Demetris Demetriou

About

Demetris Demetriou is a leading researcher in the application of deep learning to construction and demolition waste (CDW) management, a critical area for advancing sustainable construction practices. His work focuses on developing real-time object detection systems that enable automated waste sorting, directly addressing the inefficiencies of manual recycling processes. Demetriou’s most impactful contribution is a comprehensive 2023 study (95 citations) that benchmarks state-of-the-art deep learning models—comparing single-stage and two-stage detectors—for the accurate localisation and classification of CDW. This research is central to the development of a successful waste sorting robot, demonstrating how high-speed, precise detection can transform recycling operations. By rigorously evaluating models like YOLO and Faster R-CNN in real-world conditions, Demetriou provides a practical roadmap for deploying AI in waste management, reducing landfill dependency and promoting circular economies. His work has been widely cited by engineers and environmental scientists, underscoring its influence on both robotics and sustainability. Demetriou’s achievements highlight the power of deep learning to solve pressing environmental challenges, making him a key figure in the intersection of artificial intelligence and green technology.

Research Focus

Key Achievements

Top Papers

1. 1
   Real-time construction demolition waste detection using state-of-the-art deep learning methods; single–stage vs two-stage detectors

   95 citations · 2023
2. 2
   Real-Time Construction Demolition Waste Detection Using State-of-The-Art Deep Learning Methods; Single – Stage vs Two-Stage Detectors

   4 citations · 2023

Key Collaborators

Contact & Links