Abstract:
Disclosed herein is an apparatus for detecting an obstacle for an around view monitoring system including a processor configured to store a plurality of images captured through an imaging device, convert a view of the images, generate a plurality of view conversion images corresponding to the images, compare the view conversion images corresponding to a plurality of images captured at a different time interval, extract a plurality of overlapping areas between the view conversion images, calculate a degree of mismatch of the overlapping areas between the view conversion images, detect a mismatch area in the overlapping areas, classify the mismatch area as an obstacle area, and display a position of the obstacle through a display of a vehicle.
Abstract:
A method for detecting a side of an object in an apparatus for detecting a side of an object within an image includes analyzing, by a boundary line detector, an input image to search a detection target region in which a target object is included, detecting, by the boundary line detector, a boundary line between the target object and a ground within the detection target region, calculating, by a side determiner, a gradient for the boundary line, and analyzing, by the side determiner, an image within the detection target region on the basis of the gradient to determine that the entirety of the detection target region is a region of the side of the target object or to determine a separated region corresponding to the side of the target object in the detection target region.
Abstract:
Disclosed herein is an apparatus for detecting an obstacle for an around view monitoring system including a processor configured to store a plurality of images captured through an imaging device, convert a view of the images, generate a plurality of view conversion images corresponding to the images, compare the view conversion images corresponding to a plurality of images captured at a different time interval, extract a plurality of overlapping areas between the view conversion images, calculate a degree of mismatch of the overlapping areas between the view conversion images, detect a mismatch area in the overlapping areas, classify the mismatch area as an obstacle area, and display a position of the obstacle through a display of a vehicle.