Advancements in Communication and Systems
Review on Advancement in Machine Learning and Deep Learning Techniques for Crop Classification
Authors: Sarita Yadav, Srishti Sharma and Poonam Chaudhary
Publishing Date: 13-09-2024
ISBN: 978-81-955020-7-3
Abstract
Crop classification is a fundamental task for agriculture monitoring and management to optimize resource allocation and ensure food security. With the advancement of Artificial Intelligence(AI) Algorithms and Remote Sensing Technology, improved accuracy and efficiency in crop classification processes can be attained. This paper presents a comprehensive review of the various Remote Sensing technologies and AI algorithms used for crop classification. First, we will discuss the role of various remote sensing techniques used for capturing imagery, including Unmanned Aerial vehicles (UAVs) and satellites, followed by various fusion technologies for integration images from different platforms. Second, various models and techniques implemented in the literature, including both machine learning (SVM, Random Forest, Decision Tree) and deep learning (CNNs, RNNs, and Neuarl Networks) have been reviewed. Third, as conclusion , this paper finds that CNN-based models utilizing hyperspectral and mutitemporal fused imagery from various remote sensing sources are prevalent in the classification field. This paper has highlighted key challenges in areas such as data availability, scalability, model generalization, and integration of multisource imagery. Additionally, it offers potential solutions and proposes various methods and techniques for further exploration in crop classification.
Keywords
Crop Classification, Deep Learning, Remote Sensing, Satellite Imagery, UAVs, Unmanned Aerial Vehicles.
Cite as
Sarita Yadav, Srishti Sharma and Poonam Chaudhary, "Review on Advancement in Machine Learning and Deep Learning Techniques for Crop Classification", In: Ashish Kumar Tripathi and Vivek Shrivastava (eds), Advancements in Communication and Systems, SCRS, India, 2024, pp. 593-610. https://doi.org/10.56155/978-81-955020-7-3-53