Lane Departure Warning Mechanism of Limited False Alarm Rate Using Extreme Learning Residual Network and ϵ-Greedy LSTM

Gao, Qiaoming; Yin, Hang; Zhang, Weiwei

doi:10.3390/s20030644

Cited by 12 publications

(4 citation statements)

References 31 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [ 121 ] employed long short-term memory (LSTM) networks for lane position detection. Gao et al [ 131 ] minimized false alarms in lane departure warnings using an Extreme Learning Residual Network and ϵ-greedy LSTM. Moreover, ref.…”

Section: Discussion—methodologymentioning

confidence: 99%

Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends

Malligere Shivanna,

Guo

2023

Sensors

View full text Add to dashboard Cite

Advanced driver assistance systems (ADASs) are becoming increasingly common in modern-day vehicles, as they not only improve safety and reduce accidents but also aid in smoother and easier driving. ADASs rely on a variety of sensors such as cameras, radars, lidars, and a combination of sensors, to perceive their surroundings and identify and track objects on the road. The key components of ADASs are object detection, recognition, and tracking algorithms that allow vehicles to identify and track other objects on the road, such as other vehicles, pedestrians, cyclists, obstacles, traffic signs, traffic lights, etc. This information is then used to warn the driver of potential hazards or used by the ADAS itself to take corrective actions to avoid an accident. This paper provides a review of prominent state-of-the-art object detection, recognition, and tracking algorithms used in different functionalities of ADASs. The paper begins by introducing the history and fundamentals of ADASs followed by reviewing recent trends in various ADAS algorithms and their functionalities, along with the datasets employed. The paper concludes by discussing the future of object detection, recognition, and tracking algorithms for ADASs. The paper also discusses the need for more research on object detection, recognition, and tracking in challenging environments, such as those with low visibility or high traffic density.

show abstract

Section: Discussion—methodologymentioning

confidence: 99%

Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends

Malligere Shivanna,

Guo

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…8 A new machine learning is introduced to identify the driver's unintentional lane departure, and experiments validated that proposed method can reduce the false alarm rate. 9 A dual control scheme of driver assistance system is designed to prevent lane departure accidents by identifying driver drowsiness, the tradeoff between the accuracy and timeliness of drowsy driving detection is verified with a leave-one-out cross-validation. 10 Although the above researches can reduce false alarm of LDWS, it cannot predict the driver's behavior and intention for a period of time in the future.…”

Section: Introductionmentioning

confidence: 99%

A learning-based evaluation for lane departure warning system considering driving characteristics

Jin

Wang

Yan

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Misunderstanding the driver behavior in the next short time is the primary reason of the false warning for the lane departure warning system. This paper proposes a learning-based evaluation to predict whether the driver notices the deviation of the vehicle and takes corrective actions. First, statistical Gaussian model and K-means clustering method are utilized to classify driving style of drivers and determine warning areas based on key driving parameters extracted in driving scenarios. Then, according to the vehicle trajectory in the warning area and the time of lane crossing (TLC) value of the two warning area boundaries, an advanced horizontal dual-area warning (HDAW) model that is trained by bi-direction long short-term memory (BiLSTM) originated from recurrent neural network (RNN) is applied to predict the lane departure and corrective behavior of driver. The personalized warning strategy is finally developed by considering driver characteristics, which allows the warning system to adapt to different driving styles of drivers. Natural driving data from 57 drivers in the experimental driving simulator are collected to train personalized prediction and verify proposed evaluation method. The recent directional sequence of piecewise lateral slopes (DSPLS) and traditional TLC are also researched and compared. Experimental results show that the proposed approach has as low as false alarm rate of 3.97% and can improve prediction accuracy approximately 41.39% over DSPLS method.

show abstract

“…2 According to the National Highway Traffic Safety Administration (NHTSA), lane departures account for about 50% of vehicle collision accidents. 3 Fatigue and distraction are the most common causes of unintentional lane departure. 4 A brief distraction or loss of concentration can cause the drivers to leave from the lane in which the vehicle is located, leading to a collision accident.…”

Section: Introductionmentioning

confidence: 99%

Design and implementation of human driving data-based lane-keeping assistance system for electric bus

Lim

Kim

2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

This paper describes design, implementation, and evaluation of human driving data-based Lane Keeping Assistance System (LKAS) for electric bus equipped with a hybrid electric power steering system. The hybrid electric-power steering system used in this study means a steering system in which an Electric Power Steering (EPS) system and an Electro-Hydraulic Power Steering (EHPS) system are integrated into a ball-nut. A dynamic model of hybrid EPS system including EHPS system and EPS system has been developed to generate EPS torque and EHPS force corresponding to the input torque. In order to determine proper timing of LKAS intervention, driving data of electric bus drivers were collected and driving patterns were analyzed using a 2-D normal distribution probability density function. Lane information necessary for the lane-keeping assistance system is obtained from a vision camera mounted on the electric bus. Sliding mode control is used to get a Steering Wheel Angle (SWA) required for LKAS. A Proportional–Integral (PI) control is used to obtain an overlay torque required to track the target SWA. A proposed DLC threshold has been validated using vehicle simulation software, TruckSim, and MATLAB/Simulink. It is shown that the proposed DLC threshold shows good performance in both cases of slow lane departure and fast lane departure. The proposed algorithm has been successfully implemented on the electric bus and evaluated via real-world driving tests. Test scenario setting and the evaluation of performance were carried out by ISO 11270 criteria. It is shown that the algorithm successfully prevented the electric bus from unintended lane departure satisfying ISO 11270 criteria.

show abstract

Lane Departure Warning Mechanism of Limited False Alarm Rate Using Extreme Learning Residual Network and ϵ-Greedy LSTM

Cited by 12 publications

References 31 publications

Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends

Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends

A learning-based evaluation for lane departure warning system considering driving characteristics

Design and implementation of human driving data-based lane-keeping assistance system for electric bus

Contact Info

Product

Resources

About