Rectangle detection based on a windowed Hough transform

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].…”

“…An approach for detection of rectangular contours based on the Hough transform was developed in [12]. The approach relies on certain strict geometrical rules making it not suitable for detection of fragmented or incomplete structures.…”

Real-time landing place assessment in man-made environments

“…In this section we introduce a notion of shape regularity and use it to segment polygonal regions from the image indicative of man-made landing sites. Many algorithms have been proposed for polygon detection in the literature, however, most of them are restricted to fairly simple polygonal shapes [30,1]. We provide a generic measure of shape regularity applicable for the detection of a variety of polygonal structures.…”

“…For runway detection we compare against the method of [30] that employs a windowed Hough transform for rectangular region detection, and is representative of the approaches that look for landable fields as rectangles. We will refer to it as WH.…”