# Pedestrian Detection in Thermal Images using Saliency Maps

## TL;DR

This paper introduces a saliency map augmentation technique for thermal images to improve daytime pedestrian detection, achieving significant reduction in miss rates without relying on paired color images.

## Contribution

It proposes using saliency maps as an attention mechanism for thermal images, eliminating the need for paired color images in pedestrian detection.

## Key findings

- Reduced miss rate by 13.4% during daytime
- Reduced miss rate by 19.4% during nighttime
- Released a new dataset with pixel-level pedestrian masks

## Abstract

Thermal images are mainly used to detect the presence of people at night or in bad lighting conditions, but perform poorly at daytime. To solve this problem, most state-of-the-art techniques employ a fusion network that uses features from paired thermal and color images. Instead, we propose to augment thermal images with their saliency maps, to serve as an attention mechanism for the pedestrian detector especially during daytime. We investigate how such an approach results in improved performance for pedestrian detection using only thermal images, eliminating the need for paired color images. For our experiments, we train the Faster R-CNN for pedestrian detection and report the added effect of saliency maps generated using static and deep methods (PiCA-Net and R3-Net). Our best performing model results in an absolute reduction of miss rate by 13.4% and 19.4% over the baseline in day and night images respectively. We also annotate and release pixel level masks of pedestrians on a subset of the KAIST Multispectral Pedestrian Detection dataset, which is a first publicly available dataset for salient pedestrian detection.