Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Elhenawy, Mohammed, Ashqar, Huthaifa I., Rakotonirainy, Andry, Alhadidi, Taqwa I., Jaber, Ahmed, Tami, Mohammad Abu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917888182452224
author Elhenawy, Mohammed
Ashqar, Huthaifa I.
Rakotonirainy, Andry
Alhadidi, Taqwa I.
Jaber, Ahmed
Tami, Mohammad Abu
author_facet Elhenawy, Mohammed
Ashqar, Huthaifa I.
Rakotonirainy, Andry
Alhadidi, Taqwa I.
Jaber, Ahmed
Tami, Mohammad Abu
contents Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study developed a dynamic scene retrieval system using Contrastive Language-Image Pretraining (CLIP) models, which can be optimized for real-time deployment on edge devices. The proposed system outperforms state-of-the-art in-context learning methods, including the zero-shot capabilities of GPT-4o, particularly in complex scenarios. By conducting frame-level analysis on the Honda Scenes Dataset, which contains a collection of about 80 hours of annotated driving videos capturing diverse real-world road and weather conditions, our study highlights the robustness of CLIP models in learning visual concepts from natural language supervision. Results also showed that fine-tuning the CLIP models, such as ViT-L/14 and ViT-B/32, significantly improved scene classification, achieving a top F1 score of 91.1%. These results demonstrate the ability of the system to deliver rapid and precise scene recognition, which can be used to meet the critical requirements of Advanced Driver Assistance Systems (ADAS). This study shows the potential of CLIP models to provide scalable and efficient frameworks for dynamic scene understanding and classification. Furthermore, this work lays the groundwork for advanced autonomous vehicle technologies by fostering a deeper understanding of driver behavior, road conditions, and safety-critical scenarios, marking a significant step toward smarter, safer, and more context-aware autonomous driving systems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding
Elhenawy, Mohammed
Ashqar, Huthaifa I.
Rakotonirainy, Andry
Alhadidi, Taqwa I.
Jaber, Ahmed
Tami, Mohammad Abu
Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study developed a dynamic scene retrieval system using Contrastive Language-Image Pretraining (CLIP) models, which can be optimized for real-time deployment on edge devices. The proposed system outperforms state-of-the-art in-context learning methods, including the zero-shot capabilities of GPT-4o, particularly in complex scenarios. By conducting frame-level analysis on the Honda Scenes Dataset, which contains a collection of about 80 hours of annotated driving videos capturing diverse real-world road and weather conditions, our study highlights the robustness of CLIP models in learning visual concepts from natural language supervision. Results also showed that fine-tuning the CLIP models, such as ViT-L/14 and ViT-B/32, significantly improved scene classification, achieving a top F1 score of 91.1%. These results demonstrate the ability of the system to deliver rapid and precise scene recognition, which can be used to meet the critical requirements of Advanced Driver Assistance Systems (ADAS). This study shows the potential of CLIP models to provide scalable and efficient frameworks for dynamic scene understanding and classification. Furthermore, this work lays the groundwork for advanced autonomous vehicle technologies by fostering a deeper understanding of driver behavior, road conditions, and safety-critical scenarios, marking a significant step toward smarter, safer, and more context-aware autonomous driving systems.
title Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2501.05566