物联网学报2023，Vol.7Issue(4)：132-141,10.DOI:10.11959/j.issn.2096-3750.2023.00365
基于STM32的农业物联网病虫害图像识别算法研究
Research on agricultural IoT pest and disease image recognition algorithm based on STM32
摘要
Abstract
In modern agriculture IoT systems,edge computing is an indispensable component.In this context,it is feasi-ble to deploy lightweight pest and disease image recognition tasks on edge devices.However,due to the constraints of device computation and storage capabilities,this task faces significant challenges.To address these challenges,an eco-nomically practical method was proposed for pest and disease image recognition on STM32 edge devices.Specifically,the MobileNetv2 structure was improved to better suit the characteristics of STM32,quantization-aware training tech-nique was used to compresses the network,model portability was enhanced.Meanwhile,the X-CUBE-AI was used to ar-range the model and evaluate the performance.Experimental results demonstrate that the proposed model not only en-sures image classification accuracy but also reduces the Flash and RAM resource consumption on STM32 compared to other lightweight networks.关键词
农业物联网/边缘计算/病虫害识别/STM32Key words
agricultural IoT/edge computing/pest and disease recognition/STM32分类
信息技术与安全科学引用本文复制引用
许柏涛,陈翔..基于STM32的农业物联网病虫害图像识别算法研究[J].物联网学报,2023,7(4):132-141,10.基金项目
广东省现代农业产业技术创新团队专项基金资助项目(No.2023KJ122)The Guangdong Provincial Special Fund for Modern Agriculture Industry Technology Innovation Teams(No.2023KJ122) （No.2023KJ122）
