Wheat crop productivity is susceptible to decrease from Fusarium head blight (FHB). To select a highly resistant cultivar, different wheat lines would be evaluated in a crop cycle. Shortages of field laborers for manual analysis of FHB severity is inspiring the design of more efficient assessment tools. A reliable phenocart with a high-throughput camera that works in different wheat crops to automatically determine the resistance of wheat lines to FHB would bring economic benefits to cereal production. In this study, Mask region convolutional neural network (Mask-RCNN) obtained acceptable results for detecting wheat FHB disease, yielding the overall rates of precision (P), recall (R), and F1-score of 72.10%, 76.16%, and 74.04%, respectively. The proposed method enabled the rapid recognitions of diseased wheat spikes with the detection rate of 98.81%. This study demonstrates the feasibility to rapidly determine the optimal wheat line from the field, which is of great significance for ensuring food safety and sustainable supply.
|Original language||English (US)|
|State||Published - 2020|
|Event||2020 ASABE Annual International Meeting - Virtual, Online|
Duration: Jul 13 2020 → Jul 15 2020
|Conference||2020 ASABE Annual International Meeting|
|Period||7/13/20 → 7/15/20|
Bibliographical noteFunding Information:
The authors would like to acknowledge the USDA-ARS U.S. Wheat and Barley Scab Initiative (Funding No. 58-5062-8-018) supported this research. The authors also would like to acknowledge An Min from University of Minnesota.
© ASABE 2020 Annual International Meeting.
- Deep learning
- Fusarium head blight
- Target recognition
- Wheat spike