In this video the usage of spherical, high-resolution HDR images for scene reconstruction is demonstrated.
The software is developed by the department Augmented Vision of DFKI (http://av.dfki.de).Possible scenarios for its application are the reconstruction of:
The software is developed by the department Augmented Vision of DFKI (http://av.dfki.de).Possible scenarios for its application are the reconstruction of:
- cultural heritage sites
- urban scenes
- industrial production sites
- progression monitoring for building sites, archaeological excavation, etc.
The reconstruction results offer precise geometry, so that exact measurements can be made within the 3D model.
This video shows the first results for 3D object reconstruction using the depth images from the Microsoft Kinect camera.
Data acquisition is as simple as moving the Kinect around the object of interest.
From there the raw data is processed in a two step algorithm:
Data acquisition is as simple as moving the Kinect around the object of interest.
From there the raw data is processed in a two step algorithm:
- Superresolution images are computed from several consecutive captured frames.
- The superresolution images are aligned using a improved version of the global alignment technique from “3D Shape Scanning with a Time-of-Flight Camera – Yan Cui, et.al. CVPR2010”.
Nils Petersen and Didier Stricker, ‘Continuous Natural User Interface: Reducing the Gap Between Real and Digital World’, in Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR), 2009