PDIWS: Thermal Imaging Dataset for Person Detection in Intrusion Warning Systems

TL;DR

This paper introduces PDIWS, a synthetic thermal imaging dataset designed for person detection in intrusion warning systems, enabling improved training and evaluation of detection algorithms.

Contribution

The paper provides a novel synthetic thermal dataset with diverse backgrounds and poses, and demonstrates its effectiveness with high-performing object detection results.

Findings

Achieved up to 95.5% mAP at IoU 0.5

Dataset includes 2500 images with varied backgrounds and poses

Detection algorithms perform satisfactorily on the dataset

Abstract

In this paper, we present a synthetic thermal imaging dataset for Person Detection in Intrusion Warning Systems (PDIWS). The dataset consists of a training set with 2000 images and a test set with 500 images. Each image is synthesized by compounding a subject (intruder) with a background using the modified Poisson image editing method. There are a total of 50 different backgrounds and nearly 1000 subjects divided into five classes according to five human poses: creeping, crawling, stooping, climbing and other. The presence of the intruder will be confirmed if the first four poses are detected. Advanced object detection algorithms have been implemented with this dataset and give relatively satisfactory results, with the highest mAP values of 95.5% and 90.9% for IoU of 0.5 and 0.75 respectively. The dataset is freely published online for research purposes at https://github.com/thuan-researcher/Intruder-Thermal-Dataset.