# Multi-Modal Camera-Based Detection of Vulnerable Road Users

arXiv: https://arxiv.org/abs/2509.06333 · HTML: https://mlsanity.com/paper/2509.06333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels](https://mlsanity.com/paper/2301.12689/) (2023)
- [Camera-Lidar Integration: Probabilistic sensor fusion for semantic mapping](https://mlsanity.com/paper/2007.05490/) (2020)
- [Detection of E-scooter Riders in Naturalistic Scenes](https://mlsanity.com/paper/2111.14060/) (2021)
- [E-Scooter Rider Detection and Classification in Dense Urban Environments](https://mlsanity.com/paper/2205.10184/) (2022)
- [VALISENS: A Validated Innovative Multi-Sensor System for Cooperative Automated Driving](https://mlsanity.com/paper/2505.06980/) (2025)

## Abstract (arXiv)

Vulnerable road users (VRUs) such as pedestrians, cyclists, and motorcyclists represent more than half of global traffic deaths, yet their detection remains challenging in poor lighting, adverse weather, and unbalanced data sets. This paper presents a multimodal detection framework that integrates RGB and thermal infrared imaging with a fine-tuned YOLOv8 model. Training leveraged KITTI, BDD100K, and Teledyne FLIR datasets, with class re-weighting and light augmentations to improve minority-class performance and robustness, experiments show that 640-pixel resolution and partial backbone freezing optimise accuracy and efficiency, while class-weighted losses enhance recall for rare VRUs. Results highlight that thermal models achieve the highest precision, and RGB-to-thermal augmentation boosts recall, demonstrating the potential of multimodal detection to improve VRU safety at intersections.