Rice Transformer: A Novel Integrated Management System for Controlling Rice Diseases

Abstract

Rice disease classification is vital during the cultivation of rice crops. However, rice diseases were initially detected by visual examination from agricultural experts. Later the detection process progressed to automation, which involved images. The images captured lead to a lack of supporting information. The traditional approaches are less accurate when used with real time images. To address this limitation, a novel Rice Transformer is proposed in the paper that merges inputs from agricultural sensors and image data captured from the fields simultaneously. The proposed system consists of two branches: the sensor and image branches. Specifically, the attention approach is employed to extract the features from both modalities. Later, the extracted features are sent to the cross-attention module as input in a crisscross fashion, enhancing the ability to identify the features specific to rice diseases. The extracted features are further pooled, merged, and later passed through the Softmax classifier to classify the rice disease precisely. The dataset collected is a customized dataset with 4200 samples collected on a real-time basis from rice farms. The experiments conducted on the dataset represent that the proposed approach outperforms all the other fusion and attention models considered for comparison in this paper. The ablation analysis and performance metrics are measured to determine the effectiveness of the proposed system. The results achieved are quite promising as the proposed Rice transformer model achieves an accuracy of 97.38% for controlling rice disease.

PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection

“…The author developed a rice transformer, which simultaneously could combine inputs from agricultural sensors and fieldbased image data. The overall accuracy achieved was 96.9% [25].…”

“…As a result, food security is threatened due to decreasing rice production. But because of major problems with rice plants, the harvest was much smaller than expected [7]. Since this disease is contagious, it is important to find them as soon as possible and keep them away from healthy plants.…”

Design of an Iterative Method for Crop Disease Analysis Incorporating Graph Attention with Spatial-Temporal Learning and Deep Q-Networks

“…Collaboration between researchers, practitioners, and policymakers is needed in establishing standardized protocols of data collection, labeling, and sharing, and this can be beneficial in this regard, fostering the creation of large-scale annotated datasets that can support robust and generalizable models. Moreover, embracing dynamic modeling approaches will go a long way in enhancing the resilience and efficacy of disease detection systems [2,12]. That is, incorporating techniques such as recurrent neural networks (RNNs) and attention mechanisms can enable modeling of temporal dependencies and contextual information, hence improving the accuracy and reliability of disease predictions.…”

ECDBMFA: Design of an Ensemble engine for Crop Disease detection via Bioinspired Multidomain Feature Analysis

“…Plant illnesses may be identified by the use of image processing to enlarge the areas that are impacted by the disease. Both a basic threshold approach and a triangle thresholding technique were used in the process of dividing the leaf and lesion area [26]. The diseases are separated into several categories based on the total leaf area and number of lesions found on each leaf.…”