The human eye gaze plays a vital role in monitoring people's attention, and various efforts have been made to improve in-vehicle driver gaze tracking systems. Most of them build the specific gaze estimation model by pre-annotated data training in an offline way. These systems usually tend to have poor generalization performance during the online gaze prediction, which is caused by the estimation bias between the training domain and the deployment domain, making the predicted gaze points shift from their correct location. To solve this problem, a novel driver's eye gaze tracking method with non-linear gaze point refinement is proposed in a monitoring system using two cameras, which eliminates the estimation bias and implicitly fine-tunes the gaze points. Supported by the two-stage gaze point clustering algorithm, the non-linear gaze point refinement method can gradually extract the representative gaze points of the forward and mirror gaze zone and establish the non-linear gaze point re-mapping relationship. In addition, the Unscented Kalman filter is utilized to track the driver's continuous status features. Experimental results show that the non-linear gaze point refinement method outperforms several previous gaze calibration and gaze mapping methods, and improves the gaze estimation accuracy even on the cross-subject evaluation. The system can be used for predicting the driver's attention.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8949346 | PMC |
| http://dx.doi.org/10.3390/s22062326 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Background: The application of image recognition technology has been spreading to dementia screening. However, cognitive function fluctuates due to mental and physical conditions. Therefore, we believe that it may be necessary to evaluate facial information over time after considering these factors.
View Article and Find Full Text PDFExamining the influence of digital phantom models in virtual imaging trials for tomographic breast imaging.
J Med Imaging (Bellingham)
January 2025
University of Houston, Department of Biomedical Engineering, Houston, Texas, United States.
Purpose: Digital phantoms are one of the key components of virtual imaging trials (VITs) that aim to assess and optimize new medical imaging systems and algorithms. However, these phantoms vary in their voxel resolution, appearance, and structural details. We investigate whether and how variations between digital phantoms influence system optimization with digital breast tomosynthesis (DBT) as a chosen modality.
View Article and Find Full Text PDFThe social life of creative methods: Filmmaking, fabulation and recovery.
Br J Sociol
December 2024
Artist in Residence, Centre for Health, Arts, Society and the Environment (CHASE), University of Liverpool, Liverpool, UK.
In this article we consider the theoretical and methodological implications of Deleuzian fabulation for research on recovery from drugs and alcohol as an alternative way of making and doing methods in sociology. The article draws on data produced as part of an ongoing interdisciplinary research collaboration, begun in 2019, with the visual artist and filmmaker Melanie Manchot, social scientists Nicole Vitellone and Lena Theodoropoulou, and people in recovery from drugs and alcohol engaged in the production of Manchot's first feature film STEPHEN. This project attends to the methodological practice of filmmaking as a way of thinking with and alongside colleagues from divergent disciplines about the role of methods, concepts and practices for confronting and resisting processes of stigmatisation.
View Article and Find Full Text PDFObjective: In preterm and very low birth weight (VLBW) infants, attention-related problems have been found to be more pronounced and emerge later as academic difficulties that may persist into school age. In response, based on three attention networks: alerting, orienting, and executive attention, we examined the development of attention functions at 42 months (not corrected for prematurity) as a follow-up study of VLBW ( = 23) and normal birth weight (NBW: = 48) infants.
Method: The alerting and orienting attention networks were examined through an overlap task with or without warning signal.
Sophisticated perspective-takers are distinctive: Neural idiosyncrasy of functional connectivity in the mentalizing network.
iScience
December 2024
School of Psychology, Northeast Normal University, Changchun 130024, China.
Naive perspective-takers often perceive the social world in a simplistic and uniform way, whereas sophisticated ones recognize the diversity and complexity of others' minds. This commonly accepted distinction points to a possibility of greater inter-individual variability in mentalizing for sophisticated than naive perspective-takers, a difference previously overlooked in research. In the current study, participants were asked to watch a mentalizing-related movie and their neural responses, interpretations of the characters' mental states, and eye-gaze trajectories were recorded.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!