Automated Pest Detection with DNN on the Edge for Precision Agriculture

TL;DR

This paper introduces an embedded, low-power AI system with neural acceleration for real-time pest detection in orchards, enabling continuous, autonomous crop protection with extended battery life through energy harvesting.

Contribution

It presents a novel integrated embedded system with ML capabilities and energy harvesting for autonomous pest detection in precision agriculture.

Findings

Successful deployment of three ML algorithms on embedded hardware

Extended battery life enabled by energy harvesting

Continuous pest detection without farmer intervention

Abstract

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.