Automated Pest Detection With DNN on the Edge for Precision Agriculture

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 limi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on emerging and selected topics in circuits and systems 2021-09, Vol.11 (3), p.458-467
Main Authors: Albanese, Andrea, Nardello, Matteo, Brunelli, Davide
Format: Article
Language:English
Subjects:
Agriculture
Algorithms
Artificial intelligence
Automation
autonomous systems
Batteries
Computer vision
Continuity (mathematics)
Crop yield
Deep learning
Embedded systems
Energy consumption
Energy harvesting
Image edge detection
Infestation
Insects
Machine learning
machine learning (ML)
Medical imaging
Monitoring
Orchards
Plant diseases
Power management
Real-time systems
Sensors
Smart agriculture
smart cameras
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2156-3357
2156-3365
DOI:10.1109/JETCAS.2021.3101740