Interactive 3D Digitization, Retrieval, and Analysis of Ancient Sculptures, Using Infrared Depth Sensors for Mobile Devices
In this paper a novel framework is presented for interactive feature-based retrieval and visualization of human statues, using depth sensors for mobile devices. A skeletal model is fitted to the depth image of a statue or human body in general and is used as a feature vector that captures the pose variations in a given collection of skeleton data. A scale- and twist- invariant distance function is defined in the feature space and is employed in a topology-preserving low-dimensional lattice mapping framework. The user can interact with this self-organizing map by submitting queries in the form of a skeleton from a statue or a human body. The proposed methods are demonstrated in a real dataset of 3D digitized Graeco-Roman statues from Palazzo Altemps.
KeywordsDepth sensors RGB-D Kinect 3d object retrieval Digital humanities Statues Museum studies
The authors would like to acknowledge Alessandra Capodiferro for providing permission to perform this study in Palazzo Altemps and the Italian Ministry of heritage, cultural activities and tourism for providing permission to publish in this paper the collected data. This project would not be possible without the funding support by the Rothman Fellowship in the Humanities to Eleni Bozia from the Center for the Humanities and the Public Sphere at the University of Florida and the research incentive award to Angelos Barmpoutis from the College of the Arts at the University of Florida. The authors would like to thank the sponsors and the anonymous reviewers who provided insightful comments and suggestions.
- 1.Microsoft Kinect SDK. http://www.microsoft.com/en-us/kinectforwindows/
- 2.OpenNI. http://www.openni.org/
- 5.Barmpoutis, A., Fox, E.J., Elsner, I., Flynn, S.: Augmented-reality environment for locomotor training in children with neurological injuries. In: Linte, C.A. (ed.) AE-CAI 2014. LNCS, vol. 8678, pp. 108–117. Springer, Heidelberg (2014) Google Scholar
- 8.Haykin, S.: Neural Networks and Learning Machines (3rd edn). Prentice Hall (2008)Google Scholar
- 10.La Regina, A.: Museo Nationale Romano. Soprintendenza Archaeologica di Roma. Mondadori Electa S.p.A. Milan (2005)Google Scholar
- 11.Oikonomidis, I., et al.: Efficient model-based 3D tracking of hand articulations using Kinect. In: Proceedings of the British Machine Vision Association Conference (2011)Google Scholar
- 12.Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: IEEE CVPR Conference, pp. 1297–1304 (2011)Google Scholar
- 13.Ultsch, A.: Emergence in self-organizing feature maps. In: Ritter, H., Haschke, R. (eds.) Proceedings of the 6th International Workshop on Self-Organizing Maps (2007)Google Scholar
- 14.Xia, L., et al.: Human detection using depth information by Kinect. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 15–22 (2011)Google Scholar