Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.22260 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914504523120640 |
|---|---|
| author | Huang, Wenhui Zhang, Songyan Chua, Collister Liang, Yang Mao, Zhiqi Yang, Heng Lv, Chen |
| author_facet | Huang, Wenhui Zhang, Songyan Chua, Collister Liang, Yang Mao, Zhiqi Yang, Heng Lv, Chen |
| contents | Urban transportation systems face growing safety challenges that require scalable intelligence for emerging smart mobility infrastructures. While recent advances in foundation models and large-scale multimodal datasets have strengthened perception and reasoning in intelligent transportation systems (ITS), existing research remains largely centered on microscopic autonomous driving (AD), with limited attention to city-scale traffic analysis. In particular, open-ended safety-oriented visual question answering (VQA) and corresponding foundation models for reasoning over heterogeneous roadside camera observations remain underexplored. To address this gap, we introduce the Land Transportation Dataset (LTD), a large-scale open-source vision-language dataset for open-ended reasoning in urban traffic environments. LTD contains 11.6K high-quality VQA pairs collected from heterogeneous roadside cameras, spanning diverse road geometries, traffic participants, illumination conditions, and adverse weather. The dataset integrates three complementary tasks: fine-grained multi-object grounding, multi-image camera selection, and multi-image risk analysis, requiring joint reasoning over minimally correlated views to infer hazardous objects, contributing factors, and risky road directions. To ensure annotation fidelity, we combine multi-model vision-language generation with cross-validation and human-in-the-loop refinement. Building upon LTD, we further propose UniVLT, a transportation foundation model trained via curriculum-based knowledge transfer to unify microscopic AD reasoning and macroscopic traffic analysis within a single architecture. Extensive experiments on LTD and multiple AD benchmarks demonstrate that UniVLT achieves SOTA performance on open-ended reasoning tasks across diverse domains, while exposing limitations of existing foundation models in complex multi-view traffic scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22260 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset Huang, Wenhui Zhang, Songyan Chua, Collister Liang, Yang Mao, Zhiqi Yang, Heng Lv, Chen Computer Vision and Pattern Recognition Artificial Intelligence Urban transportation systems face growing safety challenges that require scalable intelligence for emerging smart mobility infrastructures. While recent advances in foundation models and large-scale multimodal datasets have strengthened perception and reasoning in intelligent transportation systems (ITS), existing research remains largely centered on microscopic autonomous driving (AD), with limited attention to city-scale traffic analysis. In particular, open-ended safety-oriented visual question answering (VQA) and corresponding foundation models for reasoning over heterogeneous roadside camera observations remain underexplored. To address this gap, we introduce the Land Transportation Dataset (LTD), a large-scale open-source vision-language dataset for open-ended reasoning in urban traffic environments. LTD contains 11.6K high-quality VQA pairs collected from heterogeneous roadside cameras, spanning diverse road geometries, traffic participants, illumination conditions, and adverse weather. The dataset integrates three complementary tasks: fine-grained multi-object grounding, multi-image camera selection, and multi-image risk analysis, requiring joint reasoning over minimally correlated views to infer hazardous objects, contributing factors, and risky road directions. To ensure annotation fidelity, we combine multi-model vision-language generation with cross-validation and human-in-the-loop refinement. Building upon LTD, we further propose UniVLT, a transportation foundation model trained via curriculum-based knowledge transfer to unify microscopic AD reasoning and macroscopic traffic analysis within a single architecture. Extensive experiments on LTD and multiple AD benchmarks demonstrate that UniVLT achieves SOTA performance on open-ended reasoning tasks across diverse domains, while exposing limitations of existing foundation models in complex multi-view traffic scenarios. |
| title | Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.22260 |