Research on recognition of dangerous driving behavior based on support vector machine

Zhang, Liumei; Tan, Baoyume; Liu, Tianshi; Li, Jiao

doi:10.1117/12.2589350

Cited by 7 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, an SVM does not work well when classifying unbalanced datasets. A study [83] applied Random-SMOTE to balance the number of positive and negative samples and then used a cost-sensitive SVM to set different penalty factors for the positive and negative samples, thus improving the model's ability to recognize dangerous driving behaviors (i.e., dangerous short-term driving style). The traditional SVM algorithm can only be used to solve binary classification problems.…”

Section: • Sommentioning

confidence: 99%

A Review of Driving Style Recognition Methods From Short-Term and Long-Term Perspectives

Chu,

Zhuang,

Wang

et al. 2023

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Driving style recognition provides an effective way to understand human driving behaviors and thereby plays an important role in the automotive sector. However, most works fail to consider the influence of deploying the recognition results on the vehicle side, which requires real-time recognition performance. To facilitate the application of driving styles in automotive, we survey related advances in driving style recognition along short-and long-term pipelines. We first defined short-and long-term driving styles and then described the input data used by the recognition models and related data-processing techniques. Furthermore, we also revisited existing evaluation metrics for different recognition algorithms. Finally, we discussed the potential applications of driving style recognition in intelligent vehicles.

show abstract

Section: • Sommentioning

confidence: 99%

A Review of Driving Style Recognition Methods From Short-Term and Long-Term Perspectives

Chu,

Zhuang,

Wang

et al. 2023

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

show abstract

“…Berndt et al [5] used the hidden Markov model (HMM) to recognize driving intentions. Zhu et al [6] and Zhang et al [7] proposed a driving behavior recognition method based on a support vector machine (SVM); the test results demonstrated a good recognition effect. Liu et al [8] integrated the HMM and SVM methods to improve the accuracy of driving intention recognition.…”

Section: Individual Intelligent Vehicle Motion-planning Modelmentioning

confidence: 99%

“…Berndt [5] 2008 Used HMM to recognize driving intention Zhu et al [6] 2017 Recognition method of driving behavior based on SVM Liu et al [8] 2018 HMM and SVM Zong et al [9] 2009 Proposed HMM and ANN driver behavior prediction models Zhang et al [10] 2019 MV-CNN has better generalization ability than ANN Zhang et al [7] 2021 SVM optimization…”

Section: Intent Recognitionmentioning

confidence: 99%

Research Progress and Prospects of Vehicle Driving Behavior Prediction

Zheng

2021

WEVJ

View full text Add to dashboard Cite

Autonomous driving technology is vital for intelligent transportation systems. Vehicle driving behavior prediction is the foundation and core of autonomous driving. A detailed review of the existing research on vehicle driving behavior prediction can improve the understanding of the current progress of research on autonomous driving and provide references for follow-up researchers. This paper primarily reviews and analyzes the control models of autonomous driving, prejudgment methods, on-road and intersection traffic decision-making, and shortcomings of the research about the prediction of individual intelligent vehicle driving behavior, the prediction on movements of vehicles connected via the Internet, and prediction of driving behavior in a mixed traffic environment. The deficiencies in the research on vehicle driving behavior prediction are as follows: (1) there are numerous limitations in the intelligent application scenarios of individual intelligent vehicles; (2) although the Internet of Vehicles is a significant developmental trend, the training and test datasets are not rich enough; and (3) as the research of mixed traffic flow is still in the initial stages, the comfort brought by autonomous driving in hybrid driving environments is not being considered. In addition to the above analyses and comments, the future research prospects of vehicle driving behavior prediction are discussed as well.

show abstract

“…Therefore, when driving on a cross slope, the speed must be slow to prevent the ground from bumping and avoid turning on the slope (Liao C. et al, 2018). Zhang L. et al believe that when the tractor runs in dangerous areas such as ditch embankment and dam edge, the tractor should be a certain distance away from the ditch edge, and the driver must concentrate on driving the tractor (Zhang L. et al, 2021).…”

Section: Fig 1 -Tractor Overturned In the Guttermentioning

confidence: 99%

Study on Active Anti Rollover Control and Model Test of Tractor Momentum Flywheel

Qiao¹,

Wei²

2021

INMATEH

View full text Add to dashboard Cite

The tractor working environment is complex and changeable, and the dynamic variation range of the center of gravity position of the tractor body is large. In order to avoid rollover accident, an active anti rollover control method of tractor momentum flywheel and its model test are proposed in this paper. The tractor dynamic system model and control strategy are verified by a 1:16 scale tractor model. The research results show that when the model tractor crosses the trapezoidal obstacle B, the roll angle of the whole machine is temporarily stable near 35 °, indicating that at this time, the tires on one side of the whole machine are in actual contact with the obstacle, showing a short stable state of the whole machine. When the pavement roughness reaches F-H level, without any active anti rollover control, the evaluation index EP shows a divergence trend when it is greater than 1, and the simulation calculation is terminated due to the occurrence of rollover of the whole machine. The test data and simulation results under two different driving speeds are in good agreement, which verifies the effectiveness and reliability of the tractor rollover dynamic system model and the momentum flywheel active stabilization system.

show abstract

Research on recognition of dangerous driving behavior based on support vector machine

Cited by 7 publications

References 0 publications

A Review of Driving Style Recognition Methods From Short-Term and Long-Term Perspectives

A Review of Driving Style Recognition Methods From Short-Term and Long-Term Perspectives

Research Progress and Prospects of Vehicle Driving Behavior Prediction

Study on Active Anti Rollover Control and Model Test of Tractor Momentum Flywheel

Contact Info

Product

Resources

About