Deep Learning Models for the Classification of Crops in Aerial Imagery: A Review

Abstract

In recent years, the use of remote sensing data obtained from satellite or unmanned aerial vehicle (UAV) imagery has grown in popularity for crop classification tasks such as yield prediction, soil classification or crop mapping. The ready availability of information, with improved temporal, radiometric, and spatial resolution, has resulted in the accumulation of vast amounts of data. Meeting the demands of analysing this data requires innovative solutions, and artificial intelligence techniques offer the necessary support. This systematic review aims to evaluate the effectiveness of deep learning techniques for crop classification using remote sensing data from aerial imagery. The reviewed papers focus on a variety of deep learning architectures, including convolutional neural networks (CNNs), long short-term memory networks, transformers, and hybrid CNN-recurrent neural network models, and incorporate techniques such as data augmentation, transfer learning, and multimodal fusion to improve model performance. The review analyses the use of these techniques to boost crop classification accuracy by developing new deep learning architectures or by combining various types of remote sensing data. Additionally, it assesses the impact of factors like spatial and spectral resolution, image annotation, and sample quality on crop classification. Ensembling models or integrating multiple data sources tends to enhance the classification accuracy of deep learning models. Satellite imagery is the most commonly used data source due to its accessibility and typically free availability. The study highlights the requirement for large amounts of training data and the incorporation of non-crop classes to enhance accuracy and provide valuable insights into the current state of deep learning models and datasets for crop classification tasks.

Comparison of Selected Machine Learning Algorithms in the Analysis of Mental Health Indicators

“…Interpretability of models-understanding why a model made certain decisions can be a problem for mental health diagnosis and treatment; • Importance of experts-ML models will not replace human expertise, but will only support it [38][39][40][41][42].…”

MultiFuseYOLO: Redefining Wine Grape Variety Recognition through Multisource Information Fusion

“…To address this issue, a novel deep learning approach is proposed in this study to mitigate the challenges associated with using a single feature for variety identification [5]. By employing deep learning algorithms such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), a multifeature fusion strategy is introduced, integrating information from both grape leaves and fruits [6]. This methodology deviates from conventional deep learning techniques by emphasizing the amalgamation of information from diverse sources, thereby enhancing the accuracy of identifying similar varieties [7].…”

Transformers for Remote Sensing: A Systematic Review and Analysis

“…However, due to various factors, including the greater number of parameters in remote sensing images compared to natural images [ 6 ] and the limited availability of such imagery, research on transformers in RS remains relatively nascent. There are three extant reviews related to the topic, with two focusing more generally on deep learning in RS [ 7 , 8 ] and providing only brief overviews of transformers in RS, and the last, by Aleissaee et al [ 9 ], focusing on RS image types (e.g., hyperspectral imagery, synthetic aperture radar imagery). Based on their review, they discussed the strengths and weaknesses of CNNs and transformers for these different RS image types.…”