off-the-shelf embedded devices which are installed into existing delineator posts. In a comprehensive field evaluation campaign, the performance of the radio fingerprinting-based approach is analyzed within an experimental live deployment on a German highway, where it is able to achieve a binary classification success ratio of more than 99% and an overall accuracy of 93.83% for a classification task with seven different classes.

Deep Binary Classification via Multi-Resolution Network and Stochastic Orthogonality for Subcompact Vehicle Recognition.

To encourage people to save energy, subcompact cars have several benefits of discount on parking or toll road charge. However, manual classification of the subcompact car is highly labor intensive. To solve this problem, automatic vehicle classification systems are good candidates. Since a general pattern-based classification technique can not successfully recognize the ambiguous features of a vehicle, we present a new multi-resolution convolutional neural network (CNN) and stochastic orthogonal learning method to train the network. We first extract the region of a bonnet in the vehicle image. Next, both extracted and input image are engaged to low and high resolution layers in the CNN model. The proposed network is then optimized based on stochastic orthogonality. We also built a novel subcompact vehicle dataset that will be open for a public use. Experimental results show that the proposed model outperforms state-of-the-art approaches in term of accuracy, which means that the proposed method can efficiently classify the ambiguous features between subcompact and non-subcompact vehicles.

RULE-BASED MAPPING OF PARKED VEHICLES USING AERIAL IMAGE SEQUENCES

Abstract. Mapping of parking spaces in cities is a prerequisite for future applications in parking space management like community-based parking. Although terrestrial or vehicle based sensors will be the favorite data source for parking space mapping, airborne monitoring can play a role in building up city wide basis maps which include also parking spaces on ancillary and suburban roads. We present a novel framework for automatic city wide classification of vehicles in moving, stopped and parked using aerial image sequences and information from a road database. The time span of observation of a specific vehicle during an image sequence is usually not long enough to decide unambiguously, whether a vehicle stopped e.g. before a traffic light or is parking along the road. Thus, the workflow includes a vehicle detection and tracking method as well as a rule-based fuzzy-logic workflow for the classification of vehicles. The workflow classifies stopped and parked vehicles by including the neighbourhood of each vehicle via a Delaunay-Graph. The presented method reaches correctness values of around 86.3%, which is demonstrated using three different aerial image sequences. The results depend on several factors like detection quality and road database accuracy.

Vehicle classification approach based on the combined texture and shape features with a compressive DL

Automatic vehicle classification is a fundamental task in intelligent transportation systems. Image-based vehicle classification is challenging due to occlusion, low-illumination, and scale change. This study proposes an innovative approach by combining texture and shape features into a complementary feature and using the complementary feature to train a compressive dictionary to improve accuracy and efficiency. In the feature combination, the scale-invariant feature transform descriptor is applied to extract the texture and shape features from the original vehicle images and their edge images, respectively. In the dictionary training, a compressive dictionary learning (DL) algorithm, called compressive K singular value decomposition (CKSVD) algorithm, is proposed to improve the dictionary training efficiency. The CKSVD algorithm divides the feature dictionary into several same-sized data blocks and then performs the DL in each data block based on a very sparse random projection matrix. On the feature combination and DL, the proposed approach employs the kernel sparse representation method to classify vehicles into four types: buses, trucks, vans, and sedans. The kernel sparse representation method enables the linearly inseparable classification in the combined feature space to be linearly separable. Experimental results show that the proposed approach can improve the accuracy and efficiency of vehicle classification.

BNNG Algorithm Modeling for Vehicle Classification Recognition under Non Line-of -sight Environment

At present, the automatic classification of vehicles on roads is mostly based on image recognition, and there are defects in adaptability under non-line-of-sight environments. In this paper, based on the similarity of the integration of the ecosystem model and multi-neural network model, an artificial neural network group (BNNG) algorithm was proposed. The vehicle’s driving acoustic signal was taken as the research object, and it was calculated using the Artificial Neural Network (BNNG) algorithm to achieve automatic classification and recognition of vehicle models. Through experimental tests, it is shown that under non-line-of-sight environments, the accuracy of vehicle classification can be improved, and the misrecognition rate of similar models can be greatly reduced. This provided a new method for the automatic classification and identification of vehicles on roads, which was of great significance to monitor vehicle safety in non-line-of-sight environments.

