Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach

TL;DR

This paper explores the use of large-scale vision language models for generating safe driving instructions by analyzing synchronized road-facing and driver-facing videos, highlighting their potential and current limitations.

Contribution

It introduces a dataset and evaluates LVLMs' performance in safety-critical driving scenarios, emphasizing the importance of fine-tuning for improved accuracy.

Findings

Fine-tuned LVLMs produce more accurate safety-aware instructions.

Pre-trained LVLMs have limited effectiveness in driving safety tasks.

Challenges remain in detecting subtle or complex events.

Abstract

Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous driving. For example, LVLMs can generate safety-oriented descriptions of videos captured by road-facing cameras. However, ensuring comprehensive safety requires monitoring driver-facing views as well to detect risky events, such as the use of mobiles while driving. Thus, the ability to process synchronized inputs is necessary from both driver-facing and road-facing cameras. In this study, we develop models and investigate the capabilities of LVLMs by constructing a dataset and evaluating their performance on this dataset. Our experimental results demonstrate that while pre-trained LVLMs have limited effectiveness, fine-tuned LVLMs can generate accurate and safety-aware driving instructions. Nonetheless, several challenges remain, particularly in detecting subtle or complex events in the video. Our findings and error analysis provide valuable insights that can contribute to the improvement of LVLM-based systems in this domain.