Imperial College London
Alternate

Professor Yiannis Demiris

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Human-Centred Robotics, Head of ISN
 
 
 
//

Contact

 

+44 (0)20 7594 6300y.demiris Website

 
 
//

Location

 

1011Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Amadori:2021:10.1109/TITS.2021.3055120,
author = {Amadori, P and Fischer, T and Demiris, Y},
doi = {10.1109/TITS.2021.3055120},
journal = {IEEE Transactions on Intelligent Transportation Systems},
pages = {5573--5585},
title = {HammerDrive: A task-aware driving visual attention model},
url = {http://dx.doi.org/10.1109/TITS.2021.3055120},
volume = {23},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We introduce HammerDrive, a novel architecture for task-aware visual attention prediction in driving. The proposed architecture is learnable from data and can reliably infer the current focus of attention of the driver in real-time, while only requiring limited and easy-to-access telemetry data from the vehicle. We build the proposed architecture on two core concepts: 1) driving can be modeled as a collection of sub-tasks (maneuvers), and 2) each sub-task affects the way a driver allocates visual attention resources, i.e., their eye gaze fixation. HammerDrive comprises two networks: a hierarchical monitoring network of forward-inverse model pairs for sub-task recognition and an ensemble network of task-dependent convolutional neural network modules for visual attention modeling. We assess the ability of HammerDrive to infer driver visual attention on data we collected from 20 experienced drivers in a virtual reality-based driving simulator experiment. We evaluate the accuracy of our monitoring network for sub-task recognition and show that it is an effective and light-weight network for reliable real-time tracking of driving maneuvers with above 90% accuracy. Our results show that HammerDrive outperforms a comparable state-of-the-art deep learning model for visual attention prediction on numerous metrics with ~13% improvement for both Kullback-Leibler divergence and similarity, and demonstrate that task-awareness is beneficial for driver visual attention prediction.
AU  - Amadori,P
AU  - Fischer,T
AU  - Demiris,Y
DO  - 10.1109/TITS.2021.3055120
EP  - 5585
PY  - 2021///
SN  - 1524-9050
SP  - 5573
TI  - HammerDrive: A task-aware driving visual attention model
T2  - IEEE Transactions on Intelligent Transportation Systems
UR  - http://dx.doi.org/10.1109/TITS.2021.3055120
UR  - https://ieeexplore.ieee.org/document/9351808
UR  - http://hdl.handle.net/10044/1/87021
VL  - 23
ER  -
Download