Abstract
Identifying an appliance for interaction in commercial buildings becomes non-trivial as the number of smart appliances explodes. We present a system for users to intuitively "look up" appliances using image matching-based technique on a pre-constructed and annotated visual model of building interiors. It matched 98% images on a public robot-collected dataset and achieved 100% recall and precision. Our lab experiments with human captured videos and images also show the feasibility of real world deployments.
Original language | English (US) |
---|---|
Title of host publication | BuildSys 2015 - Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built |
Publisher | Association for Computing Machinery, Inc |
Pages | 103-104 |
Number of pages | 2 |
ISBN (Electronic) | 9781450339810 |
DOIs | |
State | Published - Nov 4 2015 |
Externally published | Yes |
Event | 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built, BuildSys 2015 - Seoul, Korea, Republic of Duration: Nov 4 2015 → Nov 5 2015 |
Publication series
Name | BuildSys 2015 - Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built |
---|
Conference
Conference | 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built, BuildSys 2015 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 11/4/15 → 11/5/15 |
Bibliographical note
Publisher Copyright:© 2015 ACM.
Keywords
- Identification
- Image Matching
- Structure from Motion