Gaze-Vector Estimation in the Dark with Temporally Encoded Event-driven Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banerjee, Abeer, Mehta, Naval K., Prasad, Shyam S., Himanshu, Saurav, Sumeet, Singh, Sanjay
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910354118803456
author Banerjee, Abeer
Mehta, Naval K.
Prasad, Shyam S.
Himanshu
Saurav, Sumeet
Singh, Sanjay
author_facet Banerjee, Abeer
Mehta, Naval K.
Prasad, Shyam S.
Himanshu
Saurav, Sumeet
Singh, Sanjay
contents In this paper, we address the intricate challenge of gaze vector prediction, a pivotal task with applications ranging from human-computer interaction to driver monitoring systems. Our innovative approach is designed for the demanding setting of extremely low-light conditions, leveraging a novel temporal event encoding scheme, and a dedicated neural network architecture. The temporal encoding method seamlessly integrates Dynamic Vision Sensor (DVS) events with grayscale guide frames, generating consecutively encoded images for input into our neural network. This unique solution not only captures diverse gaze responses from participants within the active age group but also introduces a curated dataset tailored for low-light conditions. The encoded temporal frames paired with our network showcase impressive spatial localization and reliable gaze direction in their predictions. Achieving a remarkable 100-pixel accuracy of 100%, our research underscores the potency of our neural network to work with temporally consecutive encoded images for precise gaze vector predictions in challenging low-light videos, contributing to the advancement of gaze prediction technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02909
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaze-Vector Estimation in the Dark with Temporally Encoded Event-driven Neural Networks
Banerjee, Abeer
Mehta, Naval K.
Prasad, Shyam S.
Himanshu
Saurav, Sumeet
Singh, Sanjay
Computer Vision and Pattern Recognition
Human-Computer Interaction
Image and Video Processing
In this paper, we address the intricate challenge of gaze vector prediction, a pivotal task with applications ranging from human-computer interaction to driver monitoring systems. Our innovative approach is designed for the demanding setting of extremely low-light conditions, leveraging a novel temporal event encoding scheme, and a dedicated neural network architecture. The temporal encoding method seamlessly integrates Dynamic Vision Sensor (DVS) events with grayscale guide frames, generating consecutively encoded images for input into our neural network. This unique solution not only captures diverse gaze responses from participants within the active age group but also introduces a curated dataset tailored for low-light conditions. The encoded temporal frames paired with our network showcase impressive spatial localization and reliable gaze direction in their predictions. Achieving a remarkable 100-pixel accuracy of 100%, our research underscores the potency of our neural network to work with temporally consecutive encoded images for precise gaze vector predictions in challenging low-light videos, contributing to the advancement of gaze prediction technologies.
title Gaze-Vector Estimation in the Dark with Temporally Encoded Event-driven Neural Networks
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Image and Video Processing
url https://arxiv.org/abs/2403.02909