A system to detect houses and residential street networks in multispectral satellite images

  • Authors:
  • Cem Ünsalan;Kim L. Boyer

  • Affiliations:
  • Signal Analysis and Machine Perception Laboratory, Department of Electrical Engineering, The Ohio State University, Columbus, OH;Signal Analysis and Machine Perception Laboratory, Department of Electrical Engineering, The Ohio State University, Columbus, OH

  • Venue:
  • Computer Vision and Image Understanding
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Maps are vital tools for most government agencies and consumers. However, their manual generation and updating is tedious, time consuming, and expensive. To address these concerns, we are developing automated techniques. In this paper, we restrict our attention to residential regions. These regions provide a challenge, testing the current limits of automated image analysis. Such regions are also typically areas of rapid growth and development and, therefore, are of interest from the applications perspective. In previous studies, we introduced statistical measures to extract these kinds of regions from satellite images [in: Proceedings of the International Conference on Pattern Recognition, vol. 1, 2002, p. 127, IEEE Trans. GeoRS (2003), IEEE Trans. PAMI]. As the next step toward automatic map generation, here we introduce a novel system to detect houses and street networks in IKONOS multispectral images. These images have one meter panchromatic resolution with 4 m resolution in the spectral bands. Our system consists of four major components: multispectral analysis to detect cultural activity, segmentation of regions of possible human activity (based on the surface material), decomposition of the segmented images, and graph theoretical algorithms over the decompositions to extract the street network and to detect houses. We tested our system on a large and diverse data set. Our results indicate the usefulness of our system in detecting houses and street networks, hence generating automated maps.