Abstract
With the invention of Microsoft Kinect sensor, 3D object recognition has become an important task in computer vision research in recent years. The Viewpoint Feature Histogram (VFH) is a Point Cloud Library (PCL) descriptor that encodes only geometry and viewpoint of 3D point cloud data. In this paper, we propose a new approach to representing and learning 3D point cloud classes. First, we develop a new descriptor called VFH-Color that combines the original version of VFH descriptor with the color quantization histogram, thus adding the appearance information that would improve the recognition rate. Then, we use those features for training deep learning algorithm called Deep Belief Network (DBN). We have also tested our approach on Washington RGBD dataset and have obtained highly promising results.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
