期刊
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS
卷 11, 期 3, 页码 458-467出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JETCAS.2021.3101740
关键词
Agriculture; Task analysis; Monitoring; Insects; Image edge detection; Batteries; Real-time systems; Smart agriculture; smart cameras; artificial intelligence; machine learning (ML); autonomous systems; energy harvesting
资金
- Italian Ministry for Education, University and Research (MIUR) under the Program Dipartimenti di Eccellenza
- TIM Telecom Italia S.p.A.
This study presents an embedded system with machine learning functionalities for continuous pest detection in fruit orchards, including the training and deployment of three different ML algorithms, along with optimized energy harvesting for extended battery life, enabling automated pest detection without the intervention of farmers for an unlimited period of time.
Artificial intelligence has smoothly penetrated several economic activities, especially monitoring and control applications, including the agriculture sector. However, research efforts toward low-power sensing devices with fully functional machine learning (ML) on-board are still fragmented and limited in smart farming. Biotic stress is one of the primary causes of crop yield reduction. With the development of deep learning in computer vision technology, autonomous detection of pest infestation through images has become an important research direction for timely crop disease diagnosis. This paper presents an embedded system enhanced with ML functionalities, ensuring continuous detection of pest infestation inside fruit orchards. The embedded solution is based on a low-power embedded sensing system along with a Neural Accelerator able to capture and process images inside common pheromone-based traps. Three different ML algorithms have been trained and deployed, highlighting the capabilities of the platform. Moreover, the proposed approach guarantees an extended battery life thanks to the integration of energy harvesting functionalities. Results show how it is possible to automate the task of pest infestation for unlimited time without the farmer's intervention.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据