A Review on the Application of Deep Learning Methods in Detection and Identification of Rice Diseases and Pests

In rice production,the prevention and management of pests and diseases have always received special attention.Traditional methods require human experts,which is costly and time-consuming.Due to the complexity of the structure of rice diseases and pests,quickly and reliably recognizing and locating them is difficult.Recently,deep learning technology has been employed to detect and identify rice diseases and pests.This paper introduces common publicly available datasets;summarizes the applications on rice diseases and pests from the aspects of image recognition,object detection,image segmentation,attention mechanism,and few-shot learning methods according to the network structure differences;and compares the performances of existing studies.Finally,the current issues and challenges are explored fromthe perspective of data acquisition,data processing,and application,providing possible solutions and suggestions.This study aims to review various DL models and provide improved insight into DL techniques and their cutting-edge progress in the prevention and management of rice diseases and pests.

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning method.We demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model structure.However,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial obstacle.This issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data security.To address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

Development of an automatic monitoring system for rice light-trap pests based on machine vision

Monitring pest populations in paddy fields is important to effectively implement integrated pest management.Light traps are widely used to monitor field pests all over the world.Most conventional light traps still involve manual identification of target pests from lots of trapped insects,which is time-consuming,labor-intensive and error-prone,especially in pest peak periods.In this paper,we developed an automatic monitoring system for rice light-trap pests based on machine vision.This system is composed of an itelligent light trap,a computer or mobile phone client platform and a cloud server.The light trap firstly traps,kills and disperses insects,then collects images of trapped insects and sends each image to the cloud server.Five target pests in images are automatically identifed and counted by pest identification models loaded in the server.To avoid light-trap insects piling up,a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects.There was a close correlation(r=0.92)between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap.Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.

The Predatory Function of Three Spiders to Two Insect Pests in Rice Within a Multi-species Co-existence System

The prey-seeking behavior of three spiders (X1-Pirata subpiraticus, X2-Clubiona japonicola and X3-Tetragnatha japonica) for brown plant hopper (X4-Nilaparvata lugens) and rice spittle bug (X5-Cal-litettix versicolor) was investigated, as well as how interference between and within species occurred, by using a quadratic regression rotational composite design. Six predation models derived from the analysis of interactions among and within predators and preys were developed. The total predatory capacity of spiders on rice insect pests after coexistence for one day can be expressed as follows: Y3 = 32.795 + 2.25X1 + 1.083X2 + 0.5X3 + 10.167X4 + 3.167X5 - 1.67X12 - 2.42X22 - 3.295X32 - 0.045X42 + 0.455X52 - 3.125X1X2 + 0.375X1X3 -0.625X1X4 - 0.375X1X5 + 0.375X2X3 - 0.875X2X4 + 0.125X2X5 + 0.375X3X4 - 0.375X3X5 + 0.125X4X5. The principal efficiency analysis using this model indicated that increases in insect pest density significantly increased predation by predators; this was much greater than the effect of any single predator. X4 had a greater effect than X5; however, X4 and X5 demonstrated little interspecific interference and even promoted each other and increased predation rates as the densities of the two pests increased. Among the three predators, an increase in the density of X, had the greatest effect on the increase in predation, X3 had the second, X2 the third greatest effect. As predator density increased inter- and intra-species interference occurred, which were largely related to the size, activity, niche breadth, niche overlap and searching efficiency of the predators. X2 produced the greatest interference between different individuals and between any other predator species. X3 had the second greatest, which reduced predation levels at high predator densities. Because of these factors, the highest predation rate was obtained at a prey density of 120 per 4 rice-hills. The optimal proportion of the three predators in the multi-predator prey system was X1: X2: X3 = 5.6:1.3:4.1.

Evaluation and screening for resistance of some varieties(lines)to major diseases and insect pests of rice

During 1984-1988,2,231 varieties(lines)from International Rice Testing Program(IRTP)were evaluated and screened for resistance to riceblast(Bl),bacterial blight(BB),sheath blight

An Insect Imaging System to Automate Rice Light-Trap Pest Identification

Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast. Identification and counting of rice light-trap pests manually is time-consuming, and leads to fatigue and an increase in the error rate. A rice light-trap insect imaging system is developed to automate rice pest identification. This system can capture the top and bottom images of each insect by two cameras to obtain more image features. A method is proposed for removing the background by color difference of two images with pests and non-pests. 156 features including color, shape and texture features of each pest are extracted into an support vector machine （SVM） classifier with radial basis kernel function. The seven-fold cross-validation is used to improve the accurate rate of pest identification. Four species of Lepidoptera rice pests are tested and achieved 97.5% average accurate rate.