RESEARCH AND APPLICATION OF CROP PEST MONITORING AND EARLY WARNING TECHNOLOGY IN CHINA

The importance of food security,especially in combating the problem of acute hunger,has been underscored as a key component of sustainable development.Considering the major challenge of rapidly increasing demands for both food security and safety,the management and control of major pests is urged to secure supplies of major agricultural products.However,owing to global climate change,biological invasion(e.g.,fall armyworm),decreasing agricultural biodiversity,and other factors,a wide range of crop pest outbreaks are becoming more frequent and serious,making China,one of the world’s largest country in terms of agricultural production,one of the primary victims of crop yield loss and the largest pesticide consumer in the world.Nevertheless,the use of science and technology in monitoring and early warning of major crop pests provides better pest management and acts as a fundamental part of an integrated plant protection strategy to achieve the goal of sustainable development of agriculture.This review summarizes the most fundamental information on pest monitoring and early warning in China by documenting the developmental history of research and application,Chinese laws and regulations related to plant protection,and the National Monitoring and Early Warning System,with the purpose of presenting the Chinese model as an example of how to promote regional management of crop pests,especially of cross border pests such as fall armyworm and locust,by international cooperation across pest-related countries.

InstaCropNet:An efficient Unet-Based architecture for precise crop row detection in agricultural applications

Autonomous navigation in farmlands is one of the key technologies for achieving autonomous management in maize fields.Among various navigation techniques,visual navigation using widely available RGB images is a cost-effective solution.However,current mainstream methods for maize crop row detection often rely on highly specialized,manually devised heuristic rules,limiting the scalability of these methods.To simplify the solution and enhance its universality,we propose an innovative crop row annotation strategy.This strategy,by simulating the strip-like structure of the crop row's central area,effectively avoids interference from lateral growth of crop leaves.Based on this,we developed a deep learning network with a dual-branch architecture,InstaCropNet,which achieves end-to-end segmentation of crop row instances.Subsequently,through the row anchor segmen-tation technique,we accurately locate the positions of different crop row instances and perform line fitting.Experimental results demonstrate that our method has an average angular deviation of no more than 2°,and the accuracy of crop row detection reaches 96.5%.