PMMA：波士顿技术大学校园移动辅助设备数据集
摘要
本研究介绍了一个新的行人目标检测数据集，名为PMMA（Polytechnique Montreal Mobility Aids Dataset）。该数据集在户外环境中收集，志愿者使用轮椅、拐杖和步行器， resulting in nine categories of pedestrians: pedestrians, cane users, two types of walker users, whether walking or resting, five types of wheelchair users, including wheelchair users, people pushing empty wheelchairs, and three types of users pushing occupied wheelchairs, including the entire pushing group, the pusher and the person seated on the wheelchair. 为建立基准，我们在MMDetection框架下实现了七个目标检测模型（Faster R-CNN、CenterNet、YOLOX、DETR、Deformable DETR、DINO和RT-DETR）和三个跟踪算法（ByteTrack、BOT-SORT和OC-SORT）。实验结果显示，YOLOX、Deformable DETR和Faster R-CNN取得了最佳检测性能，而三个跟�器之间的差异相对较小。PMMA数据集已公开available at https://doi.org/10.5683/SP3/XJPQUG，视频处理和模型训练代码也available at https://github.com/DatasetPMMA/PMMA。
关键词
引用
@article{arxiv.2602.10259,
title = {PMMA: The Polytechnique Montreal Mobility Aids Dataset},
author = {Qingwu Liu and Nicolas Saunier and Guillaume-Alexandre Bilodeau},
journal= {arXiv preprint arXiv:2602.10259},
year = {2026}
}
备注
Submitted to the journal IEEE Open Journal Intelligent Transportation Systems, under review