11-07, 09:30– (Australia/Hobart), Main Auditorium
Exploring the potential for open-source machine learning methods to aid rock art research
Rock art is globally recognized as significant, yet the resources allocated to the study and exploration of this important form of cultural heritage are often scarce. In 2022, I co-authored a paper that reflected on the potential of machine learning for rock art research to bypass this problem. As a proof-of-concept, we used open-source deep learning methods (VGG, ResNet , and Inception) to train a model to identify images with painted rock art (pictograms). In this presentation, I will evaluate what has developed so far and what is still needed.
Dr Andrea Jalandoni is a pioneering Digital Archaeologist specializing in rock art recording and enhancement using photogrammetry and other remote sensing techniques including lidar and unmanned aerial systems. She has almost 20 years of archaeological experience in Australia, Southeast Asia, and Micronesia working on some of the most famous World Heritage Sites like Kakadu National Park (NT), Niah Cave (Malaysia), and Nan Madol (Pohnpei).
Andrea is a Senior Research Fellow at Griffith University currently working on an ARC DECRA 2024 fellowship.