The 3D-Pitoti Dataset

Abstract

Abstract-The development of powerful 3D scanning hardware and reconstruction algorithms has strongly promoted the generation of 3D surface reconstructions in different domains. An area of special interest for such 3D reconstructions is the cultural heritage domain, where surface reconstructions are generated to digitally preserve historical artifacts. While reconstruction quality nowadays is sufficient in many cases, the robust analysis (e.g. segmentation, matching, and classification) of reconstructed 3D data is still an open topic. In this paper, we target the automatic and interactive segmentation of high-resolution 3D surface reconstructions from the archaeological domain. To foster research in this field, we introduce a fully annotated and publicly available large-scale 3D surface dataset including high-resolution meshes, depth maps and point clouds as a novel benchmark dataset to the community. We provide baseline results for our existing random forest-based approach and for the first time investigate segmentation with convolutional neural networks (CNNs) on the data. Results show that both approaches have complementary strengths and weaknesses and that the provided dataset represents a challenge for future research.

Artificial Intelligence, 3D Documentation, and Rock Art—Approaching and Reflecting on the Automation of Identification and Classification of Rock Art Images

“…Using AI to analyse rock art is a newly emerging field in both data science and archaeology. In the course of the ERC funded 3D-Pitoti project, several methods have been proposed and tested on a relatively limited set of rock art images (Poier et al, 2016(Poier et al, , 2017Zeppelzauer et al, 2016;. 2D and 3D documentations were used to create an automatic segmentation algorithm.…”

How to Tell Ancient Signs Apart? Recognizing and Visualizing Maya Glyphs with CNNs

“…Petroglyph, in other words rock-art, analysis [8,28,[31][32][33]46] is another related topic to our glyph recognition task. For petroglyph segmentation that can be considered as foreground/background classification of pixels, Seidl et al [31] studied various combinations of traditional textural features.…”

“…Specifically, third order Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) were shown to outperform color or dense-SIFT features in a late classification fusion setting [31]. In a recent 3D petroglyph segmentation study, Poier et al [28] reported that fully-connected CNNs produced better segmentation results thanks to capturing the spatial context better than random forests. Poier et al [28] also noted that the contribution of traditional color and textural features to final segmentation maps was negligible, therefore only depth maps and orthophotos generated from the point clouds were used as input to the classifiers.…”

Using Structure from Motion Mapping to Record and Analyze Details of the Colossal Hats (Pukao) of Monumental Statues on Rapa Nui (Easter Island)

“…SfM is well-suited for identifying petroglyphs on uneven surfaces, such as those often found in caves (Caninas et al 2016; Fritz et al 2016), and SfM models give spatial context to petroglyphs that is helpful for interpretation (Alexander et al 2015; Janik et al 2007). Because of the value of SfM for the interpretation of rock art, archaeologists have recently explored methods of digitally enhancing model visualization (e.g., Carrero-Pazos et al 2016; Vilas-Estevez et al 2016), have developed specialized tools for efficiently collecting rock art photographs (e.g., Höll et al 2014), and have segmented rock art models to effectively store and query models in databases (e.g., Poier et al 2016; Zeppelzauer et al 2015; Zeppelzauer et al 2016). Significantly, SfM mapping has a substantially lower impact on rock art than tracing, and monitoring of archaeological features through SfM mapping can be used to identify conservation priorities (Plets et al 2012).…”