Laser intelligent bag breaking of household waste based on deep learning

Qi Lan; Guangfeng Shi

doi:10.1117/12.3039385

4 September 2024 Laser intelligent bag breaking of household waste based on deep learning

Qi Lan, Guangfeng Shi

Proceedings Volume 13259, International Conference on Automation Control, Algorithm, and Intelligent Bionics (ACAIB 2024); 1325948 (2024) https://doi.org/10.1117/12.3039385
Event: Fourth International Conference on Automation Control, Algorithm, and Intelligent Bionics (ICAIB 2024), 2024, Yinchuan, China

Abstract

In order to realize the domestic waste recycling and processing industry chain highly intelligent, automated garbage bag breaking. An improved DeeplabV3+ network model is proposed for garbage bag bag recognition and bag breaking by laser. The experiment uses binocular camera to calculate the depth information and position coordinates of the garbage bag body, the laser is adjusted to the path according to the positioning coordinates of the garbage bag body, and the parameter optimization design is carried out using fiber laser marking machine. The experimental results show that the improved Deeplabv3+ model in this paper has an average pixel accuracy of 95.95%, an average intersection and merger ratio of 88.66%, and a checking rate of 92.23%; and that the height estimation by binocular camera is able to satisfy the adjustment of laser out-of-focus amount. The results show that the improved model is able to realize the segmentation of garbage bag body and complex background, and the laser bag breaking is sufficient to meet the demand in the garbage disposal production line.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Qi Lan and Guangfeng Shi "Laser intelligent bag breaking of household waste based on deep learning", Proc. SPIE 13259, International Conference on Automation Control, Algorithm, and Intelligent Bionics (ACAIB 2024), 1325948 (4 September 2024); https://doi.org/10.1117/12.3039385

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