MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909441715077120 |
|---|---|
| author | Fan, Jiaqi Wu, Jianhua Gao, Jincheng Yu, Jianhao Wang, Yafei Chu, Hongqing Gao, Bingzhao |
| author_facet | Fan, Jiaqi Wu, Jianhua Gao, Jincheng Yu, Jianhao Wang, Yafei Chu, Hongqing Gao, Bingzhao |
| contents | Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing the type of driving scenario, actions of risk objects, and driving intentions and suggestions of ego-vehicle. Ultimately, a transformer-based network incorporating a regression token is trained to locate the risk objects. Extensive experiments on the existing DRAMA-ROLISP dataset and the extended DRAMA-SRIS dataset demonstrate that our method is efficient, surpassing many state-of-the-art image-based and video-based methods. Specifically, our method achieves 80.1% BLEU-1 score and 298.5% CIDEr score in the scene understanding task, and 59.6% accuracy in the localization task. Codes and datasets are available at https://github.com/fjq-tongji/MLLM-SUL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19406 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios Fan, Jiaqi Wu, Jianhua Gao, Jincheng Yu, Jianhao Wang, Yafei Chu, Hongqing Gao, Bingzhao Computer Vision and Pattern Recognition Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing the type of driving scenario, actions of risk objects, and driving intentions and suggestions of ego-vehicle. Ultimately, a transformer-based network incorporating a regression token is trained to locate the risk objects. Extensive experiments on the existing DRAMA-ROLISP dataset and the extended DRAMA-SRIS dataset demonstrate that our method is efficient, surpassing many state-of-the-art image-based and video-based methods. Specifically, our method achieves 80.1% BLEU-1 score and 298.5% CIDEr score in the scene understanding task, and 59.6% accuracy in the localization task. Codes and datasets are available at https://github.com/fjq-tongji/MLLM-SUL. |
| title | MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.19406 |