Driver Activity Classification Using Generalizable Representations from Vision-Language Models

Ross Greer, Mathias Viborg Andersen, Andreas Møgelmose, Mohan M. Trivedi

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstract

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.
OriginalsprogEngelsk
TitelVision and Language for Autonomous Driving and Robotics Workshop, CVPR
Publikationsdato2024
StatusUdgivet - 2024
BegivenhedVision and Language for Autonomous Driving and Robotics Workshop 2024 - Seattle, USA
Varighed: 18 jun. 202418 jun. 2024
https://vision-language-adr.github.io/#papers

Workshop

WorkshopVision and Language for Autonomous Driving and Robotics Workshop 2024
Land/OmrådeUSA
BySeattle
Periode18/06/202418/06/2024
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Driver Activity Classification Using Generalizable Representations from Vision-Language Models'. Sammen danner de et unikt fingeraftryk.

Citationsformater