构建首个面向移动辅具使用者的行人检测数据集，助力智能交通安全
PMMA: The Polytechnique Montreal Mobility Aids Dataset
- 采集户外真实场景下9类使用辅具行人数据，涵盖轮椅、拐杖、助行器等
- YOLOX、可变形DETR和Faster R-CNN在检测任务中表现最佳，平均精度超75%
- 开源数据与代码，适合自动驾驶、智能监控领域研究者使用
本研究提出一个新的行人检测数据集PMMA，聚焦使用移动辅具的行人。数据在室外环境采集，志愿者使用轮椅、拐杖和助行器，共包含九类行人：普通行人、拐杖使用者、两类助行器使用者（行走或静止）、五类轮椅使用者（包括空载、推空轮椅、三类载人轮椅，以及推轮椅者与被推者）。为建立基准，采用七种目标检测模型（Faster R-CNN、CenterNet、YOLOX、DETR、可变形DETR、DINO、RT-DETR）与三种跟踪算法（ByteTrack、BOT-SORT、OC-SORT），基于MMDetection框架进行实验。结果显示，YOLOX、可变形DETR和Faster R-CNN检测性能最优，三类跟踪器差异较小。PMMA数据集公开于https://doi.org/10.5683/SP3/XJPQUG，视频处理与模型训练代码见https://github.com/DatasetPMMA/PMMA。
原文摘要 · Abstract (English)
This study introduces a new object detection dataset of pedestrians using mobility aids, named PMMA. The dataset was collected in an outdoor environment, where volunteers used wheelchairs, canes, and walkers, 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. To establish a benchmark, seven object detection models (Faster R-CNN, CenterNet, YOLOX, DETR, Deformable DETR, DINO, and RT-DETR) and three tracking algorithms (ByteTrack, BOT-SORT, and OC-SORT) were implemented under the MMDetection framework. Experimental results show that YOLOX, Deformable DETR, and Faster R-CNN achieve the best detection performance, while the differences among the three trackers are relatively small. The PMMA dataset is publicly available at https://doi.org/10.5683/SP3/XJPQUG, and the video processing and model training code is available at https://github.com/DatasetPMMA/PMMA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。