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. Brassica oleracea (B. oleracea) is a plant species including many important vegetables such as broccoli, cauliflower, and cabbage. However, these vegetables can only be produced during spring or fall time in Georgia, to avoid strong heat in summer time. Increasing heat tolerance of B. oleracea would extend the growing season, and reduce economic losses due to climate changes. The goal of this study was to develop and evaluate an approach based on deep learning and thermal imaging to measure plant temperature in the field. Thermal images were collected using a high throughput phenotyping system (GPhenoVision), and 60 thermal images were manually labeled at the pixel level. Mask RCNN and a thresholding based approach were proposed for plant localization, segmentation, and temperature extraction. The 60 labeled thermal images were randomly split into two subsets: 50 images for training and 10 for testing. Experiments showed that Mask RCNN outperformed the thresholding approach for all tasks, resulting in a significant improvement on the accuracy of extracted plant temperatures. This improvement dramatically reduced the variations due to sensor measurements, which is particularly important for successive biological analyses. Therefore, the proposed deep learning and thermal imaging based approach is an accuracy and effective tool for measuring plant temperature in the field, which could advance breeding programs and genetics studies of heat-tolerant genotypes.