Abstract
We propose a novel diminished reality method which is able to (i) automatically recognize the region to be diminished, (ii) work with a single RGB-D sensor, and (iii) work without pre-processing to generate a 3D model of the target scene by utilizing SLAM, segmentation, and recognition framework. Especially, regarding the recognition of the area to be diminished, our method is able to maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. These advantages are demonstrated on the UW RGB-D Dataset and Scenes.
Original language | English |
---|---|
Title of host publication | Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 338-343 |
Number of pages | 6 |
ISBN (Electronic) | 9780769563275 |
DOIs | |
Publication status | Published - 2017 Oct 27 |
Event | 16th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017 - Nantes, France Duration: 2017 Oct 9 → 2017 Oct 13 |
Other
Other | 16th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017 |
---|---|
Country | France |
City | Nantes |
Period | 17/10/9 → 17/10/13 |
Keywords
- Convolutional Neural Network
- Diminished Reality
- Object Recognition
- Segmentation
- SLAM
ASJC Scopus subject areas
- Human-Computer Interaction
- Media Technology
- Computer Science Applications