6533b834fe1ef96bd129e2cd
RESEARCH PRODUCT
Know Beyond Seeing: Combining Computer Vision with Semantic Reasoning
Christophe NicolleJulien DuboisRoberto Marroquinsubject
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]0209 industrial biotechnologybusiness.industryComputer scienceDigital data0211 other engineering and technologiesCognition02 engineering and technology[INFO] Computer Science [cs]Semantics[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]020901 industrial engineering & automation021105 building & constructionContextual informationComputer vision[INFO]Computer Science [cs]Artificial intelligenceMeaning (existential)businessAND gateBuilding automationdescription
International audience; To date, computer vision systems are limited to extract the digital data of what the cameras "see". However, the meaning of what they observe could be greatly enhanced by considering the environment and common-sense knowledge. A new approach to combine computer vision with semantic modeling has been developed. This approach extracts the knowledge from images and uses it to perform real-time reasoning according to the contextual information, events of interest and logic rules. The reasoning with image knowledge allows protecting the privacy of the users, to overcome some problems of computer vision such as occlusion and missed detections and to offer services such as people guidance and people counting. This approach is the first step to develop an "all-seeing" smart building that can automatically react according to its evolving information.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2018-01-31 |