PDIWS

This dataset presents 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 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. 

本数据集面向入侵预警系统人员检测（Person Detection in Intrusion Warning Systems，简称PDIWS）任务，构建了一套合成式热成像数据集。该数据集包含训练集与测试集两个子集，其中训练集含2000张图像，测试集含500张图像。每张图像均通过改进型泊松图像编辑法，将目标人物（入侵者）与背景图像合成得到。数据集共涵盖50种不同背景，以及近1000个目标人物样本，该样本集依据人体姿态划分为五类：匍匐前进、四肢爬行、弯腰俯身、攀爬动作以及其他姿态。若检测到前四类姿态，则可确认场景中存在入侵者。已有多款先进目标检测算法基于本数据集开展实验，并取得了较为理想的检测效果：在交并比（Intersection over Union，IoU）为0.5与0.75的场景下，最高平均精度均值（mean Average Precision，mAP）分别可达95.5%与90.9%。本数据集已面向科研用途免费在线发布，访问地址为：https://github.com/thuan-researcher/Intruder-Thermal-Dataset。