Multimodal Presence Detection
An office presence detection system is presented in this paper. Context information from multi-sensory inputs is integrated to infer a user’s activities in an office. We design a layered architecture to model human activities with different granularities. An IHDR (Incremental Hierarchical Discriminant Regression) tree is used to automatically generate models for acoustic signals from unsegmented auditory streams, with a high adaptive capability to new settings. Hidden Markov Models (HMM) are implemented to detect human motion patterns. The outputs of the above two components are fed into high-level HMMs to analyze human activities. Experimental results of the real-time prototype system are reported.
See more on this video at https://www.microsoft.com/en-us/research/video/multimodal-presence-detection/
Other Videos By Microsoft Research
2016-12-16 | Scopri il nuovo Microsoft Translator |
2016-12-16 | اكتشف Microsoft Translator الجديد |
2016-12-16 | Descubra el nuevo Microsoft Translator |
2016-12-15 | Откройте для себя новый Microsoft Translator |
2016-12-15 | Descubra o novo Microsoft Translator |
2016-12-15 | Entdecken Sie den neuen Microsoft Translator |
2016-12-15 | 探索新版的 Microsoft Translator |
2016-12-15 | A Practical Guide to Neural Machine Translation |
2016-12-15 | Personal Telepresence Station Prototype Demo |
2016-12-15 | Projector-Whiteboard-Camera System for Remote Collaboration |
2016-12-15 | Multimodal Presence Detection |
2016-12-15 | Whiteboard Streaming |
2016-12-15 | Découvrez le nouveau Microsoft Translator |
2016-12-13 | VisualPanel Demo (short) |
2016-12-13 | Visual Screen Demo |
2016-12-13 | Zhengyou Zhang on CBS Saturday Early Show with Renay San Miguel |
2016-12-13 | VisualPanel Demo |
2016-12-13 | Discover the new Microsoft Translator |
2016-12-09 | Pre-Touch Sensing for Mobile Interaction |
2016-12-08 | RIMES: Embedding Interactive Multimedia Exercises in Lecture Videos |
2016-12-07 | Touch-Sensing Input Devices |