PhD student Aanis Ahmad wins ITSC Paper Award
A paper led by a PhD student in Purdue University’s School of Electrical and Computer Engineering has received an award from the American Society of Agricultural and Biological Engineers (ASABE). Aanis Ahmad was lead author on the paper, titled “Comparison of Deep Learning Models for Corn Disease Identification, Tracking, and Severity Estimation Using Images Acquired From UAV-Mounted and Handheld Sensors,” which won a 2021 Information Technology, Sensors, and Control Systems (ITSC) Paper Award.
The paper examines how accurately locating disease outbreak sites in corn fields is a first step in developing an effective disease management system. Such a system will lead to accurate disease identification and track the extent of severity estimation. The study is based on images taken by a Unmanned Aerial Vehicle (UAV) and handheld sensor from actual corn fields located at Purdue‘s Agronomy Center for Research and Education (ACRE) in summer 2020. A total of 55 UAV flights were conducted over a roughly three month period over three different corn fields, resulting in a collection of approximately 59,000 images. The disease severity levels of Northern Leaf Spot (NLS) was estimated with accuracies up to 94.02% by using a total of 1,200 handheld images that were acquired at severity levels corresponding to low, medium, and high. Finally, an object-detection algorithm, YOLOv4, was used for identifying and locating multiple instances of disease lesions within the Northern Leaf Blight (NLB), Gray Leaf Spot (GLS), and NLS handheld images with a mean Average Precision (mAP) score of 57.93%. This study presents details about four elements of a disease management system and provides promising results for realizing a working system.
Ahmad is a student of ECE Prof. Aly El Gamal. Co-authors on the paper are Prof. Dharmendra Saraswat from Purdue’s School of Agricultural and Biological Engineering and Prof. Gurmukh Johal from Purdue’s College of Agriculture. The Information Technology, Sensors, and Control Systems (ITSC) Technical Community judges select the top papers from the ITSC community that will be presented at the annual international meeting (AIM) each year.