ConímbrigAR: A Prototype Augmented Mobile Application for Exploration of Roman Mosaics 2ªs Jornadas de Documentação e Representação Digital de Bens Culturais, 19-20 Oct, School of Arts, Porto, 2018 André Belo, Jorge C. S. Cardoso CISUC/DEI, Universidade de Coimbra
“Mosaico - Conímbriga e Sicó” Project ● Integrated into the CREATOUR national project as a pilot initiative - Creative Tourism Destination Development in Small Cities and Rural Areas ● “Mosaico – Conímbriga e Sicó” is a creative tourism project based on the Roman Mosaic heritage ○ Develops educational, cultural, and creative activities around Roman Mosaic
“Mosaico - Conímbriga e Sicó” Project ● Based on the valuable Roman Mosaic Heritage present in the geographical axis constituted by ○ the Ruins of the Roman city of Conímbriga, ○ the Roman Villa of Rabaçal, and ○ the Monumental Complex of Santiago da Guarda. ● Headquartered in the “Monographic Museum of Conímbriga – National Museum” ○ an important center for archaeological research, conservation and restoration of Roman Mosaic in Portugal
“Mosaico - Conímbriga e Sicó” Project ● Promotes cultural and creative activities within the museums, interpretative centers and archaeological sites included in its program of action. ● The visitors are invited to be involved in alternative experiences of sharing knowledge about the Roman Mosaic Heritage ● Mosaic as an expression of creativity brought into the present and reinterpreted now and in the future.
Digital Tools for Exploring Roman Mosaic In the context of the “Mosaico - Conímbriga e Sicó” project Various planned digital tools to support different activities for exploring roman mosaic
Augmented Reality Mobile Application ● Technical information about the mosaics, for example, when they were uncovered, what was the latest conservation or restoration work, etc. ● Provide additional conservation and restoration information, for example, display image overlays of the conservation or restoration works on mosaics over time.
Augmented Reality Mobile Application ● Provide a platform for the visualization of virtual restoration of the existing mosaics. The virtual restoration images could be created by different audiences with different purposes. For example, in the context of a school visit, students could digitally manipulate mosaic images and creatively “restore” missing parts which could then be experienced through the AR application.
Augmented Reality Mobile Application ● Provide visual indication regarding specific aspects of the various mosaics. ● For example, mosaics could be highlighted with graphical information regarding the various motifs found in the mosaics ○ geometric patterns, animals, plants, compositions, mythological figures, etc.
Augmented Reality Mobile Application ● Hybrid application (run on Android, iOS, etc.) ○ Lower development effort ● What AR development frameworks are most suitable for detecting mosaics?
Types of Augmented Reality - (Structured) Marker Based ● Based on a pre-defined, structured visual marker image ● Very precise, requires placement of artificial markers on site
Types of Augmented Reality - (Natural Image Features) Marker Based ● Based on a pre-defined natural images (targets) ● Very precise, if targets are good enough ● May be used against natural images on site ● Usually used with printed images
AR Development Frameworks ● We studied multi-platform AR development frameworks and their features ○ We wanted natural image features ● Narrowed down to 3 frameworks suitable for natural image detection
AR Framework Evaluation ● Real-world evaluation with roman mosaics at Conímbriga ● Targets with different characteristics were captured ● A test application was developed using each of the 3 AR frameworks
AR Test Application ● Test application overlaid graphical shapes over the targets ● We screen-captured in video the execution of the application over each of the mosaic targets
AR Test Application ● We subjectively analysed the various videos on 3 metrics ○ Recognition delay ○ Minimum required target area ○ Visual alignment and stability
AR Framework Evaluation Results - Overall Recognition ● Not all targets were recognized ○ This was expected ○ Targets were captured from a distance ○ Not much effort in capturing targets ● Wikitude performed very poorly ○ Unexpected ○ Requires further study as to why
AR Framework Evaluation Results - Visual alignment and stability -1: bad alignment / stability 0: ok alignment / stability 1: good alignment / stability
Conclusion ● Study allowed us to understand strong and weak points of these AR frameworks ● AR frameworks’ performance varies depending on the type of image they are recognizing ● AR frameworks have different performance compromises ○ No single one is best at every performance attribute ● Virtual Heritage application developers should test different frameworks before commiting to one ● We still need to study additional aspects such as the best way to capture targets ○ Explore alternative AR types