3D object classification based on deep belief networks and point clouds. (6th December 2019)

• Record Type: Journal Article
• Authors: Ouadiay, Fatima Zahra; Zrira, Nabila; Hannat, Mohamed; Bouyakhf, El Houssine; Himmi, Majid Mohamed
• Is Part Of: International journal of computational vision and robotics. Volume 9:Number 6(2019)
• Page Start: 527
• Page End: 558
• Publication Date: 2019-12-06
• Subjects: Kinect -- 3D object classification -- point cloud library -- PCL -- recognition threshold -- deep belief networks -- DBNs -- Washington RGB-D -- Robotic -- Computational Vision; Computer vision -- Periodicals; Robotics -- Periodicals; Artificial intelligence -- Periodicals; 006.3705
• Languages: English
• ISSNs: 1752-9131

Abstract

Since the discovery of 3D sensors such as Kinect camera, 3D object models, and point clouds become frequently used in many areas. The most important one is the 3D object recognition and classification in robotic applications. This type of sensors, like the human vision, allows generating the object model from a field of view or even a complete 3D object model by combining several individual Kinect frames. In this work, we propose a new feature learning-based object classification approach using point cloud library (PCL) detectors and descriptors and deep belief networks (DBNs). Before developing the classification approach, we evaluate 3D descriptors by proposing a new pipeline that uses the L2-distance and the recognition threshold. 3D descriptors are computed on different datasets, in order to achieve the best descriptors. Subsequently, these descriptors are used to learn robust features in the classification approach using DBNs. We evaluate the performance of these contributions on two datasets; Washington RGB-D and our real 3D object datasets. The results show that the proposed approach outperforms advanced methods by approximately 5% in terms of accuracy.