SIP9

Smart Pest Observation and Tracking for
Identifying Flying Insects (SPOTIFLY)

Partners involved: bSpoke (ADS developer) / CRDOP Aceite de Lucena (Farmer and end-user)

Sector: Crop Pest and Disease Detection / Olive Cultivation

Country of the Pilot: Spain

About the SIP

SPOTIFLY tackles one of agriculture’s most persistent challenges, the damage caused by pest infestations in olive groves, through AI-driven, continuous pest monitoring. Traditional trap-based scouting methods are labor-intensive, prone to error, and often reactive rather than preventive. SPOTIFLY introduces an intelligent, non-intrusive system capable of detecting and tracking flying insects in real time, providing farmers with accurate data to guide targeted pest control decisions.

The pilot is implemented in Lucena, Spain, with olive farmers from the CRDOP Aceite de Lucena cooperative, and co-created with end users to ensure practicality, affordability, and ease of deployment in Mediterranean farming conditions.

 

The Problem

Pest infestations account for 20–40% of global crop yield losses, making continuous pest monitoring essential to reduce pesticide dependency. However, excessive pesticide use has led to pest resistance, biodiversity loss, and long-term environmental damage. Olive producers in Spain face additional challenges from the olive fruit fly (Bactrocera oleae) and olive moth (Prays oleae)—two major pests that thrive under shifting climate conditions and cause significant yield losses.

Current monitoring relies on manual scouting and pheromone traps, which are time-consuming and often fail to provide real-time, spatially accurate data. Farmers need a reliable, automated system that supports early detection and precise interventions to reduce chemical inputs and improve environmental sustainability.

 

The Solution

SPOTIFLY delivers an AI-powered pest monitoring system that combines advanced imaging sensors with edge and cloud computing to achieve 24/7 pest detection and analysis:

  • Cloud-based ADS – Uses Intel RealSense RGB-D cameras and infrared lighting to capture high-resolution visual and depth data, which are processed in the cloud using advanced AI models (YOLO for detection, ResNet-50 for classification, and DeepSORT for tracking). The system aggregates and analyzes large datasets to detect pest population trends across multiple sites and integrates with OpenAgri OS services such as Weather Data and Pest & Disease Management for predictive modeling.

  • Edge-based ADS – Runs the same AI pipeline locally through a Jetson Orin Nano edge device, ensuring full operation in low-connectivity environments. Results are stored and processed on-site, allowing for immediate, low-latency pest alerts and decision support. Once internet access returns, data automatically syncs to the cloud.

By combining real-time computer vision, motion tracking, and deep learning, SPOTIFLY enables precise detection with ≥90% accuracy, reduces pesticide use by over 20%, and cuts field scouting time significantly. The system’s open-source hardware specifications and integration with OpenAgri Gatekeeper ensure transparency, interoperability, and scalability across different crops and regions.

 

© 2025 OpenAgri

Project Coordination:

Prof. Christopher Brewster
Maastricht University

Minderbroedersberg 4-6,
6211 LK Maastricht,
Netherlands

christopher.brewster@

maastrichtuniversity.nl

Project Communication:

Maja Radisic
Foodscale Hub
Trg Dositeja Obradovića 8
21000 Novi Sad,
SERBIA
maja@foodscalehub.com
 
foodscalehub.com

Follow Us:

Subscribe:

OpenAgri — Where Inclusive Innovation Meets Agriculture!

OpenAgri has received funding from the EU’s Horizon Europe research and innovation programme under Grant Agreement no. 101134083. This output reflects only the author’s view and the European Commission cannot be held responsible for any use that may be made of the information contained therein.
Fill the form

Drop us a line

Fill in this form or send us an e-mail with your inquiry.

Or come visit us at:

301 Howard St. #600
San Francisco, CA 94105