Mapping built environments from UAV imagery: a tutorial on mixed methods of deep learning and GIS

被引:5
作者
Hong, Xin [1 ]
Sheridan, Scott [2 ]
Li, Dong [3 ]
机构
[1] Koc Univ, Res Ctr Anatolian Civilizat, Istiklal Cd 181, TR-34433 Istanbul, Turkey
[2] Kent State Univ, Dept Geog, Kent, OH 44242 USA
[3] Kent State Univ, Dept Comp Sci, Kent, OH 44242 USA
来源
COMPUTATIONAL URBAN SCIENCE | 2022年 / 2卷 / 01期
关键词
Deep learning; GIS; UAV mapping; Greenspace; Sidewalks; Image segmentation; WALKABILITY;
D O I
10.1007/s43762-022-00039-w
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Evidence has suggested that built environments are significantly associated with residents' health and the conditions of built environments vary between neighborhoods. Recently, there have been remarkable technological advancements in using deep learning to detect built environments on fine spatial scale remotely sensed images. However, integrating the extracted built environment information by deep learning with geographic information systems (GIS) is still rare in existing literature. This method paper presents how we harnessed deep leaning techniques to extract built environments and then further utilized the extracted information as input data for analysis and visualization in a GIS environment. Informative guidelines on data collection with an unmanned aerial vehicle (UAV), greenspace extraction using a deep learning model (specifically U-Net for image segmentation), and mapping spatial distributions of greenspace and sidewalks in a GIS environment are offered. The novelty of this paper lies in the integration of deep learning into the GIS decision-making system to identify the spatial distribution of built environments at the neighborhood scale.
引用
收藏
页数:15
相关论文
共 53 条
[1]   Learning to extract buildings from ultra-high-resolution drone images and noisy labels [J].
Ahmed, Nahian ;
Bin Mahbub, Riasad ;
Rahman, Rashedur M. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2020, 41 (21) :8216-8237
[2]   Predicting COVID-19 Incidence Through Analysis of Google Trends Data in Iran: Data Mining and Deep Learning Pilot Study [J].
Ayyoubzadeh, Seyed Mohammad ;
Ayyoubzadeh, Seyed Mehdi ;
Zahedi, Hoda ;
Ahmadi, Mahnaz ;
Kalhori, Sharareh R. Niakan .
JMIR PUBLIC HEALTH AND SURVEILLANCE, 2020, 6 (02) :192-198
[3]  
Belloni V., 2020, ISPRS - Int Arch Photogramm Remote Sens Spat Inf Sci, VXLIII-B4-2020, P741, DOI DOI 10.5194/ISPRS-ARCHIVES-XLIII-B4-2020-741-2020
[4]   YOLACT Real-time Instance Segmentation [J].
Bolya, Daniel ;
Zhou, Chong ;
Xiao, Fanyi ;
Lee, Yong Jae .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :9156-9165
[5]  
Brown HE, 2013, NCA REGION INPUT REP, P312, DOI 10.5822/978-1-61091-484-0_15
[6]  
Brownlee J., 2019, Machine Learning Mastery, P1
[7]   Integrating Aerial and Street View Images for Urban Land Use Classification [J].
Cao, Rui ;
Zhu, Jiasong ;
Tu, Wei ;
Li, Qingquan ;
Cao, Jinzhou ;
Liu, Bozhi ;
Zhang, Qian ;
Qiu, Guoping .
REMOTE SENSING, 2018, 10 (10)
[8]   Walk Score™ As a Global Estimate of Neighborhood Walkability [J].
Carr, Lucas J. ;
Dunsiger, Shira I. ;
Marcus, Bess H. .
AMERICAN JOURNAL OF PREVENTIVE MEDICINE, 2010, 39 (05) :460-463
[9]  
Centers for Disease Control and Prevention, 2016, Impact of the built environment on health
[10]  
Chang Kang-TSUNG., 2018, INTRO GEOGRAPHIC INF, V9th