通过深度学习评估公共开放空间的利用率：以底特律河岸开放空间研究为例

hi，大家好~我是shadow，一枚设计师/全栈工程师/算法研究员，目前主要研究方向是人工智能写作和人工智能设计，当然偶尔也会跨界到人工智能艺术及其他各种AI产品。这是我发在《人工智能Mix》的一篇论文阅读笔记。

文末了解《人工智能Mix》 

Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront

通过深度学习评估公共开放空间的利用率：以底特律河岸开放空间研究为例

体育活动和社交活动是确保健康生活方式的基本活动。公园、广场和绿道等公共开放空间（Public open spaces ，POS）是进行这些活动的关键环境。为了评估POS，需要研究人类如何使用POS中的设备。然而，研究POS使用率的传统方法是手工、耗费时间和人力的，往往也只定性研究。

因此，利用监控摄像机采集的画面，通过计算机视觉提取用户的相关信息是一个重要的研究课题。

- POC概念验证

该论文提出了一个概念验证，使用深度学习计算机视觉框架（主要是Mask R-CNN），用于定量评估POS中的人类活动，并以底特律河滨保护区（DRFC）为例，对提出的框架进行了实例研究。

- 数据集

本文还构建了一个数据集 “Objects in Public Open Spaces” (OPOS)，该数据集包含了从18个摄像机采集的7826幅在不同照明条件下穿过DRFC停车场的带标注的图像。

- 应用

该框架自动生成行为地图以定位不同的POS用户：

原文摘要

Physical activities and social interactions are essential activities that ensure a healthy lifestyle. Public open spaces (POS), such as parks, plazas and greenways, are key en- vironments that encourage those activities. To evaluate a POS, there is a need to study how humans use the facilities within it. However, traditional approaches to studying use of POS are manual and therefore time and labor intensive. They also may only provide qualitative insights.

It is ap- pealing to make use of surveillance cameras and to extract user-related information through computer vision.

This pa- per proposes a proof-of-concept deep learning computer vision framework for measuring human activities quanti- tatively in POS and demonstrates a case study of the pro- posed framework using the Detroit Riverfront Conservancy (DRFC) surveillance camera network.

A custom image dataset is presented to train the framework; the dataset in- cludes 7826 fully annotated images collected from 18 cam- eras across the DRFC park space under various illumina- tion conditions. Dataset analysis is also provided as well as a baseline model for one-step user localization and activ- ity recognition. The mAP results are 77.5% for pedestrian detection and 81.6% for cyclist detection. Behavioral maps are autonomously generated by the framework to locate dif- ferent POS users and the average error for behavioral lo- calization is within 10 cm.

---

更多相关内容，欢迎在专栏《人工智能MIX》中讨论。

mixlab开设的专栏

欢迎加入