Skip to main content
ARS Home » Plains Area » Lubbock, Texas » Cropping Systems Research Laboratory » Cotton Production and Processing Research » Research » Publications at this Location » Publication #401156
Research Project: Enhancing the Profitability and Sustainability of Upland Cotton, Cottonseed, and Agricultural Byproducts through Improvements in Pre-Ginning, Ginning, and Post-Ginning Processes

Location: Cotton Production and Processing Research

Title: Cotton gin stand machine-vision inspection and removal system for plastic contamination: Auto-calibration design

Author
item Pelletier, Mathew
item Wanjura, John
item KOTHARI, NEHA - Cotton, Inc
item Holt, Gregory

Submitted to: AgriEngineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/23/2023
Publication Date: 7/14/2023
Citation: Pelletier, M.G., Wanjura, J.D., Kothari, N., Holt, G.A. 2023. Cotton gin stand machine-vision inspection and removal system for plastic contamination: Auto-calibration design. AgriEngineering. 3(3). https://doi.org/10.3390/agriengineering3030033.
DOI: https://doi.org/10.3390/agriengineering3030033

Interpretive Summary: The U.S. cotton industry is highly concerned with removing plastic contamination from cotton lint. A major source of this contamination is the plastic used to wrap cotton modules produced by John Deere round module harvesters. A machine-vision detection and removal system has been developed to address this problem, using low-cost color cameras to detect plastic in the cotton stream and remove it. However, the system requires a lot of calibration and is difficult for cotton gin workers to operate due to its reliance on low-cost computers. This research aims to make the system more user-friendly by adding an auto-calibration feature that can track cotton colors and avoid plastic images, reducing the need for skilled personnel to operate the system and making it easier for the cotton ginning industry to adopt.

Technical Abstract: The removal of plastic contamination from cotton lint is an issue of top priority to the U.S. cotton industry. One of the main sources of plastic contamination showing up in marketable cotton bales is the plastic used to wrap cotton modules produced by John Deere round module harvesters. Despite diligent efforts by cotton ginning personnel to remove all plastic encountered during module unwrapping, plastic still finds a way into the cotton gin’s processing system. To help mitigate plastic contamination at the gin, a machine-vision detection and removal system was developed that utilizes low-cost color cameras to see plastic coming down the gin-stand feeder apron, which upon detection, blows plastic out of the cotton stream to prevent contamination. As the system is comprised of 30-50 computers, it takes a great deal of effort to calibrate and tune the system for optimal performance. Further, as the system is developed around low-cost ARM computers running Linux, there is also a technology barrier for the typical cotton gin workers, to be able to effectively operate this equipment. This research seeks to eliminate this step, turning the system into more of a plug-and-play appliance. The key to this hands-off approach is the addition of an auto-calibration system that can dynamically track the cotton colors while avoiding plastic images that would impair the performance should any plastic images get utilized in the auto-calibration process. This paper presents the design for the autocalibration algorithm which is anticipated to greatly reduce the overhead in setup and ongoing use of the system. The addition of an auto-calibration function will reduce the need for skilled personnel to operate the system. It is anticipated that the addition of an autocalibration feature will streamline the adoption of the plastic removal system by the cotton ginning industry.