MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918139730591744 |
|---|---|
| author | Zhao, Kaikai Liu, Zhaoxiang Wang, Peng Wang, Xin Ma, Zhicheng Xu, Yajun Zhang, Wenjing Nan, Yibing Wang, Kai Lian, Shiguo |
| author_facet | Zhao, Kaikai Liu, Zhaoxiang Wang, Peng Wang, Xin Ma, Zhicheng Xu, Yajun Zhang, Wenjing Nan, Yibing Wang, Kai Lian, Shiguo |
| contents | General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated multimodal datasets. To address this gap, we introduce MITS (Multimodal Intelligent Traffic Surveillance), the first large-scale multimodal benchmark dataset specifically designed for ITS. MITS includes 170,400 independently collected real-world ITS images sourced from traffic surveillance cameras, annotated with eight main categories and 24 subcategories of ITS-specific objects and events under diverse environmental conditions. Additionally, through a systematic data generation pipeline, we generate high-quality image captions and 5 million instruction-following visual question-answer pairs, addressing five critical ITS tasks: object and event recognition, object counting, object localization, background analysis, and event reasoning. To demonstrate MITS's effectiveness, we fine-tune mainstream LMMs on this dataset, enabling the development of ITS-specific applications. Experimental results show that MITS significantly improves LMM performance in ITS applications, increasing LLaVA-1.5's performance from 0.494 to 0.905 (+83.2%), LLaVA-1.6's from 0.678 to 0.921 (+35.8%), Qwen2-VL's from 0.584 to 0.926 (+58.6%), and Qwen2.5-VL's from 0.732 to 0.930 (+27.0%). We release the dataset, code, and models as open-source, providing high-value resources to advance both ITS and LMM research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09730 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance Zhao, Kaikai Liu, Zhaoxiang Wang, Peng Wang, Xin Ma, Zhicheng Xu, Yajun Zhang, Wenjing Nan, Yibing Wang, Kai Lian, Shiguo Computer Vision and Pattern Recognition Artificial Intelligence General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated multimodal datasets. To address this gap, we introduce MITS (Multimodal Intelligent Traffic Surveillance), the first large-scale multimodal benchmark dataset specifically designed for ITS. MITS includes 170,400 independently collected real-world ITS images sourced from traffic surveillance cameras, annotated with eight main categories and 24 subcategories of ITS-specific objects and events under diverse environmental conditions. Additionally, through a systematic data generation pipeline, we generate high-quality image captions and 5 million instruction-following visual question-answer pairs, addressing five critical ITS tasks: object and event recognition, object counting, object localization, background analysis, and event reasoning. To demonstrate MITS's effectiveness, we fine-tune mainstream LMMs on this dataset, enabling the development of ITS-specific applications. Experimental results show that MITS significantly improves LMM performance in ITS applications, increasing LLaVA-1.5's performance from 0.494 to 0.905 (+83.2%), LLaVA-1.6's from 0.678 to 0.921 (+35.8%), Qwen2-VL's from 0.584 to 0.926 (+58.6%), and Qwen2.5-VL's from 0.732 to 0.930 (+27.0%). We release the dataset, code, and models as open-source, providing high-value resources to advance both ITS and LMM research. |
| title | MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09730 |