Skip to main content
ARS Home » Plains Area » Lubbock, Texas » Cropping Systems Research Laboratory » Cotton Production and Processing Research » Research » Research Project #441455

Research Project: Color and Lighting Independent Plastic Contamination Detection Via Adaptive Image Processing

Location: Cotton Production and Processing Research

Project Number: 3096-21410-009-013-R
Project Type: Reimbursable Cooperative Agreement

Start Date: Jan 1, 2022
End Date: Dec 31, 2022

The global objective of the proposed research is to assess the best method for detecting plastic contamination at the gin-stand feeder apron and in the field. The specific objectives is to develop adaptive translation tracking algorithms that are immune to variations in ambient lighting and able to detect colored plastics that have the same colors as cotton constituents; such as white plastic against a background of white cotton. The Primary Objectives in this years research will be to 1) Write code and port the lighting independent algorithms, identified by this years research effort, 2) test the efficacy of the lighting independent algorithms that were identified by the authors in this year's research effort.

The incumbents have developed several promising classification algorithms that are immune to variation in lighting differences. The developed algorithms will be tested under various conditions for classification with a focus on deployment in the gin and onto a cotton harvester. This will require coding algorithms onto embedded processors for use in real-time, low-lag, high-speed image object-detection and plastic contamination classification. The high speed classification constraints, for the algorithms, will be driven by the difficulty in seeing plastic contaminants on the cotton plants at 20 to 30 ft in front of the harvester that when coupled with forward speed of the harvester constrains the type of algorithms, and image processing hardware, to only the most expedient in order to satisfy these high-speed real-time constraints. Once the classification algorithms have been converted to a suitable real-time platform; verification testing will be conducted in the gin to assess efficacy of detection, under structured lighting, and the later, time permitting with COVID constraints, tests will also be conducted under field conditions with widely varying lighting brightness and natural variation in color temperature (sunrise, noon, sunset, shadows, overcast).