Driver Activity Classification Using Generalizable Representations from Vision-Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Greer, Ross, Andersen, Mathias Viborg, Møgelmose, Andreas, Trivedi, Mohan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909178706001920
author Greer, Ross
Andersen, Mathias Viborg
Møgelmose, Andreas
Trivedi, Mohan
author_facet Greer, Ross
Andersen, Mathias Viborg
Møgelmose, Andreas
Trivedi, Mohan
contents Driver activity classification is crucial for ensuring road safety, with applications ranging from driver assistance systems to autonomous vehicle control transitions. In this paper, we present a novel approach leveraging generalizable representations from vision-language models for driver activity classification. Our method employs a Semantic Representation Late Fusion Neural Network (SRLF-Net) to process synchronized video frames from multiple perspectives. Each frame is encoded using a pretrained vision-language encoder, and the resulting embeddings are fused to generate class probability predictions. By leveraging contrastively-learned vision-language representations, our approach achieves robust performance across diverse driver activities. We evaluate our method on the Naturalistic Driving Action Recognition Dataset, demonstrating strong accuracy across many classes. Our results suggest that vision-language representations offer a promising avenue for driver monitoring systems, providing both accuracy and interpretability through natural language descriptors.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14906
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Driver Activity Classification Using Generalizable Representations from Vision-Language Models
Greer, Ross
Andersen, Mathias Viborg
Møgelmose, Andreas
Trivedi, Mohan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Driver activity classification is crucial for ensuring road safety, with applications ranging from driver assistance systems to autonomous vehicle control transitions. In this paper, we present a novel approach leveraging generalizable representations from vision-language models for driver activity classification. Our method employs a Semantic Representation Late Fusion Neural Network (SRLF-Net) to process synchronized video frames from multiple perspectives. Each frame is encoded using a pretrained vision-language encoder, and the resulting embeddings are fused to generate class probability predictions. By leveraging contrastively-learned vision-language representations, our approach achieves robust performance across diverse driver activities. We evaluate our method on the Naturalistic Driving Action Recognition Dataset, demonstrating strong accuracy across many classes. Our results suggest that vision-language representations offer a promising avenue for driver monitoring systems, providing both accuracy and interpretability through natural language descriptors.
title Driver Activity Classification Using Generalizable Representations from Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.14906