Micro-Doppler Mini-UAV Classification Using Empirical-Mode Decomposition Features

In this letter, we propose an empirical-mode decomposition (EMD)-based method for automatic multicategory mini-unmanned aerial vehicle (UAV) classification. The radar echo signal is first decomposed into a set of oscillating waveforms by EMD. Then, eight statistical and geometrical features are extracted from the oscillating waveforms to capture the phenomenon of blade flashes. After feature normalization and fusion, a nonlinear support vector machine is trained for target class-label prediction. Our empirical results on real measurement of radar signals show encouraging mini-UAV classification accuracy performance.

Automatic Moving Vehicle Detection and Classification Based on Artificial Neural Fuzzy Inference System

The main objective of this work is to automatically detect moving vehicles on the road. Adaptive Neuro-Fuzzy Inference System (ANFIS) classifier is adopted in this paper to classify moving vehicles on road. An input traffic video scenes are taken with vertical and horizontal positioned cameras. The proposed system contains six major steps such as preprocessing, vehicle detection, tracking, structural matching, feature extraction and classification. In this proposed method, preprocessing consists of color conversion and noise removal. Vehicle detection is performed by using background subtraction and Otsu thresholding algorithm. Kalman filter is used in the third step to track moving vehicles in successive frames. In the fourth step, Active Shape Modelling method is used to recover the 3D shape of the vehicle in order to find the boundaries of vehicle. In the fifth step, features of the detected vehicles are extracted by Harrish corner detector, log Gabor filter and these features are taken into account to classify the types of vehicle. Finally, ANFIS is proposed to classify the vehicles which is trained by updating the membership function. Experimentation results provides better accuracy rate and low mean error rate when compared with the state of art methods.

Deep Reinforcement Learning With Visual Attention for Vehicle Classification

Automatic vehicle classification is crucial to intelligent transportation system, especially for vehicle-tracking by police. Due to the complex lighting and image capture conditions, image-based vehicle classification in real-world environments is still a challenging task and the performance is far from being satisfactory. However, owing to the mechanism of visual attention, the human vision system shows remarkable capability compared with the computer vision system, especially in distinguishing nuances processing. Inspired by this mechanism, we propose a convolutional neural network (CNN) model of visual attention for image classification. A visual attention-based image processing module is used to highlight one part of an image and weaken the others, generating a focused image. Then the focused image is input into the CNN to be classified. According to the classification probability distribution, we compute the information entropy to guide a reinforcement learning agent to achieve a better policy for image classification to select the key parts of an image. Systematic experiments on a surveillance-nature dataset which contains images captured by surveillance cameras in the front view, demonstrate that the proposed model is more competitive than the large-scale CNN in vehicle classification tasks.

Automated Vehicle Detection and Classification

Automated Vehicle Classification (AVC) based on vision sensors has received active attention from researchers, due to heightened security concerns in Intelligent Transportation Systems. In this work, we propose a categorization of AVC studies based on the granularity of classification, namely Vehicle Type Recognition, Vehicle Make Recognition, and Vehicle Make and Model Recognition. For each category of AVC systems, we present a comprehensive review and comparison of features extraction, global representation, and classification techniques. We also present the accuracy and speed-related performance metrics and discuss how they can be used to compare and evaluate different AVC works. The various datasets proposed over the years for AVC are also compared in light of the real-world challenges they represent, and those they do not. The major challenges involved in each category of AVC systems are presented, highlighting open problems in this area of research. Finally, we conclude by providing future directions of research in this area, paving the way toward efficient large-scale AVC systems. This survey shall help researchers interested in the area to analyze works completed so far in each category of AVC, focusing on techniques proposed for each module, and to chalk out strategies to enhance state-of-the-art technology.