An Effective Pyramid Neural Network Based on Graph-Related Attentions Structure for Fine-Grained Disease and Pest Identification in Intelligent Agriculture

Abstract

In modern agriculture and environmental protection, effective identification of crop diseases and pests is very important for intelligent management systems and mobile computing application. However, the existing identification mainly relies on machine learning and deep learning networks to carry out coarse-grained classification of large-scale parameters and complex structure fitting, which lacks the ability in identifying fine-grained features and inherent correlation to mine pests. To solve existing problems, a fine-grained pest identification method based on a graph pyramid attention, convolutional neural network (GPA-Net) is proposed to promote agricultural production efficiency. Firstly, the CSP backbone network is constructed to obtain rich feature maps. Then, a cross-stage trilinear attention module is constructed to extract the abundant fine-grained features of discrimination portions of pest objects as much as possible. Moreover, a multilevel pyramid structure is designed to learn multiscale spatial features and graphic relations to enhance the ability to recognize pests and diseases. Finally, comparative experiments executed on the cassava leaf, AI Challenger, and IP102 pest datasets demonstrates that the proposed GPA-Net achieves better performance than existing models, with accuracy up to 99.0%, 97.0%, and 56.9%, respectively, which is more conducive to distinguish crop pests and diseases in applications for practical smart agriculture and environmental protection.

A high-precision jujube disease spot detection based on SSD during the sorting process

“…The proliferation of deep learning techniques for image recognition has spurred researchers to explore their application in agricultural disease identification, aiming to achieve efficient and accurate results in detecting agricultural diseases [34][35][36]. To this end, a transfer learning strategy [37] is employed, leveraging knowledge acquired from other datasets to enhance the accuracy of disease identification and reduce detection time.…”

A Fine-Grained Recognition Neural Network with High-Order Feature Maps via Graph-Based Embedding for Natural Bird Diversity Conservation

“…Then, using the semantic grouping strategy of a graph, the features of high-dimensional data are mapped to low-dimensional space, and the learning parameters are reduced. Lin et al [ 54 ] constructed a graph convolution network method for weakly supervised fine-grained image classification based on correlation learning. This method learns the implicit relationship between different regions from the network transmission to fully mine and utilize the context relationship between other discrimination regions, thus improving the network’s recognition ability.…”

Prediction of Food Safety Risk Level of Wheat in China Based on Pyraformer Neural Network Model for Heavy Metal Contamination

“…The Nemerow Integrated Pollution Indicator (NIPI) is a weighted multi-factor environmental quality indicator that takes into account extreme values, and is one of the most common methods used at home and abroad to analyze the pollution levels in soil [23,24], crop [25,26], water [27][28][29], atmosphere [30,31], fruits [32] and vegetables [33]. It can take into account the most polluting impact factors and objectively reflect the comprehensive impact of various pollutants on wheat.…”