VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929282096300032 |
|---|---|
| author | Wang, Hao Qin, Jiayou Bastola, Ashish Chen, Xiwen Suchanek, John Gong, Zihao Razi, Abolfazl |
| author_facet | Wang, Hao Qin, Jiayou Bastola, Ashish Chen, Xiwen Suchanek, John Gong, Zihao Razi, Abolfazl |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12415 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation Wang, Hao Qin, Jiayou Bastola, Ashish Chen, Xiwen Suchanek, John Gong, Zihao Razi, Abolfazl Computer Vision and Pattern Recognition Human-Computer Interaction 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. |
| title | VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction |
| url | https://arxiv.org/abs/2403.12415 |