Skip to Main Content
In this paper, we discuss an object recognition and tracking system that utilizes the depth information from a low-cost depth sensor. Conventional object recognition methods that utilize RGB cameras are unable to accurately identify objects in the real world since they do not take into consideration the shape and three-dimensional characteristics of the object. Another major factor determining the accuracy of recognition is the lighting conditions and object pose at the time of recognition. We discuss an approach making use of the depth information and 3d properties of objects inorder to accurately identify them independent of lighting conditions.