Next Article in Journal
Classification Endmember Selection with Multi-Temporal Hyperspectral Data
Previous Article in Journal
Game Control Methods Comparison when Avoiding Collisions with Multiple Objects Using Radar Remote Sensing
Open AccessArticle

Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net

by Zhuokun Pan 1,2,3, Jiashu Xu 4, Yubin Guo 4,*, Yueming Hu 1,5,6,7 and Guangxing Wang 3
1
College of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, China
2
Guangdong Youyuan Land Information Technology Co., Ltd, Guangzhou 510642, China
3
School of Earth Systems and Sustainability, Southern Illinois University, Carbondale, IL 62901, USA
4
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
5
Guangdong Provincial Key Laboratory of Land Use and Consolidation, Guangzhou 510642, China
6
Guangdong Provincial Land Information Engineering Research Center, Guangzhou 510642, China
7
Guangzhou South China Research Institute of Natural Resource Science and Technology, Guangzhou 510640, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(10), 1574; https://doi.org/10.3390/rs12101574
Received: 8 April 2020 / Revised: 11 May 2020 / Accepted: 12 May 2020 / Published: 15 May 2020
Unplanned urban settlements exist worldwide. The geospatial information of these areas is critical for urban management and reconstruction planning but usually unavailable. Automatically characterizing individual buildings in the unplanned urban village using remote sensing imagery is very challenging due to complex landscapes and high-density settlements. The newly emerging deep learning method provides the potential to characterize individual buildings in a complex urban village. This study proposed an urban village mapping paradigm based on U-net deep learning architecture. The study area is located in Guangzhou City, China. The Worldview satellite image with eight pan-sharpened bands at a 0.5-m spatial resolution and building boundary vector file were used as research purposes. There are ten sites of the urban villages included in this scene of the Worldview image. The deep neural network model was trained and tested based on the selected six and four sites of the urban village, respectively. Models for building segmentation and classification were both trained and tested. The results indicated that the U-net model reached overall accuracy over 86% for building segmentation and over 83% for the classification. The F1-score ranged from 0.9 to 0.98 for the segmentation, and from 0.63 to 0.88 for the classification. The Interaction over Union reached over 90% for the segmentation and 86% for the classification. The superiority of the deep learning method has been demonstrated through comparison with Random Forest and object-based image analysis. This study fully showed the feasibility, efficiency, and potential of the deep learning in delineating individual buildings in the high-density urban village. More importantly, this study implied that through deep learning methods, mapping unplanned urban settlements could further characterize individual buildings with considerable accuracy. View Full-Text
Keywords: deep learning; urban village settlement; Worldview imagery; U-net; segmentation; Guangzhou deep learning; urban village settlement; Worldview imagery; U-net; segmentation; Guangzhou
Show Figures

Graphical abstract

MDPI and ACS Style

Pan, Z.; Xu, J.; Guo, Y.; Hu, Y.; Wang, G. Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net. Remote Sens. 2020, 12, 1574.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop