IJBTT

UAV-Based Corn Health Recognition Model Using Enhanced Threshold-Based Segmentation and Template Matching for Corn Plantation

UAV-Based Corn Health Recognition Model Using Enhanced Threshold-Based Segmentation and Template Matching for Corn Plantation
	© 2025 by IJETT Journal
	Volume-73 Issue-7
	Year of Publication : 2025
	Author : Joel M. Gumiran
	DOI : 10.14445/22315381/IJETT-V73I7P140

How to Cite?
Joel M. Gumiran, "UAV-Based Corn Health Recognition Model Using Enhanced Threshold-Based Segmentation and Template Matching for Corn Plantation ," International Journal of Engineering Trends and Technology, vol. 73, no. 7, pp.522-530, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I7P140

Abstract
Phenotyping plays a vital role in assessing the health traits of a plant. However, the process can become tedious and labour-intensive, especially when applied in a wide range of applications. Hence, an Unmanned Aerial Vehicle or UAV has been utilized due to its user-friendliness, high-resolution capabilities, and cost-effectiveness. Despite their advantages, UAV phenotyping Segmentation faces several challenges that can hinder the segmentation process and negatively impact recognition accuracy. Thus, an Enhanced Threshold-based Segmentation technique has been implemented, normalising image luminosity and improving both segmentation and recognition accuracy. Additionally, template matching was employed during the recognition phase, achieving perfect correlation when the Normalized Cross-Correlation (NCC) equals 1. Following normalization of the images, recognition accuracy improved by 5.25 percent, reaching an impressive 98.07 percent recognition accuracy at a distance of 4 meters. This advancement allows for more precise identification of unhealthy leaves, providing significant benefits to farmers and agriculturists by reducing time, effort, and costs associated with crop management.

Keywords
Corn health recognition, Corn disease detection, Drone, Enhanced threshold-based segmentation, Phenotyping, Template matching, Unmanned Aerial Vehicle.

References
[1] Shrikrishna Kolhar, and Jayant Jagtap, “Plant Trait Estimation and Classification Studies in Plant Phenotyping Using Machine Vision - A Review,” Information Processing in Agriculture, vol. 10, no. 1, pp. 114-135, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] José Armando Fernández Gallego, “Image Processing Techniques for Plant Phenotyping Using RGB and Thermal Imagery = RGB and Thermal Image Processing Techniques as a Tool for Crop Phenotyping,” Doctoral Theses, University of Barcelona, 2019.
[Google Scholar] [Publisher Link]
[3] Lei Feng et al., “A Comprehensive Review on Recent Applications of Unmanned Aerial Vehicle Remote Sensing with Various Sensors for High-Throughput Plant Phenotyping,” Computers and Electronics in Agriculture, vol. 182, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Shrikrishna Ulhas Kolhar, and Jayant Jagtap, “Bibliometric Review on Image Based Plant Phenotyping,” Library Philosophy and Practice (E-Journal), pp. 1-16, 2021.
[Google Scholar] [Publisher Link]
[5] Mohd Shahrimie Mohd Asaari et al., “Analysis of Hyperspectral Images for Detection of Drought Stress and Recovery in Maize Plants in a High-Throughput Phenotyping Platform,” Computers and Electronics in Agriculture, vol. 162, pp. 749-758, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Lucas Prado Osco et al., “A Review on Deep Learning in UAV Remote Sensing,” International Journal of Applied Earth Observation and Geoinformation, vol. 102, pp. 1-21, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Eva Rosenqvist et al., “The Phenotyping Dilemma-The Challenges of a Diversified Phenotyping Community,” Frontiers in Plant Science, vol. 10, pp. 1-6, 2019.
[CrossRef] [Google Scholar] [Publisher Link]