Automatic building detection and land-use classification in urban areas using multispectral high-spatial resolution imagery and LiDAR data

Abstract

Urban areas are important environments, accounting for approximately half the population of the world. Cities attract residents partly because they offer ample opportunities for development, which often results in urban sprawl and its complex environmental implications. It is therefore necessary to develop technologies and methodologies that permit monitoring the effects of various problems that have been or are thought to be associated with urban sprawl. These technologies would facilitate the adoption of policies seeking to minimize the negative effects of urban sprawl. Solutions require a precise knowledge of the urban environment under consideration to enable the development of more efficient urban zoning plans. The high dynamism of urban areas produces seemingly continuous alterations of land cover and use; consequently, cartographic information becomes quickly and is oftentimes outdated. Hence, the availability of detailed and up-to-date cartographic and geographic information is imperative for an adequate management and planning of urban areas. Usually the process of creating land-use/land-cover maps of urban areas involves field visits and classical photo-interpretation techniques employing aerial imagery. These methodologies are expensive, time consuming, and also subjective. Digital image processing techniques help reduce the volume of information that needs to be manually interpreted.