Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model
AbstractLand cover classification is the most important element of land cover mapping and is a key input to many societal benefits. Traditional classification methods require a large amount of remotely sensed images, which are time consuming and labour intensive. Recently, crowdsourcing geographic information (CGI), including geo-tagged photos and other sources, has been widely used with lower costs, but still requires extensive labour for data classification. Alternatively, CGI textual information is available from online sources containing land cover information, and it provides a useful source for land cover classification. However, the major challenge of utilising CGI is its uneven spatial distributions in land cover regions, leading to less reliability of regions for land cover classification with sparsely distributed CGI. Moreover, classifying various unorganised CGI texts automatically in each land cover region is another challenge. This paper investigates a faster and more automated method that does not require remotely sensed images for land cover classification. Spatial clustering is employed for CGI to reduce the effect of uneven spatial distributions by extracting land cover regions with high density of CGI. To classify unorganised various CGI texts in each extracted region, land cover topics are calculated using topic model. As a case study, we applied this method using points of interest (POIs) as CGI to classify land cover in Shandong province. The classification result using our proposed method achieved an overall accuracy of approximately 80%, providing evidence that CGI with textual information has a great potential for land cover classification. View Full-Text
Scifeed alert for new publicationsNever miss any articles matching your research from any publisher
- Get alerts for new papers matching your research
- Find out the new papers from selected authors
- Updated daily for 49'000+ journals and 6000+ publishers
- Define your Scifeed now
Xing, H.; Meng, Y.; Hou, D.; Song, J.; Xu, H. Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model. Remote Sens. 2017, 9, 602.
Xing H, Meng Y, Hou D, Song J, Xu H. Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model. Remote Sensing. 2017; 9(6):602.Chicago/Turabian Style
Xing, Hanfa; Meng, Yuan; Hou, Dongyang; Song, Jie; Xu, Haibin. 2017. "Employing Crowdsourced Geographic Information to Classify Land Cover with Spatial Clustering and Topic Model." Remote Sens. 9, no. 6: 602.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.