The advantages of UAV video in flexibility, traceability, easy-operation, and abundant information make it a popular and powerful aerial tool applied in traffic monitoring in recent years. This paper proposed a systematic approach to detect and track vehicles based on the YOLO v3 model and the deep SORT algorithm for further extracting key traffic parameters. A field experiment was implemented to provide data for model training and validation to ensure the accuracy of the proposed approach. In the experiment, 5400 frame images and 1192 speed points were collected from two test vehicles equipped with high-precision GNSS-RTK and onboard OBD after completion of seven experimental groups with a different height (150 m to 500 m) and operating speed (40 km/h to 90 km/h). The results indicate that the proposed approach exhibits strong robustness and reliability, due to the 90.88% accuracy of object detection and 98.9% precision of tracking vehicle. Moreover, the absolute and relative error of extracted speed falls within ±3 km/h and 2%, respectively. The overall accuracy of the extracted parameters reaches up to 98%.

Driving behavior recognition can provide an important reference for the intelligent vehicle industry and probe vehicle-based traffic estimation. The identification of driving behavior using mobile sensing techniques such as smartphone- and vehicle-mounted terminals has gained significant attention in recent years. The present work proposed the monitoring of longitudinal driving behavior using a machine learning approach with the support of an on-board unit (OBU). Specifically, based on velocity, three-axis acceleration and three-axis angular velocity data were collected by a mobile vehicle terminal OBU; through the process of data preprocessing and feature extraction, seven machine learning algorithms, including support vector machine (SVM), random forest (RF), k-nearest neighbor algorithm (KNN), logistic regression (LR), BP neural network (BPNN), decision tree (DT), and the Naive Bayes (NB), were applied to implement the classification and monitoring of the longitudinal driving behavior of probe vehicles. The results show that the three classifiers SVM, RF and DT achieved good performances in identifying different longitudinal driving behaviors. The outcome of the present work could contribute to the fields of traffic management and traffic safety, providing important support for the realization of intelligent transport systems and the improvement of driving safety.

Pavement condition monitoring is an important task in road asset management and efficient abnormal pavement condition detection is critical for timely conservation management decisions. The present work introduces a mobile pavement condition monitoring approach utilizing low-cost sensor technology and machine-learning-based methodologies. Specifically, an on-board unit (OBU) embedded with an inertial measurement unit (IMU) and global positioning system (GPS) is applied to collect vehicle posture data in real time. Through a comprehensive analysis of both time domain and frequency domain data features for both normal and abnormal pavement conditions, feature engineering is conducted to identify how the most important features affect abnormal pavement condition recognition. Six machine learning models are then developed to identify different types of pavement conditions. The performance of different algorithms and the significance of different features are then analyzed. Moreover, the influence of vehicle speed on pavement condition assessment is further examined and classification models for different speed intervals are developed. The results indicate that the random forest (RF) model that considers vehicle speed achieves the best performance in pavement condition monitoring. The outcomes of the present work would contribute to cost-effective pavement condition monitoring and provide an important reference for pavement maintenance sectors.

There have been many implementations of carbon credit incentives (CCIs) for promoting green travel, but research on quantifying the effectiveness remains limited. To fill this gap, this study focuses on residents’ daily transportation mode choices under the incentive of carbon credits by employing an integrated choice and latent variable (ICLV) model to adequately address the role of attitudinal variables related to carbon credits, such as perceived usefulness, perceived ease of use, and behavioral intentions. Data from a questionnaire survey show that the ICLV model provides a richer and more nuanced understanding of the green mode choice than a traditional multinomial logit (MNL) model, where the AIC value of the ICLV model (3901.17) is smaller than that of the MNL model (3910.09). Carbon credits exhibit diverse impacts across various modes of eco-friendly transportation and specific demographic groups. Commuting trips reveal noteworthy positive associations between carbon credits and the use of bicycles as well as metro/bus services. Moreover, carbon credits exert a more pronounced influence on individuals with higher education levels, older age groups, and owners of new energy vehicles, whereas their impact on high-income individuals is relatively constrained. Furthermore, perceptions of carbon credits are pivotal, with perceived utility emerging as the most influential factor. The results provide a scientific basis for formulating more effective policies regarding carbon credit and incentive measures in the future.