# Pedestrain detection for low-light vision proposal

arXiv: https://arxiv.org/abs/2303.12725 · HTML: https://mlsanity.com/paper/2303.12725/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 24 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 3 of 3)

- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [DenseFuse: A Fusion Approach to Infrared and Visible Images](https://mlsanity.com/paper/1804.08361/) (2018)
- [Improved Actor Relation Graph based Group Activity Recognition](https://mlsanity.com/paper/2010.12968/) (2020)

## Abstract (arXiv)

The demand for pedestrian detection has created a challenging problem for various visual tasks such as image fusion. As infrared images can capture thermal radiation information, image fusion between infrared and visible images could significantly improve target detection under environmental limitations. In our project, we would approach by preprocessing our dataset with image fusion technique, then using Vision Transformer model to detect pedestrians from the fused images. During the evaluation procedure, a comparison would be made between YOLOv5 and the revised ViT model performance on our fused images