Speak2Label: Using Domain Knowledge for Creating a Large Scale Driver Gaze Zone Estimation Dataset

Ghosh, Shreya; Dhall, Abhinav; Sharma, Garima; Gupta, Sarthak; Sebe, Nicu

doi:10.1109/iccvw54120.2021.00324

Cited by 21 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid a labor-intensive and error-prone annotation process, drivers are instructed to look at specific areas or markers in the vehicle or the scene while seated in the parked vehicle. This approach is taken in LISA v2 [73], DGW [235], and DMD [236] datasets. In LISA v2, subjects were filmed under different lighting conditions (daytime, nighttime and harsh lighting) with and without eyeglasses.…”

Section: B Driving Datasets Without Eye-tracking Datamentioning

confidence: 99%

Attention for Vision-Based Assistive and Automated Driving: A Review of Algorithms and Datasets

Kotseruba

Tsotsos

2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Driving safety has been a concern since the first cars appeared on the streets. Driver inattention has been singled out as a major cause of accidents early on. This is hardly surprising, as drivers routinely perform other tasks in addition to controlling the vehicle. Decades of research into what causes lapses or misdirection of drivers' attention resulted in improvements in road safety through better design of infrastructure, driver training programs, in-vehicle interfaces, and, more recently, the development of driving assistance systems (ADAS) and driving automation. This review focuses on the methods for modeling and detecting spatio-temporal aspects of drivers' attention, i.e. where and when they look, for the two latter categories of applications.We start with a brief theoretical background on human visual attention, methods for recording and measuring attention in the driving context, types of driver inattention, and factors causing it. We then discuss machine learning approaches for 1) modeling gaze for assistive and self-driving applications and 2) detecting gaze for driver monitoring. Following the overview of state-of-the-art models, we provide an extensive list of publicly available datasets that feature recordings of drivers' gaze and other attention-related annotations. We conclude with a general overview of the remaining challenges, such as data availability and quality, evaluation methods, and the limited scope of attention modeling, and outline steps toward rectifying some of these issues. Categorized and annotated lists of the reviewed models and datasets are available at https://github.com/ykotseruba/attention_and_driving

show abstract

Section: B Driving Datasets Without Eye-tracking Datamentioning

confidence: 99%

Attention for Vision-Based Assistive and Automated Driving: A Review of Algorithms and Datasets

Kotseruba

Tsotsos

2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…TabletGaze [33], RT-GENE [19] and DGW [25]. CAVE [74] dataset has 5,880 high resolution images of 56 subjects.…”

Section: Experimental Protocolsmentioning

confidence: 99%

“…The ground truth annotation is assigned using a motion capture system connected with eye-tracking glasses. DGW [25] is a large scale driver gaze zone estimation dataset. DGW contains data from 338 subjects fixating their gaze 'inside a car' scenario with variation in illumination, occlusion etc.…”

Section: Experimental Protocolsmentioning

confidence: 99%

“…We evaluate the performance of Ize-Net network by cross-validating it's performance some with other gaze estimation task. We choose Driver Gaze in the Wild (DGW) [25] data for this purpose. It performs automatic labeling by adding domain knowledge during the data recording process and generate a large scale gaze zone estimation dataset.…”

Section: Raw Pixels* [33]mentioning

confidence: 99%

“…It performs automatic labeling by adding domain knowledge during the data recording process and generate a large scale gaze zone estimation dataset. TABLE VII shows the comparison between performance of the baseline model proposed in [25] with Ize-Net. It is observed that our approach outperforms several supervised models with a large margin which indicates that our model learns relevant representative features.…”

Section: Raw Pixels* [33]mentioning

confidence: 99%

See 2 more Smart Citations