Vehicle Type Classification using Hybrid Features and a Deep Neural Network

Currently, considerable research has been done in vehicle type classification, especially due to the success of deep learning in many image classification problems. In this research, a system incorporating hybrid features is proposed to improve the performance of vehicle type classification. The feature vectors are extracted from the pre-processed images using Gabor features, a histogram of oriented gradients and a local optimal oriented pattern. The hybrid set of features contains complementary information that could help discriminate between the classes better, further, an ant colony optimizer is utilized to reduce the dimension of the extracted feature vectors. Finally, a deep neural network is used to classify the types of vehicles in the images. The proposed approach was tested on the MIO vision traffic camera dataset and another more challenging real-world dataset consisting of videos of multiple lanes of a toll plaza. The proposed model showed an improvement in accuracy ranging from 0.28% to 8.68% in the MIO TCD dataset when compared to well-known neural network architectures.

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%.

Development of AI-Based Vehicle Detection and Tracking System for C-ITS Application

There are various means of monitoring traffic situations on roads. Due to the rise of artificial intelligence (AI) based image processing technology, there is a growing interest in developing traffic monitoring systems using camera vision data. This study provides a method for deriving traffic information using a camera installed at an intersection to improve the monitoring system for roads. The method uses a deep-learning-based approach (YOLOv4) for image processing for vehicle detection and vehicle type classification. Lane-by-lane vehicle trajectories are estimated by matching the detected vehicle locations with the high-definition map (HD map). Based on the estimated vehicle trajectories, the traffic volumes of each lane-by-lane traveling direction and queue lengths of each lane are estimated. The performance of the proposed method was tested with thousands of samples according to five different evaluation criteria: vehicle detection rate, vehicle type classification, trajectory prediction, traffic volume estimation, and queue length estimation. The results show a 99% vehicle detection performance with less than 20% errors in classifying vehicle types and estimating the lane-by-lane travel volume, which is reasonable. Hence, the method proposed in this study shows the feasibility of collecting detailed traffic information using a camera installed at an intersection. The approach of combining AI and HD map techniques is the main contribution of this study, which shows a high chance of improving current traffic monitoring systems.

Multi-object Recognition Method Based on Improved YOLOv2 Model

A method of vehicle multi-object identification and classification based on the YOLOv2 algorithm is proposed to solve the problems of low detection rate, poor robustness, and unsatisfactory classification effect for the classical multi-object detection and vehicle type classification on real road environment. Based on the YOLOv2 algorithm, the network structure of YOLOv2-voc is improved according to the actual road conditions. The classification training model was obtained based on the ImageNet data and fine-tuning technology, according to the analysis of training results and vehicle object characteristics. This paper proposed the improved vehicle identification classification network structure, namely called YOLOv2-voc_mul. In order to verify the validity of the detection method, experiments are performed using samples from simple backgrounds and complex backgrounds and compared with the existing YOLOv2, YOLOv2-voc, and YOLOv3 models after 70000 iterations, respectively. The results show that the proposed YOLOv2-voc_mul model has an accuracy of 98.6% under the simple background, and the mAP (mean Average Precision) of different models reaches 87.81%. Under the complex background, the improved YOLOv2-voc_mul model has an average accuracy of 92.09% and 89.64% for single and multi-object detection of four different models. In summary, our proposed method has better accuracy, a low false detection rate, and good robustness.

Vibration Detection of Vehicle Impact Using Smartphone Accelerometer Data and Long-Short Term Memory Neural Network

Vehicle's analysis can be useful for a variety of traffic problems, such as monitoring road damages and vehicle type classification. Further, traffic behavior analysis can be useful to monitor traffic jams as a smart cities solution. In this paper, the vibration caused by a vehicle passing through a speed bump was recorded with a docked smartphone. The acquired signals were processed in order to detect the generated impact. In order to analyze this data a LSTM neural network was used due to its classification process over time while the smartphone accelerometer was continuously operating (waiting for a vehicle pass by). This deep learning technique allows the use of raw 3-axis accelerometer data. The results achieved 98% of accuracy with a low level of false positives (less than 1%). Indicating that the methodology is effective in classification of vehicles by their impact vibration.