CLASSIFICATION OF VEHICLE TYPES USING BACKPROPAGATION NEURAL NETWORKS WITH METRIC AND ECENTRICITY PARAMETERS

One of the efforts to break down traffic jams is to establish special lanes that can be passed by two, four or more wheeled vehicles. By being able to recognize the type of vehicle can reduce congestion. Citran based vehicle classification helps in providing information about the vehicle type. This study aims to classify the type of vehicle using a backpropagation neural network algorithm. The vehicle image can be recognized based on its shape, then the backpropagation neural network algorithm will be supported by metric and eccentricity parameters to perform feature extraction. Then from the results of feature extraction with metric parameters and eccentricity, the object will be classified using a backpropagation neural network algorithm. The test results show an accuracy of 87.5%. This shows the algorithm can perform classification well.

Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network

Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and classification of Bangladeshi native vehicle types. An extensive dataset of Bangladeshi native vehicles, encompassing 10,440 images, was developed. Here, the images are categorized into 13 common vehicle classes in Bangladesh. The method utilized was a residual network (ResNet-50)-based model, with extra classification blocks added to improve performance. Here, vehicle type features were automatically extracted and categorized. While conducting the analysis, a variety of metrics was used for the evaluation, including accuracy, precision, recall, and F1 − Score. In spite of the changing physical properties of the vehicles, the proposed model achieved progressive accuracy. Our proposed method surpasses the existing baseline method as well as two pre-trained DL approaches, AlexNet and VGG-16. Based on result comparisons, we have seen that, in the classification of Bangladeshi native vehicle types, our suggested ResNet-50 pre-trained model achieves an accuracy of 98.00%.

Traffic Study and Analysis of Highway (NH5) from Balongi to Kharar

Evaluation of in service pavements is very vital for keeping them in good serviceable condition because pavements deteriorate with age and traffic loading. To get a complete idea of the existing condition of any pavement both structural and functional evaluation are necessary. This study aims to investigate the accidental spots, traffic volume, and pavement condition. For this survey, the location of Kharar was chosen i.e. Balongi to Kharar Bus-Stand of 7 km stretch. The road initiates with intersection near Kharar bus stand and passes through many in between intersections near Sunny Enclave, VR Punjab Mall which are prime locations in that area. This road also connects with T junction and connects to NH5 / NH7 via Airport road. The data collected was processed, categorized and analyzed to generate reports for vehicle classification, hourly traffic variation, accidental black spots, pavement condition and origin & destination of trips.

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.