International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 05 | May 2025
p-ISSN: 2395-0072
www.irjet.net
UAV Image Processing For Soybean Detection Using MATLAB 1Sanika Chandgude, 2Tanvi Gund, 3Aishwarya Hanpude, 4Jagadish Hallur 1UG Student, Department of ENTC, SVERI’s College of Engineering, Pandharpur, PAHSUS, Maharashtra, India 2Assistant Professor, Department of E&TC, SVERI’s College of Engineering, Pandharpur, PAHSUS, Maharashtra,
India ------------------------------------------------------------------------***-----------------------------------------------------------------------Abstract. This paper presents an automated system for detecting and classifying soybean leaf diseases using UAV imagery and advanced image processing techniques. The system employs the SLIC algorithm for segmenting soybean leaf images into superpixels, followed by feature extraction and classification using deep learning models such as ResNet-50. MATLAB is used for image segmentation, dataset creation, and model training. The proposed system demonstrates high accuracy inidentifying diseases such as Frogeye Leaf Spot, Septoria Brown Spot, and Soybean Mosaic Virus. This innovation offers a valuable tool for precision agriculture, improving disease detection and crop management practices.
Keywords: UAV, soybean leaf diseases, SLIC segmentation, deep learning, MATLAB, precision agriculture 1 Introduction Precision agriculture plays a crucial role in optimizing crop management and disease detection. Unmanned Aerial Vehicles (UAVs), combined with advanced image processing techniques, have shown promise in detecting diseases in crops such as soybeans, enabling early interventions to improve crop health and yield. Previous studies have demonstrated the efficacy of UAVs in monitoring crop diseases (Yong et al., 2024), while deep learning models like CNNs have achieved remarkable accuracies in disease classification (Sadia et al., 2024). Soybean diseases such as Soybean Rust, Frogeye Leaf Spot, and Mosaic Virus can severely impact crop yield and quality if not detected early. UAVs offer a solution by capturing high-resolution images allowing detailed plant health monitoring (Everton et al., 2020).
2 Methodology:-
Fig.1 Methodology 2.1 UAV Imagery Collection In this study, UAV imagery was collected using a DJI Phantom 4 UAV equipped with a 20 MP multispectral camera. The UAV was flown at heights of 2 meters and 3 meters over soybean fields to capture high-resolution images that could reveal details of both healthy and diseased leaves. The flights were conducted under optimal weather conditions to reduce noise, such as shadows or glare, which might interfere with the disease detection process. By capturing images from these altitudes, we ensured that the imagery provided sufficient detail for accurate disease classification, particularly for diseases such as Soybean Rust and Mosaic Virus (Yong et al., 2024; Sadia et al., 2024). 2.2 Image Segmentation Using SLIC The collected UAV images were processed using MATLAB to apply Simple Linear Iterative Clustering (SLIC) for segmentation. This step divides the images into superpixels, allowing for a more detailed examination of individual soybean leaves. A superpixel count of 3000 to 5000 was used for each image, and a compactness value of 20 was selected
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 736