Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract. Round cotton modules are increasingly popular because they improve harvest efficiency and reduce harvest costs by eliminating extra machines and operators. Farmers and ginners still face challenges in collecting each module's information for high-quality cotton production. A single board-computer-based portable system was developed to collect necessary details (handling route, moisture content, temperature, wrap damage status) during the handling of the round modules. A convolutional neural network (CNN) model was also trained to detect the cover damage of the round cotton modules captured by the system. During the field test, it was determined that only 28% to 32% of the total handling time was used for the active handling of the modules. Hence there has scope to increase the handling efficiency by optimizing the handling time. The cover damage detection accuracy of the model was 73% which needs to be improved by training the model with more images. However, the successful implementation of the system will help improve the handling efficiency of the modules and produce contamination-free high-quality cotton.