Fusarium Head Blight (FHB) is a wheat and barley disease, that results in huge yield and quality loss which reflect direct in the whole economy because it is a strategic importance.  Many Fusarium species produce mycotoxins fungal chemicals that are harmful to human and animals.

Rank the level of infection on develop lines by breeders needs expertise and the process is a time consuming and labour intensive. Chemical controls in a late stage, provide partial control of FHB and associated mycotoxin contamination. Several foliar fungicides have been used to manage FHB in some areas and are applied around the period of wheat flowering. To solve this issue, there are two ways: first by developing resistive lines by breeders for contamination control. And second, early detection will make the use of chemicals to be more effective and feasible.

The advancements in both Artificial Intelligence (AI) and image processing now (literally) will change the picture for farmers. The amount of image processing applications in precise agriculture is growing steadily with the availability of higher-quality measurements coupled with modern algorithms and increased possibility to fuse multiple sources of information from satellite imagery and sensors positioned in fields. Utilising such technology for early detecting disease like the FHB in wheat and barley will make a revolution change.

The Objectives was to create and develop an intelligent 360° Deep Scanning Capturing System, then calibrate the scanner system to capture images at specific angle with a synchronised traveling speed, then collect the photos that have been captured to create a Deep Convolutional Neural Network (DCNN) data set to train the AI robot for detecting the FHB early stages. As a result, a scanning cart has been designed and constructed in SDSU fabrication shop by Precision Ag team, and the Photos have been captured to create the data set. Then DCNN is being used in the training stage to detect the targeted locations in the infected areas.

ACKNOWLEDGEMENT AND DISCLAIMER

Confidential- please do not share the content of the submission publicly before the 2022 National FHB Forum. This material is based upon work supported by the U.S. Department of Agriculture, under Agreement, 59-0206-2-143, 59-0206-2-153, and FY-SP-002. This is a cooperative project with the U.S. Wheat & Barley Scab Initiative. Any opinions, findings, conclusions, or recommendations expressed in this publication are those of the author(s) and do not necessarily reflect the view of the U.S. Department of Agriculture.