Computer Optics · 2013 · 21 citations · 0 references
ComputingComputer ScienceComputer VisionGeometryMachine VisionFeature DescriptionObject DetectionObject RecognitionShape AnalysisTraffic Sign RecognitionVisual LocalizationContour DetectionObject LocalizationScale-invariant Feature DetectionTraffic Sign DetectionTraffic Sign Detection In ImagesTraffic Sign LocalizationTraffic Sign TrackingVisual Object Localization
This paper considers the problem of localization of objects in images, when the scale of the sought for object is different from the scale of the sample object. We use the feature of the Hough transform to form the response in the shape of lines in the accumulator space; these lines correspond to the straight-line sections of the object’s contour. The paper contains the results of the formation of the responses in the accumulator space for some simple geometric figures. We introduce the technology of traffic signs localization, based on the considered approach.