利用非侵入性環境感測器達成智慧型家庭下之多人行為辨識

Multiple-Resident Activity Recognition Using Pervasive Non-obtrusive Sensors in a Smart Home Environment

徐國鐘(Kuo-Chung Hsu)

指導教授 ： 傅立成

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2010年)

https://doi.org/10.6342/NTU.2010.01888

摘要

從環境中的資訊辨識出使用者當下的行為是挑戰的，為了提供使用者更合適的服務，了解使用者的行為將能更正確地提供使用者所需要的服務。在過去的研究裡，為了簡化問題的複雜度，往往有家中僅有單一居住者的假設。本文的目標是建立一個系統能學習多位居住者的行為模式，並能即時的辨識家中各個居住者的行為。
本文的貢獻主要有以下三點：第一，茲因在非侵入性環境中資訊的不充足，多人行為辨識的資料鏈結並不容易被分類。於是我們嘗試設計能夠推論資料鏈結的模型；第二，由於每個居住者的行為有可能被其他居住者影響，人與人之間的互動必須被納入考慮，這樣的動機使我們提出了一個多人行為辨識模型；第三，手動標記資料鏈結是一個十分耗費人力的工作，特別是在多人環境中，因此我們實作了一個自動標記方法。

關鍵字

智慧家庭 ； 行為辨識 ； 多居住者 ； 條件隨機場 ； 資料鏈結 ； 動態貝氏網路

並列摘要

Reliable recognition of activities from cluttered sensory data is challenging and important for a smart home to provide more desirable services. Traditionally, most of prior works often assume that there is always only one resident at home for the purpose of simplification of solving a complicated problem regarding multiple-resident activity recognition. Therefore, the goal of this thesis is to build a system which learns multiple-resident activity models to facilitate reliable activity recognition of each resident.
The main contribution of this thesis is three-fold. Firstly, due to the insufficiency of information in an environment using pervasive non-obtrusive sensors, data association for multiple-resident activity recognition is hard to be identified. Therefore, we aim to design a model which can infer the data association. Secondly, interactions among residents should be modeled since the activity of one resident may be influenced by another, and this concern motivates us to propose a multiple-resident activity recognition system which can adapt to the interaction between residents. Thirdly, because manually annotating data association is laborious, especially in an environment involving multiple residents, we design a mechanism which can automatically annotate the data association.

並列關鍵字

Smart Home ； Activity Recognition ； Multiple Residents ； Conditional Random Field (CRF) ； Data Association ； Dynamic Bayesian Network (DBN)

參考文獻

[2] L. McCowan, D. Gatica-Perez, S. Bengio, G. Lathoud, M. Barnard, and D. Zhang, "Automatic Analysis of Multimodal Group Actions in Meetings," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, pp. 305-317, 2005.

[3] N. Nguyen, S. Venkatesh, and H. Bui, "Recognising Behaviours of Multiple People with Hierarchical Probabilistic Model and Statistical Data Association," Proceedings of British Machine Vision Conference, Oxford, 2005.

[4] D. H. Wilson and C. G. Atkeson, "Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors," Proceedings of the 3rd International Conference on Pervasive Computing, Munich, Germany, pp. 62-79, 2005.

[5] G. Singla, D. Cook, and M. Schmitter-Edgecombe, "Recognizing Independent and Joint Activities among Multiple Residents in Smart Environments," Journal of Ambient Intelligence and Humanized Computing, vol. 1, pp. 57-63, 2010.

[6] C.-H. Lu, C.-L. Wu, and L.-C. Fu, "Hide and Not Easy to Seek: A Hybrid Weaving Strategy for Context-aware Service Provision in a Smart Home," Proceedings of IEEE Asia-Pacific Services Computing Conference, Yilan, Taiwan, 2008.