1. |
|
|
2. |
- Xue, Qingwen, et al.
(författare)
-
A Context-Aware Framework for Risky Driving Behavior Evaluation Based on Trajectory Data
- 2023
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 15:1, s. 70-83
-
Tidskriftsartikel (refereegranskat)abstract
- Risky driving behaviors are one of the key contributors to traffic accidents. The rapid and accurate identification of them is important to improve the safety of the driving environment. This study introduces a contextaware framework for the evaluation of risky driving behaviors based on trajectory data. It consists of three models to identify the context, determine risky maneuvers, and evaluate risky driving behaviors. We first propose a surrogate-based method to label risky maneuvers considering context factors. Then, the features of driving trajectories are extracted as the input features for the evaluation of risky behavior. Based on the labeling result and maneuver features, supervised machine learning algorithms are leveraged to model their relationships for evaluations. Three feature extraction methods and five classifiers are compared in this article to select the most suitable one. Last, a context-aware evaluation framework is proposed to recognize risky driving behaviors incorporating context. The trajectory data extracted from unmanned aerial vehicles are used to validate the proposed framework. The results show that the accuracy of risky driving behaviors evaluation could reach 97%. The proposed framework in this study can effectively evaluate risky driving behaviors based on trajectory data with the consideration of context factors.
|
|
3. |
- Xue, Qingwen, et al.
(författare)
-
Driving Style Recognition Incorporating Risk Surrogate by Support Vector Machine
- 2021
-
Ingår i: Smart Innovation, Systems and Technologies. - Singapore : Springer Singapore. - 2190-3026 .- 2190-3018. ; 231, s. 123-131
-
Konferensbidrag (refereegranskat)abstract
- Accurate driving style recognition is a crucial component for advanced driver assistance systems and vehicle control systems to reduce potential rear-end collision risk. This study aims to develop a driving style recognition method incorporating matching learning algorithms and vehicle trajectory data. A risk surrogate, Modified Margin to Collision (MMTC), is proposed to evaluate the collision risk level of each driver’s trajectory. Particularly, the traffic level is considered when labelling the driving style, while it has a great impact on driving preference. Afterwards, each driver’s driving style is labelled based on their collision risk level using the K-means algorithm. Driving behavior features, including acceleration, relative speed, and relative distance, are extracted from vehicle trajectory and processed by time-sequence analysis. Finally, Supporting Vector Machine (SVM) is applied to recognize driving style based on the extracted features and labelled data. The performance of Random Forest (RF), K-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) are also compared with SVM. The “leave-one-out” method is used to validate the performance and effectiveness of the proposed model. The results show that SVM over performs others with 91.7% accuracy. This recognition model could effectively recognize the aggressive driving style, which can better support ADAS.
|
|
4. |
- Yuan, Ye, et al.
(författare)
-
Smart Pavement: An Attention-Based Classification Model for Road Pavement Material
- 2022
-
Ingår i: Smart Innovation, Systems and Technologies. - Singapore : Springer Nature Singapore. - 2190-3026 .- 2190-3018. ; 304 SIST, s. 133-140
-
Konferensbidrag (refereegranskat)abstract
- Intelligent recognition of traffic road damage is essential for realizing smart vehicles and intelligent transportation systems. The classification of road material types before recognition is a challenge for traffic road damage recognition due to differences in features such as concrete and asphalt. In addition, the widely distributed roads make environmental factors a critical factor affecting the classification. In this paper, we propose a deep learning-based road material classification method that introduces an attention mechanism to deal with the influence of different environments on road material recognition. We acquired tens of thousands of road surface images for training and testing and performed practical validation in real roads. The experiments show that our method has high accuracy and recall in road material classification.
|
|