PMMA: The Polytechnique Montreal Mobility Aids Dataset

TL;DR

This paper introduces PMMA, a new outdoor pedestrian dataset with mobility aids, and benchmarks multiple detection and tracking models, providing a valuable resource for improving mobility aid detection.

Contribution

The creation of the PMMA dataset with diverse mobility aid categories and the benchmarking of seven detection models and three tracking algorithms.

Findings

YOLOX, Deformable DETR, and Faster R-CNN perform best among detection models.

Detection performance varies across models, but tracking differences are minor.

The dataset and code are publicly available for research use.

Abstract

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.