Leader
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum.
Hosting Facilities
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum.
ARGUS
Data Collection
AI-Based Remote Grid Utility Surveillance
Challenge: 2D/3D image analysis for large Energy Infrastructure predictive maintenance
ARGUS develops an AI-driven UAV monitoring system for power transmission line corridors. The project addresses two use cases, vegetation health monitoring and vegetation height estimation, combining multispectral imagery and LiDAR data with deep learning models to detect species, assess health status, and identify encroachment risks along transmission lines. A predictive analytics layer enriched with weather data generates risk-scored maintenance recommendations, delivered through a GIS dashboard. The solution is validated at TRL7 on real overhead-line corridors in Slovenia operated by ELES, enabling a shift from schedule-driven to condition-based vegetation management.
Leader
Hosting Facilities
The low-TRL playground, hosted by LEITAT in Barcelona, supports laboratory-based validation of image analysis models using hyperspectral cameras on controlled vegetation samples. The high-TRL playground, hosted by ELES in Slovenia, provides real overhead-line corridor sections for end-to-end field testing of the AI pipeline with operational UAV data.
Background
The ARGUS consortium brings together iLink and Local-AI, two complementary Greek SMEs. iLink, established in Athens in 2005, provides enterprise software, IoT, and telematics solutions to over 1,000 clients and participates in several Horizon Europe projects, including FORTIS, COP-PILOT, NERO, and 3C4AI. iLink leads system architecture, data integration, and dashboard development. Local-AI, based in Kalamata, specialises in deep learning for sustainability and energy transition. A member of the Smart Attica EDIH and active in Interconnect H2020. Local-AI brings proven experience in designing and validating AI solutions in operational environments and leads all model development for ARGUS.
Solution
ARGUS delivers an end-to-end AI pipeline for vegetation monitoring along high-voltage transmission corridors. UAV platforms operated by ELES capture RGB, multispectral, and LiDAR data over pilot corridor sections in Slovenia. Deep learning models process this data to classify vegetation species, assess health through spectral indices, and estimate canopy height to flag encroachment risks near conductors. A predictive analytics layer combines these outputs with weather forecasts and historical maintenance records to generate prioritised maintenance recommendations. All results are visualised through a web-based GIS dashboard with API-based export to existing operator systems.
Objectives
- Develop AI models for vegetation health monitoring and height estimation from UAV-acquired multispectral and LiDAR data
- Deliver a predictive analytics and GIS dashboard platform
- Validate the end-to-end system at TRL7 on real overhead-line corridors in Slovenia
- Reduce vegetation-related field mobilisations and associated CO₂ emissions
KPIs achieved
Development
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum. Duis vel nulla hendrerit augue aliquet posuere. In erat arcu, accumsan ut rhoncus in, fringilla at elit. Morbi non gravida ligula. Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum. Duis vel nulla hendrerit augue aliquet posuere. In erat arcu, accumsan ut rhoncus in, fringilla at elit. Morbi non gravida ligula.
Feedback
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.