3D Shape Recognition Based on 1D Signal Processing for Real-Time Applications
- PDF / 1,421,526 Bytes
- 13 Pages / 612 x 792 pts (letter) Page_size
- 71 Downloads / 113 Views
3D Shape Recognition Based on 1D Signal Processing for Real-Time Applications K. Baibaia,*, K. Hachamia,**, M. Emharrafa,***, and B. Bellacha,**** a
LSE2I Laboratory, School of Applied Sciences Engineering, Mohamed I University, Oujda, Morocco * e-mail: [email protected] ** e-mail: [email protected] *** e-mail: [email protected] **** e-mail: [email protected]
Abstract—Nowadays, many researches are being carried out in the field of 3D object recognition. All developed 3D recognition approaches are based on 2D data processing (images) or 3D data (3D models), obtained through 3D reconstruction processes. The main disadvantages of these approaches, especially for real-time applications, are the processing and calculation complexity, which directly affects the recognition time response. In this paper, we propose a new approach for 3D shape recognition adapted to real time applications that is effective for many industrial applications such as: inspection and objects storing, which must be fast enough to satisfy the speed requirements of their application environment. It consists of 3D recognition based on 1D signals, resulting from projecting uncoded structured light lines on the surface of the object. Thereafter for each signal, a group of descriptors are calculated in order to recognize the 3D shape of the object using a classification system. Our approach has been evaluated on a dataset formed by descriptors of real 3D objects calculated from various view-points. The experimental results show that our approach attains an important classification accuracy (99.8%) and requires less than 1ms run-time. It offers an incomplex and clear methodology, and therefore a reduced computational time, since the processing is carried out directly on 1D signals without passing through the 3D model, which makes our system suitable for real time applications. Keywords: 3D shape recognition, real-time, classification, 1D signal, shape-based DOI: 10.1134/S1054661820030037
1. INTRODUCTION Real-time 3D object recognition is a very active research field, especially in recent years [1], those researches attempt to develop rapid and robust approaches. Many approaches have been proposed to preprocess 3D shapes in order to obtain the necessary input data, and it’s becoming more important in practical applications, which have been applied to several fields including robotics [2], multimedia games, medical diagnosis, and industrial applications such as: inspection [3] and objects storing. Industrial vision inspection plays an important role in achieving 100% quality control in production, reducing costs and ensuring a high level of customer satisfaction. Among the industrial machine vision inspection tasks: counting objects on a conveyer, sorting of objects and searching for defects surface. The existing 3D shape recognition approaches are mostly based on 2D-3D data processing (2D images) or 3D-3D data (point clouds). For 2D-3D approaches, the analysis of 3D data is done only from
Received February 4, 2019; revised Decembe
Data Loading...
