Pest Detection for Precision Agriculture Based on IoT Machine Learning
- 14 Downloads
Apple orchards are widely expanding in many countries of the world, and one of the major threats of these fruit crops is the attack of dangerous parasites such as the Codling Moth. IoT devices capable of executing machine learning applications in-situ offer nowadays the possibility of featuring immediate data analysis and anomaly detection in the orchard. In this paper, we present an embedded electronic system that automatically detects the Codling Moths from pictures taken by a camera on top of the insects-trap. Image pre-processing, cropping, and classification are done on a low-power platform that can be easily powered by a solar panel energy harvester.
KeywordsInternet of Things Machine learning Precision agriculture
This research was supported by the IoT Rapid-Proto Labs projects, funded by Erasmus+ Knowledge Alliances program of the European Union (588386-EPP-1-2017-FI-EPPKA2-KA).
- 3.Magno M, Tombari F, Brunelli D, Di Stefano L, Benini L (2009) Multimodal abandoned/removed object detection for low power video surveillance systems. In: 2009 Sixth IEEE international conference on advanced video and signal based surveillance, pp 188–193Google Scholar
- 5.Polonelli T, Brunelli D, Benini L (2018) Slotted ALOHA overlay on LoRaWAN—a distributed synchronization approach. In: 2018 IEEE 16th international conference on embedded and ubiquitous computing (EUC), Oct 2018, pp 129–132Google Scholar
- 7.Polonelli T, Brunelli D, Girolami A, Demmi GN, Benini L (2019) A multi-protocol system for configurable data streaming on IoT healthcare devices. In: 2019 IEEE 8th international workshop on advances in sensors and interfaces (IWASI), June 2019, pp 112–117Google Scholar
- 9.Tessaro L, Raffaldi C, Rossi M, Brunelli D (2018) Lightweight synchronization algorithm with self-calibration for industrial LoRa sensor networks. In: 2018 Workshop on metrology for industry 4.0 and IoT, Apr 2018, pp 259–263Google Scholar
- 10.Liu S, Deng W (2015) Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR), Nov 2015, pp 730–734Google Scholar
- 11.NeuralNetworks. https://github.com/frank1789/NeuralNetworks (Online). Accessed 25 May 2019