The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-1/W1
https://doi.org/10.5194/isprs-archives-XLII-1-W1-643-2017
https://doi.org/10.5194/isprs-archives-XLII-1-W1-643-2017
31 May 2017
 | 31 May 2017

COMPACT AND HYBRID FEATURE DESCRIPTION FOR BUILDING EXTRACTION

Z. Li, Y. Liu, Y. Hu, P. Li, and Y. Ding

Keywords: Building Extraction, Machine Learning, Local Feature, Descriptor, Binary Uniformity Tests, Binary Random Trees, Superpixel segmentation

Abstract. Building extraction in aerial orthophotos is crucial for various applications. Currently, deep learning has been shown to be successful in addressing building extraction with high accuracy and high robustness. However, quite a large number of samples is required in training a classifier when using deep learning model. In order to realize accurate and semi-interactive labelling, the performance of feature description is crucial, as it has significant effect on the accuracy of classification. In this paper, we bring forward a compact and hybrid feature description method, in order to guarantees desirable classification accuracy of the corners on the building roof contours. The proposed descriptor is a hybrid description of an image patch constructed from 4 sets of binary intensity tests. Experiments show that benefiting from binary description and making full use of color channels, this descriptor is not only computationally frugal, but also accurate than SURF for building extraction.