Parcel based urban land use mapping-- based on PLPSOM framework
Topics: Land Use
, Remote Sensing
, Urban Geography
Keywords: Remote sensing, land use
Session Type: Virtual Paper Abstract
Day: Saturday
Session Start / End Time: 2/26/2022 11:20 AM (Eastern Time (US & Canada)) - 2/26/2022 12:40 PM (Eastern Time (US & Canada))
Room: Virtual 15
Authors:
Weishan Bai, University at Buffalo, Department of Geography
Le Wang, University at Buffalo, Department of Geography
,
,
,
,
,
,
,
,
Abstract
Abstract: With the rapid growth of urbanization, urban environmental problems have received worldwide attention during the past few decades. To solve those problems, reliable urban land use maps are essential because the spatial distribution of land use reflects the complex environment of cities under the combined effects of nature and socioeconomics. To make urban land-use maps with less time-consuming sample production, more transferability and universality, open-source data was using, and point-line-polygon semantic object mapping (PLPSOM) framework was proposed. The PLPSOM framework utilizes open-source data (VHR images and VGI data) and use enhanced deep adaptation network (EDAN) scene classification model to obtain the training sample from remote sensing images and use a rule-based category mapping (RCM) model to determine the land-use category systems. However, in previously studies, two potential impact factors of this framework have not been
determined:1) the number of categories of VGI data from which the point semantic object’s attributes are inherited from.2) the ratio of VGI data to VHR images in land parcel scale. In this study, the effect of those potential impact factor will be tested and the methods to improve the PLPSOM framework’s performance of the PLPSOM framework will be proposed and the VHR images, POI’s data and social media data will be used as VGI data.
Parcel based urban land use mapping-- based on PLPSOM framework
Category
Virtual Paper Abstract
Description
This abstract is part of a session. Click here to view the session.
| Slides