From object detection to semantic segmentation: Leveraging the AI4EOSC platform for UAS-based thermal image analysis

This presentation is part of the third session of the second AI4EOSC Webinar Series "Exploring the Future of AI, Machine Learning, and Federated Learning" titled "Accelerating Research with AI4EOSC: Real Use Cases Exploiting the Platform". It discusses how we can leverage AI and thermal / multispectral (RGBT) remotely sensed data to find thermal points of interest in our urban environments. This spans from detecting thermal bridges on building rooftops for energy retrofits, over identifying all manner of common urban hot-spots, to segmenting thermal anomalies for pipeline leak detection.

Three modules have been implemented on the AI4EOSC platform that enable the training of object detection and semantic segmentation models as well as prediction with well-known CNN- and transformer-based architectures. Not only are the platform's resources leveraged to perform both these tasks but other functionalities are also made use of, such as MLFlow for experiment tracking.