# Hazard-Aware Traffic Scene Graph Generation

arXiv: https://arxiv.org/abs/2603.03584 · HTML: https://mlsanity.com/paper/2603.03584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Message Passing for Hyper-Relational Knowledge Graphs](https://mlsanity.com/paper/2009.10847/) (2020)
- [SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing](https://mlsanity.com/paper/2004.13316/) (2020)
- [Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB](https://mlsanity.com/paper/1804.02675/) (2018)
- [Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions](https://mlsanity.com/paper/2009.06435/) (2020)
- [Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks](https://mlsanity.com/paper/1909.09272/) (2019)
- [RSG-Net: Towards Rich Sematic Relationship Prediction for Intelligent Vehicle in Complex Environments](https://mlsanity.com/paper/2207.12321/) (2022)

## Abstract (arXiv)

Maintaining situational awareness in complex driving scenarios is challenging. It requires continuously prioritizing attention among extensive scene entities and understanding how prominent hazards might affect the ego vehicle. While existing studies excel at detecting specific semantic categories and visually salient regions, they lack the ability to assess safety-relevance. Meanwhile, the generic spatial predicates either for foreground objects only or for all scene entities modeled by existing scene graphs are inadequate for driving scenarios. To bridge this gap, we introduce a novel task, Traffic Scene Graph Generation, which captures traffic-specific relations between prominent hazards and the ego vehicle. We propose a novel framework that explicitly uses traffic accident data and depth cues to supplement visual features and semantic information for reasoning. The output traffic scene graphs provide intuitive guidelines that stress prominent hazards by color-coding their severity and notating their effect mechanism and relative location to the ego vehicle. We create relational annotations on Cityscapes dataset and evaluate our model on 10 tasks from 5 perspectives. The results in comparative experiments and ablation studies demonstrate our capacity in ego-centric reasoning for hazard-aware traffic scene understanding.