Lane-change intention prediction using eye-tracking technology: A systematic review

Pan, Yunxian; Zhang, Qinyu; Zhang, Yifan; Ge, Xianliang; Gao, Xiaoqing; Yang, Shiyan; Xu, Jie

doi:10.1016/j.apergo.2022.103775

Cited by 15 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Testing resulted in a maximum F1-score of 0.9, achieved with a confidence score between 0.1 and 0.9, a satisfactory result along with Precision and Recall, both exceeding 0.9. However, from the inference results, and thus from knowing only the coordinates of the center of mass of the bounding boxes, it is not possible to measure the distance of the caregiver from the wheelchair since this also depends on the intrinsic parameters of the camera, as demonstrated in Equations ( 1) and (2). For these reasons, the camera was calibrated.…”

Section: Training Resultsmentioning

confidence: 99%

“…The concept of Advanced Driver-Assistance Systems (ADASs) is nowadays applied in an increasing number of fields. Initially, the prevalent field of use has been in the world of self-driving vehicles, particularly in supporting decisions such as obstacle avoidance, lane keeping, and other decisions to avoid accidents [ 1 , 2 ]. ADASs have since been employed in drones for both military and civilian use as a useful aid in avoiding obstacles in flight and supporting the ground operator in operating the aircraft [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

“…( 3). 2 In particular, when the caregiver moves away from the wheelchair, the angle β, reported 2 in the equation, increases to over 60°. For these angles, however, the slope of the tangent 2 The results of the calibration curve show that the deviation of the measured values from the ideal calibration line is much greater for values close to the full scale of the instrument.…”

mentioning

confidence: 99%

“…The results of the calibration curve show that the deviation of measured values from 2 the ideal calibration line is much greater for values close to the full scale of the instrument. 2 The systematic error contribution to the full scale of the instrument is mainly due to Eq. ( 3).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Design and Characterization of a Powered Wheelchair Autonomous Guidance System

Gallo,

Shallari,

Carratù

et al. 2024

Sensors

View full text Add to dashboard Cite

The current technological revolution driven by advances in machine learning has motivated a wide range of applications aiming to improve our quality of life. Representative of such applications are autonomous and semiautonomous Powered Wheelchairs (PWs), where the focus is on providing a degree of autonomy to the wheelchair user as a matter of guidance and interaction with the environment. Based on these perspectives, the focus of the current research has been on the design of lightweight systems that provide the necessary accuracy in the navigation system while enabling an embedded implementation. This motivated us to develop a real-time measurement methodology that relies on a monocular RGB camera to detect the caregiver’s feet based on a deep learning method, followed by the distance measurement of the caregiver from the PW. An important contribution of this article is the metrological characterization of the proposed methodology in comparison with measurements made with dedicated depth cameras. Our results show that despite shifting from 3D imaging to 2D imaging, we can still obtain comparable metrological performances in distance estimation as compared with Light Detection and Ranging (LiDAR) or even improved compared with stereo cameras. In particular, we obtained comparable instrument classes with LiDAR and stereo cameras, with measurement uncertainties within a magnitude of 10 cm. This is further complemented by the significant reduction in data volume and object detection complexity, thus facilitating its deployment, primarily due to the reduced complexity of initial calibration, positioning, and deployment compared with three-dimensional segmentation algorithms.

show abstract

Section: Training Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Design and Characterization of a Powered Wheelchair Autonomous Guidance System

Gallo,

Shallari,

Carratù

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Zhang Lei [10] reviewed the research progress of the lane-changing model, lane-changing behavior characteristics, lane-changing assisted warning, and autonomous lane-changing system. Based on the systematic literature review, Pan [11] showed that eye-tracking data features and other data sources can be used as useful inputs for predicting DLCI. useful input for predicting DLCI; Li et al [12] proposed a hidden Markov model (HMM) that links driver physiological information and vehicle dynamics data to driving risk; and Deng et al [13] studied a model that can be used to develop proactive crash prevention strategies.…”

mentioning

confidence: 99%