VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation

TL;DR

This paper presents a framework combining Large Language Models and real-time object detection to identify anomalies in visual navigation, enhancing safety and flexibility in complex environments.

Contribution

It introduces a novel LLM-assisted anomaly detection system that integrates open-world object detection and dynamic scenario switching for improved visual navigation.

Findings

Effective zero-shot anomaly detection in real-time

Enhanced scene transition capabilities

Potential for improved visual accessibility

Abstract

This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation. With the assistance of the state-of-the-art real-time open-world object detection model Yolo-World and specialized prompts, the proposed framework can identify anomalies within camera-captured frames that include any possible obstacles, then generate concise, audio-delivered descriptions emphasizing abnormalities, assist in safe visual navigation in complex circumstances. Moreover, our proposed framework leverages the advantages of LLMs and the open-vocabulary object detection model to achieve the dynamic scenario switch, which allows users to transition smoothly from scene to scene, which addresses the limitation of traditional visual navigation. Furthermore, this paper explored the performance contribution of different prompt components, provided the vision for future improvement in visual accessibility, and paved the way for LLMs in video anomaly detection and vision-language understanding.