BusStopCV: A Real-time AI Assistant for Labeling Bus Stop Accessibility Features in Streetscape Imagery

BusStopCV: A Real-time AI Assistant for Labeling Bus Stop Accessibility Features in Streetscape Imagery
复制标题

BusStopCV:实时人工智能助手,用于在街景图像中标记公交车站无障碍功能

DOI:
10.1145/3597638.3614481
复制
发表时间:
2023
期刊:
Proceedings of the 25th International ACM SIGACCESS Conference on Computers and Accessibility
影响因子:
--
通讯作者:
Chamberlain, Brent
Chamberlain, Brent
中科院分区:
--
文献类型:
--
作者:
Kulkarni, Minchu;Li, Chu;Ahn, Jaye Jungmin;Ma, Katrina Oi;Zhang, Zhihan;Saugstad, Michael;Wu, Kevin;Eisenberg, Yochai;Novack, Valerie;Chamberlain, Brent

文献摘要

参考文献

相似文献

公共交通为残疾人提供了至关重要的连接,方便他们获得工作、教育和医疗服务。虽然现代导航应用程序提供了一套关于公交选择的信息,包括公交车或火车到达的实时更新,但它们缺乏关于公交车站本身可达性的数据。公交车站的特征,如座位,庇护所和着陆区是至关重要的,但很少有城市提供这方面的信息。在这篇演示论文中,我们介绍了BusStopCV,这是一个Human+AI Web原型,用于使用实时计算机视觉和人类标记来可扩展地收集公交车站特征数据。我们描述了BusStopCV的设计,自定义培训与YOLOv8模型,并在华盛顿州西雅图随机选择的100个巴士站的评价。我们的研究结果证明了BusStopCV的潜力,并强调了未来工作的机会。
Public transportation provides vital connectivity to people with disabilities, facilitating access to work, education, and health services. While modern navigation applications provide a suite of information about transit options—including real-time updates about bus or train arrivals—they lack data about the accessibility of the transit stops themselves. Bus stop features such as seatings, shelters, and landing areas are critical, but few cities provide this information. In this demo paper, we introduce BusStopCV, a Human+AI web prototype for scalably collecting data on bus stop features using real-time computer vision and human labeling. We describe BusStopCV’s design, custom training with the YOLOv8 model, and an evaluation of 100 randomly selected bus stops in Seattle, WA. Our findings demonstrate the potential of BusStopCV and highlight opportunities for future work.
DOI: 10.3390/s120810678
发表时间: 2012
期刊: Sensors (Basel, Switzerland)
影响因子: --
作者:
Zhou H;Hou KM;Zuo D;Li J
通讯作者: Li J
DOI: 10.3390/ijerph19084548
发表时间: 2022-04-09
影响因子: --
作者:
Adams, Marc A.;Phillips, Christine B.;Patel, Akshar;Middel, Ariane
通讯作者: Middel, Ariane
迈向全球规模的人群人工智能技术,为残疾人绘制和评估人行道
DOI: --
发表时间: 2022
期刊: arXiv.org
影响因子: --
作者:
Maryam Hosseini;Michael Saugstad;Fábio Miranda;Andres Sevtsuk;Cláudio T. Silva;Jon E. Froehlich
通讯作者: Jon E. Froehlich
DOI: 10.5038/2375-0901.1.4.4
发表时间: 1997
期刊: The Journal of Public Transportation
影响因子: --
作者:
W. Sarasua;R. Awuah;Mark Fawley;C. Byars;J. Orton
通讯作者: J. Orton