The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIV-4/W3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-4/W3-2020, 151–158, 2020
https://doi.org/10.5194/isprs-archives-XLIV-4-W3-2020-151-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIV-4/W3-2020, 151–158, 2020
https://doi.org/10.5194/isprs-archives-XLIV-4-W3-2020-151-2020

  23 Nov 2020

23 Nov 2020

GEO-TAGGED IMAGE RETRIEVAL FROM MAPILLARY STREET IMAGES FOR A TARGET BUILDING

N. Çelik and E. Sümer N. Çelik and E. Sümer
  • Dept. of Computer Engineering, Baskent University, Ankara, Turkey

Keywords: Image Retrieval, Target Building, pre-trained Unet, Mapillary, street view images

Abstract. This study aims to investigate the possibility to automate the image selection process for the target building from Mapillary images through a web application where the user only initiates one image of the target building as a query. Using the data provided with Mapillary API and Overpass API, all images having full or partial coverage of the target building were selected. Then the images were segmented by using a pre-trained U-Net model to discard any images having less than 20% building coverage. The experiments showed promising results yielding 0.971 and 0.887 of overall accuracy after segmentation steps for two different target buildings.