A Probabilistic Framework to Detect Buildings in Aerial and Satellite Images

Abstract

Detecting buildings from very high resolution (VHR) aerial and satellite images is extremely useful in map making, urban planning, and land use analysis. Although it is possible to manually locate buildings from these VHR images, this operation may not be robust and fast. Therefore, automated systems to detect buildings from VHR aerial and satellite images are needed. Unfortunately, such systems must cope with major problems. First, buildings have diverse characteristics, and their appearance (illumination, viewing angle, etc.) is uncontrolled in these images. Second, buildings in urban areas are generally dense and complex. It is hard to detect separate buildings from them. To overcome these difficulties, we propose a novel building detection method using local feature vectors and a probabilistic framework. We first introduce four different local feature vector extraction methods. Extracted local feature vectors serve as observations of the probability density function (pdf) to be estimated. Using a variable-kernel density estimation method, we estimate the corresponding pdf. In other words, we represent building locations (to be detected) in the image as joint random variables and estimate their pdf. Using the modes of the estimated density, as well as other probabilistic properties, we detect building locations in the image. We also introduce data and decision fusion methods based on our probabilistic framework to detect building locations. We pick certain crops of VHR panchromatic aerial and Ikonos satellite images to test our method. We assume that these crops are detected using our previous urban region detection method. Our test images are acquired by two different sensors, and they have different spatial resolutions. Also, buildings in these images have diverse characteristics. Therefore, we can test our methods on a diverse data set. Extensive tests indicate that our method can be used to automatically detect buildings in a robust and fast manner in Ikonos satellite and our aerial images.

Detection of incomplete enclosures of rectangular shape in remotely sensed images

“…We have also tested other methods for building detection (e.g. [31,12]) applied to detection of livestock enclosures. Unfortunately, these methods completely fail to detect the enclosures, preventing us from reporting the corresponding quantitative comparison.…”

“…Examples are detection of buildings in remotely sensed images [24,19,14,3,12,15,1,31,30,23,26], traffic signs [21,13,22], and particles of a rectangular shape in cryo-electron microscopy images [36,35]. The methods used were based on Markov Random Fields [15,21], Marked Point Processes [1,26], search on a graph [14,38], Hough Transform and other voting schemes [3,12,36,13,22], template matching [25], aggregation of local features [1,23,31], and heuristic rules [19].…”

“…In [31] a set of local features that carried local corner information were used to produce a probability map of building rooftops. Unfortunately, in the case of fragmented enclosures corners are not reliable features.…”

The Cartographic Concept of the Image Map

“…However, they have not dealt with the relationship between symbols and orthophotographs, especially orthoimages used as a topographic base. Similarly, remote sensing and digital image processing research is focused on information extraction (Alvarez et al 2008, Baltsavias 1996, Longbotham et al 2012, Sirmacek, Unsalan 2011) from images but orthoimage usage for cartographical purposes is rarely investigated.…”

Multidirectional Building Detection in Aerial Images Without Shape Templates

“…State-of-the-art methods can be divided into two main groups. The first group only localizes buildings without giving any shape information, like (Sirmaçek andÜnsalan, 2009) and (Sirmaçek andÜnsalan, 2011).…”