The computational team at GIAP (ICAC) has been enjoying a fruitful long-term collaboration with the Computer Vision Center (CVC) of the Autonomous University of Catalonia (UAB), which has contributed to our projects with their expertise and state-of-the-art computational equipment.
These past weeks, Prof. Hèctor A. Orengo (ICREA Research professor at ICAC) and Dr. Felipe Lumbreras (CVC-UAB), along with other team members of the computational team, have been hosting meetings to discuss ongoing projects and define new collaborations.
Featured image: from left to right: Iban Berganzo-Besga, Hèctor A. Orengo, Felipe Lumbreras and Arnau Garcia-Molsosa
Current projects include:
- A collaboration in the context of the MAHSA project Mapping Archaeological Heritage in South Asia, (led by the University of Cambridge and funded by Arcadia Fund), which will be renewed during the following months to continue its outstanding developments, which aim at protecting and monitoring the most vulnerable heritage through an approach based on digital humanities: remote sensing, machine learning, and the complete digitisation of existing archives with conventional archaeological surveys and record-based investigations.
- A collaboration to investigate the use of hyperspectral images for the identification of specific typologies from ceramic sherds, led by Dr. Daniel Ponsa (CVC-UAB) in collaboration with Dr Núria Romaní (UAB) and other colleagues from the the CVC-UAB and the Departament de Ciències de l’Antiguitat i de l’Edat Mitjana of the Autonomous University of Barcelona (UAB).
- The co-supervision of Iban Berganzo-Besga’s PhD thesis “New Computational Methods for Automated Large-Scale Archaeological Site Detection” by Hèctor A. Orengo (ICREA Research professor) and Felipe Lumbreras (CVC-UAB). The PhD viva voce was held this past Friday (10th of March) in ICAC.
Besides ongoing collaborations, new projects at GIAP (ICAC) have presented the chance of establishing new synergies with the CVC-UAB:
- In the context of the MAPHSA project: Mapping the Archaeological Pre-Columbian Heritage of South America‘ (led by UPF and funded by Arcadia Fund), which aims at documenting the archaeological heritage of about 3.5 million km2 of endangered forest and savanna biomes across Brazil and Colombia, through a combination of archival work, remote sensing, machine learning, and ground survey.
- In the context of the AI4Archaeology project: “Deep learning algorithms for the automated detection of sites in Aragón and Extremadura” (funded by Enel-Endesa), which aims at developing a series of algorithms using deep-learning approaches for the detection of archaeological structures above the surface or partially buried.
- State-of-the-art training on novel techniques for remote sensing & machine/deep Learning.
Additionally, exciting future collaborations have been discussed, which include route modelling for ancient commerce, the automation of seed classification and robotic surveying for archaeological sites. Stay tuned to our channels to learn all about them!
Learn more about the current results of this fruitful ongoing collaboration:
Posts:
- Computational archaeology thesis defence: Iban Berganzo-Besga
- The computational team welcomes a new researcher for 6 months!
- GIAP expands the team on Remote Sensing and Archaeobotany!
- Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms
- Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm Detects Near 10k Archaeological Tumuli in North-Western Iberia
References:
- Berganzo-Besga, I., Orengo, H.A., Lumbreras, F., Aliende, P., N. Ramsey, M. 2022. Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms. Journal of Archaeological Science. https://doi.org/10.1016/j.jas.2022.105654
- Berganzo-Besga, I.; Orengo, H.A.; Canela, J.; Belarte, M.C. Potential of Multitemporal Lidar for the Detection of Subtle Archaeological Features under Perennial Dense Forest. Land 2022, 11, 1964. https://doi.org/10.3390/land11111964
- Berganzo-Besga, I.; Orengo, H.A.; Lumbreras, F.; Carrero-Pazos, M.; Fonte, J.; Vilas-Estévez, B. Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm Detects Near 10k Archaeological Tumuli in North-Western Iberia. Remote Sens. 2021, 13, 4181.https://doi.org/10.3390/rs13204181
- Orengo, H.A.; Garcia-Molsosa, A.; Berganzo-Besga, I.; Landauer, J.; Aliende, P. and Tres-Martínez, S. 2021. New developments in drone-based automated surface survey: towards a functional and effective survey system. Archaeological Prospection. https://doi.org/10.1002/arp.1822
- Belarte, M. C.; Canela, J.; Orengo, H.A.; Berganzo-Besga, I., “Using LiDAR to detect architectural features in urban sites in the coast of Northern Iberia (6th – 3rd centuries BC). Preliminary results” a Belarte, M. C.; Noguera, J.; Plana-Mallart, R.; Sanmartí, J., Urbanization in Iberia and Mediterranean Gaul in the first millennium BC, Treballs de la Mediterrània Antiga, 7, ICAC, Tarragona, p. 137-148. https://www.recercat.cat/bitstream/handle/2072/417717/2020-Using-lidar-detect-architectural-features-urban-sites.pdf
