Mechanical CAD Parts Recognition for Industrial Automation
Object matching, counting and inspection are routine jobs done at several manufacturing plants, research laboratories, and other different companies. The detailed analysis of manufactured components is possible with information obtained from their inspect
- PDF / 388,479 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 64 Downloads / 187 Views
Abstract Object matching, counting and inspection are routine jobs done at several manufacturing plants, research laboratories, and other different companies. The detailed analysis of manufactured components is possible with information obtained from their inspection. For a large number of objects manual counting and inspection is a repetitive, difficult and time-taking process. The efficiency of overall object matching, counting and inspection process can be increased with industrial automation and it also minimizes resources and saves time. This paper presents a computationally efficient 3D computer vision based approach to recognize the Mechanical CAD parts. In this chapter features based industrial object detection techniques are implemented in MATLAB to recognize the presence of the industrial CAD parts in the query image.
1 Introduction Today in different types of product manufacturing industries (e.g., locks, gear boxes, alarm clocks, engines and motors, etc.) and packaging industries with large-scale production units automated assembly systems are widely used. They used mechanized devices such as image capturing unit, conveyor, part recognition unit, part feeder, part selection unit, and intelligent robots that follow fixed sequence of steps to assemble the product [1]. In general with respect to productivity there are three categories of assembly systems namely low, medium and high volume production units. The assemblies systems are fully automated in high volume production, assembly of parts in other two classes are performed in semi-automated or manual by hand. The cost for establishing such systems initially is high, but in longer run it saves time, money, J. Tushar (&) Meenu Mechanical Engineering Department, NIT Kurukshetra, Kurukshetra, India e-mail: [email protected] H.K. Sardana CSIO, Chandigarh, India © Springer Nature Singapore Pte Ltd. 2018 S.C. Satapathy et al. (eds.), Smart Computing and Informatics, Smart Innovation, Systems and Technologies 78, https://doi.org/10.1007/978-981-10-5547-8_35
341
342
J. Tushar et al.
Fig. 1 A schematic diagram for machine parts detection in model assembly line
and labor. The benefits of such system are huge quantity of production, stable product design with good quality and reliability. In automated assembly systems the machine parts identification is entirely different from simple object recognition; moreover the ability of human to differentiate between correct and no correct machine parts are better but it is a difficult task for a machine. In general with fast moving machine parts on conveyor manual defect detection by human inspectors are impractical also it is expensive, inaccurate, subjective, eye straining and other health issues to quality control inspectors. A computer vision based non-contact inspection technique is developed with image processing methods by considering these problems, for defect detection in industrial machine parts [2]. The present work will help the industrial robot used in assembly process and industrial inspection systems (F
Data Loading...
