Abstract
This paper proposes an object localization and segmentation method based on a small set of training images captured from a Kinect red-green-blue-depth (RGB-D) camera. The method consists of three stages. The first stage localizes candidate objects based on the hybrid color features of cluster-based pixel distribution and color entropy and a new fuzzy classifier (FC). In the second stage, the object candidates are then sent to another FC for filtering by using the color feature of entropies of color geometrical distributions. After the two-stage localization using the color features, the depth measurement from the Kinect is used to segment the shape of the object for final localization and shape segmentation. A histogram-based shape feature is used to filter the candidate objects from the first two stages. Experimental results show that good performance is achieved by using only a small set of training images..
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have