Research on the method of workpieces recognition and pose estimation in scattered scene

Jie Zhang; Tao Jiang

doi:10.1117/12.2688874

18 July 2023 Research on the method of workpieces recognition and pose estimation in scattered scene

Jie Zhang, Tao Jiang

Proceedings Volume 12744, Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023); 1274429 (2023) https://doi.org/10.1117/12.2688874
Event: Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023), 2023, Nanjing, China

Abstract

In order to solve the problem of recognition and pose estimation of scattered workpieces with similar product shapes in industrial sorting scene, a method combining the improved YOLOv5 workpieces target detection algorithm and 3D point cloud pose estimation algorithm was proposed. RGB images and depth maps were obtained by D435i sensor, and the workpieces in the scattered scene were identified by target detection. The mask of a single workpieces was obtained, the local 3D point cloud was reconstructed through the mask and the aligned depth map, and the pose estimation of the workpieces was carried out by combining the point cloud registration method. The results show that the system can realize the real-time recognition and pose estimation of the workpieces in the industrial scene and meet the industrial requirements.

Citation Download Citation

Jie Zhang and Tao Jiang "Research on the method of workpieces recognition and pose estimation in scattered scene", Proc. SPIE 12744, Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023), 1274429 (18 July 2023); https://doi.org/10.1117/12.2688874

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available