Drone Survey Dataset
Glasnevin and All Hallows Campuses
Following are the artefacts created by a recent drone survey and mapping exercise of the DCU campuses carried out by:
This work was carried out in conjunction with Intel Movidius, developers of the Movidius Myriad chip that provides collision detection and Object tracking in DJI drones.
This work is part of an on-going effort to digitize Dublin and to create highly accurate 3D datasets for future drone navigation applications. The intention is that drones will actively create 3D reconstructions of their environment and collectively build a highly accurate and regularly updated collaborative map.
The All Hallow reconstruction was generated from 500 images and the main campus was reconstructed from 800 images captured by the Phantom 4. The models were built using structure from motion software Pix4D
The link to the Trinity College Dublin Drone Survey Dataset, part of the same project, is below:
Below are videos showing what can be achieved using the datasets
Technical Data and Assets
The dataset consists of Drone Videos and Images and software specific rendering files.
It is possible to create various models using the datasets provided using Potree, a free opensource webgl based point cloud renderer for large point clouds, available at http://potree.org
Links to the visual assets and 3D modelling information collected are provided below:
- DCU Campus, Glasnevin Image Assets
- DCU Campus, All Hallows Image Assets
- DCU Campuses 3D Technical Data
© 2018 Intel Corporation.
This dataset and the related documents are Intel copyrighted materials, and your use of them is governed by the Community Data License Agreement – Sharing, Version 1.0. This dataset and the related documents are provided as is, with no express or implied warranties, other than those that are expressly stated in the License.