Object Detection using General Landmark Regions

This paper describes a method for detecting and locating objects in images. The presented approach relies on finding general landmark candidates (glc) in an image. A glc is a closed region that can be either an object landmark (ol) or a non-object landmark (nol). The entire oVs are then grouped into object clusters (oc´s). Given a set of training images, the method builds a database of ol and nol regions and oc´s. When a query image is presented, we detect all of the ol´s and group them into oc candidates. These cluster candidates are then classified using the oc´s from the training database. This method can be used to detect and locate objects from images in many different unconstrained environments, such as detecting vehicles, speed signs, etc... The method is tested on two different cases and is shown to yield a high success rate