Integrated solution for anomalous driving detection based on BeiDou/GPS/IMU measurements

Sun, Rui; Han, Ke; Hu, Jun; Wang, Yanjun; Hu, Minghua; Ochieng, Washington Yotto

doi:10.1016/j.trc.2016.06.006

Cited by 19 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In-vehicle camera [29][30][31][32][33], sensors, hardware [10,24] Real-world driving data; high-accuracy data; Access to driver's personal data and vehicle control data Expensive and time consuming; Lack of data in extreme and dangerous driving condition…”

Section: Collection Approaches Advantages Disadvantagesmentioning

confidence: 99%

“…Table 1 summarizes the advantage and the disadvantages of different driving data collection approaches. Researchers used instrumented vehicles to conduct naturalist driving experiments to identify behaviors [29][30][31]. Some instrumented vehicles were equipped with in-vehicle mounted cameras to capture video images of drivers [32,33], while others got help from specialized hardware and sensors to acquire throttle opening, pedal brake, wheel steering, vehicle speed, acceleration rate, and yaw rate [10,24].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data

Xue

Wang

et al. 2019

Journal of Advanced Transportation

View full text Add to dashboard Cite

Rear-end collision crash is one of the most common accidents on the road. Accurate driving style recognition considering rear-end collision risk is crucial to design useful driver assistance systems and vehicle control systems. The purpose of this study is to develop a driving style recognition method based on vehicle trajectory data extracted from the surveillance video. First, three rear-end collision surrogates, Inversed Time to Collision (ITTC), Time-Headway (THW), and Modified Margin to Collision (MMTC), are selected to evaluate the collision risk level of vehicle trajectory for each driver. The driving style of each driver in training data is labelled based on their collision risk level using K-mean algorithm. Then, the driving style recognition model’s inputs are extracted from vehicle trajectory features, including acceleration, relative speed, and relative distance, using Discrete Fourier Transform (DFT), Discrete Wavelet Transform (DWT), and statistical method to facilitate the driving style recognition. Finally, Supporting Vector Machine (SVM) is applied to recognize driving style based on the labelled data. The performance of Random Forest (RF), K-Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) is also compared with SVM. The results show that SVM overperforms others with 91.7% accuracy with DWT feature extraction method.

show abstract

Section: Collection Approaches Advantages Disadvantagesmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data

Xue

Wang

et al. 2019

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…The prediction for (2) is based on vehicle kinematic motion models. Constant acceleration (CA) and Constant Turn Rate and Acceleration (CTRA) models, shown to provide reasonable approximation of motion, are used on straight/curved roads (Tsogas et al, 2005;Sun et al, 2015a;Sun et al, 2015b;Sun et al, 2016). Thus, for every particle in (2), the prediction models are applied during the filtering processing as in equation (4).…”

Section: Predictionmentioning

confidence: 99%

Integrated GNSS/DR/road segment information system for variable road user charging

Qin

Sun

Ochieng

et al. 2017

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

Road User Charging (RUC) is designed to reduce congestion and collect revenue for the maintenance of transportation infrastructure. In order to determine the charges, it is important that appropriate Road User Charging Indicators (RUCI) are defined. This paper focusses on Variable Road User Charging (VRUC) as the more dynamic and flexible compared to Fixed Road User Charging (FRUC), and thus is a better reflection of the utility of the road space. The main issues associated with VRUC are the definition of appropriate charging indicators and their measurement. This paper addresses the former by proposing a number of new charging indicators, considering the equalization of the charges and marginal social cost imposed on others. The measurement of the indicators is addressed by a novel data fusion algorithm for the determination of the vehicle state based on the integration of Global Navigation Satellite Systems (GNSS) with Dead Reckoning (DR) and road segment information. Statistical analyses are presented in terms of the Required Navigation Performance (RNP) parameters of accuracy, integrity, continuity and availability, based on simulation and field tests. It is shown that the proposed fusion model is superior to positioning with GPS only, and GPS plus GLONASS, in terms of all the RNP parameters with a significant improvement in availability

show abstract

“…Some studies proposed Hidden Markov Model (HMM) to detect dangerous driving behaviors [27], which could be challenging with a large number of states to be estimated [28]. SVM also has been widely applied to various kinds of pattern recognition problems, including voice identification, text categorization, and face detection [29,30].…”

Section: Introductionmentioning

confidence: 99%

Improve Aggressive Driver Recognition Using Collision Surrogate Measurement and Imbalanced Class Boosting

Wang

Xue

Xing

et al. 2020

IJERPH

View full text Add to dashboard Cite

Real-time recognition of risky driving behavior and aggressive drivers is a promising research domain, thanks to powerful machine learning algorithms and the big data provided by in-vehicle and roadside sensors. However, since the occurrence of aggressive drivers in real traffic is infrequent, most machine learning algorithms treat each sample equally and prone to better predict normal drivers rather than aggressive drivers, which is our real interest. This paper aims to test the advantage of imbalanced class boosting algorithms in aggressive driver recognition using vehicle trajectory data. First, a surrogate measurement of collision risk, called Average Crash Risk (ACR), is proposed to calculate a vehicle’s crash risk. Second, the driver’s driving aggressiveness is determined by his/her ACR with three anomaly detection methods. Third, we train classification models to identify aggressive drivers using partial trajectory data. Three imbalanced class boosting algorithms, SMOTEBoost, RUSBoost, and CUSBoost, are compared with cost-sensitive AdaBoost and cost-sensitive XGBoost. Additionally, we try two resampling techniques with AdaBoost and XGBoost. Among all algorithms tested, CUSBoost achieves the highest or the second-highest Area Under Precision-Recall Curve (AUPRC) in most datasets. We find the discrete Fourier coefficients of gap as the key feature to identify aggressive drivers.

show abstract

Integrated solution for anomalous driving detection based on BeiDou/GPS/IMU measurements

Cited by 19 publications

References 16 publications

Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data

Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data

Integrated GNSS/DR/road segment information system for variable road user charging

Improve Aggressive Driver Recognition Using Collision Surrogate Measurement and Imbalanced Class Boosting

Contact Info

Product

Resources

About