Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data

Abstract

Urban zoning enables various applications in land use analysis and urban planning. As cities evolve, it is important to constantly update the zoning maps of cities to reflect urban pattern changes. This paper proposes a method for automatic urban zoning using higher-order Markov random fields (HO-MRF) built on multi-view imagery data including street-view photos and top-view satellite images. In the proposed HO-MRF, top-view satellite data is segmented via a multi-scale deep convolutional neural network (MS-CNN) and used in lower-order potentials. Street-view data with geo-tagged information is augmented in higher-order potentials. Various feature types for classifying street-view images were also investigated in our work. We evaluated the proposed method on a number of famous metropolises and provided in-depth analysis on technical issues.

Cite

Text

Feng et al. "Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01237-3_38

Markdown

[Feng et al. "Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/feng2018eccv-urban/) doi:10.1007/978-3-030-01237-3_38

BibTeX

@inproceedings{feng2018eccv-urban,
  title     = {{Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data}},
  author    = {Feng, Tian and Truong, Quang-Trung and Thanh Nguyen, Duc and Yu Koh, Jing and Yu, Lap-Fai and Binder, Alexander and Yeung, Sai-Kit},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01237-3_38},
  url       = {https://mlanthology.org/eccv/2018/feng2018eccv-urban/}
}