Automatic Building Detection with Polygonizing and Attribute Extraction from High-Resolution Images

ISPRS International Journal of Geo-Information

Samitha Daranagama¹  Apichon Witayangkurn² 

[1] Department of Information and Communication Technologies, School of Engineering and Technology, Asian Institute of Technology, Pathumthani 12120, Thailand;School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, Thailand;

关键词: deep learning;    building extraction;    UAV images;    aerial images;    semantic segmentation;    transfer learning;   

DOI  :  10.3390/ijgi10090606

来源: DOAJ

【 摘 要 】

Buildings can be introduced as a fundamental element for forming a city. Therefore, up-to-date building maps have become vital for many applications, including urban mapping and urban expansion analysis. With the development of deep learning, segmenting building footprints from high-resolution remote sensing imagery has become a subject of intense study. Here, a modified version of the U-Net architecture with a combination of pre- and post-processing techniques was developed to extract building footprints from high-resolution aerial imagery and unmanned aerial vehicle (UAV) imagery. Data pre-processing with the logarithmic correction image enhancing algorithm showed the most significant improvement in the building detection accuracy for aerial images; meanwhile, the CLAHE algorithm improved the most concerning UAV images. This study developed a post-processing technique using polygonizing and polygon smoothing called the Douglas–Peucker algorithm, which made the building output directly ready to use for different applications. The attribute information, land use data, and population count data were applied using two open datasets. In addition, the building area and perimeter of each building were calculated as geometric attributes.

【 授权许可】

Unknown