Shervin Ardeshir. Geo-semantic Segmentation

Geo-semantic Segmentation

Shervin Ardeshir1 Kofi Malcolm Collins-Sibley2 Mubarak Shah1

1 Center for Research in Computer Vision, University of Central Florida

2 Northeastern University

  文档链接

  来源 CVPR2015

  利用GIS中的3D模型信息“GIS database containing the building outlines”，和照片中的相机参数（EXIF参数），GPS等信息。将上述二者进行迭代fitting。最终正确分割图片。

  

  GIS Dataset available at: http://crcv.ucf.edu/projects/Geosemantic/

  相关参考文献：

  [1] M.-Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa. Entropy rate superpixel segmentation. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 2097–2104. IEEE, 2011.

    Segmenting the image into an initial set of superpixels.