本系統目的在於實現以智慧家庭概念為基礎的家電監控系統，除了可遠端即時監控家電狀態與電量使用紀錄之外，更結合了幼兒與寵物防護機制，來達到具備便利性、自動化、能源監控與安全性的系統功能。
為達到家電監控功能，本系統針對家中插座進行監控，監控者可隨時以手持裝置遠端查看插座目前開關與鎖定狀態、電量圖表、估算電費、警訊通知，並藉由定時開關設定，以達到便利與節能之目的。監控系統共可分為四大模組，分別為智慧插座裝置、家用負載監控器、資料庫伺服器、以及Android遠端監控軟體，其中以資料庫伺服器為資料儲存控制核心，除了智慧插座裝置與家用負載監控器為透過ZigBee傳輸插座資訊外，其他模組皆以TCP/IP網路協定與資料庫做連線溝通。
而幼兒與寵物防護機制為透過輸入影像，偵測是否有幼兒或寵物進出房間，並對特定插座做鎖定控制，避免高危險或高耗能之家電被誤觸後發生危險或造成電能的浪費，藉此加強監控系統的能源控管與安全性。偵測流程為移動物偵測、移動物資訊分析與目標物進出辨識，其中移動物偵測方式以Codebook背景模型為基礎，經修正並加入陰影去除程序後應用之，並藉由目標物之位移、高度與寬高比計算，來辨識目標物進出事件以及目標物是否為幼兒或寵物。由實驗結果顯示，此模組可準確偵測出幼兒與寵物進出事件，其執行速度為8.6 ms/frame，推論可應用於即時系統中。
本研究之智慧插座監控系統成功結合了安全防護機制，除了能夠控制插座開關外，藉由電量圖表可輕易比較各插座的消耗電量，並透過警訊機制即時顯示通知於監控畫面中，如插座使用電量超過設定值、幼兒與寵物進出監控區域，最後利用自動鎖定機制達到家電安全防護效果，為家電自動化提供一個發展基礎。

As the internet and communication technologies become mature, the design and development smart homes have been more and more popular in recent years. In order to control household appliances and monitor the power consumption remotely, this thesis designs a smart remote monitoring system for sockets, which can control the socket switch and measure the power consumption. Through monitoring the power consumption, the system’s users can adjust their behavior of using appliances and save some power.
The smart socket monitoring system provides some special features as follows.
1. Friendly graphic user interface.
2. Monitoring sockets by groups, which simplifies the management.
3. Comparing monthly power consumption and fees among sockets and groups by graphics.
4. Displaying immediate alert notification to users via mobile device.
In addition, our system adds children and pets protection design into the smart sockets monitoring system to enhance the safety of appliances using. The method of detecting moving objects is based on the Codebook background model through input videos. When children or pets enter the sockets monitoring area, the detection model would send the alert message to server and lock the related sockets. In this way, the accidents which may be caused by inappropriate use ways can be prevented.
To conclude, our system shows that we can integrate power monitoring with security functions, and it can serve as the base to the future home automation system.

[1] B. Shoushtarian, and H. E. Bez, “A practical adaptive approach for dynamic background subtraction using an invariant color model and object tracking,” Pattern Recognition Letters, vol. 26, no. 1, pp. 5-26, 2005.
[2] E. R. Davies, “Machine Vision: Theory, Algorithms, Practicalities,” 3rd Edition, Morgan Kaufmann, San Francisco, 2005.
[3] E. Salvador, A. Cavallaro, and T. Ebrahimi, “Cast Shadow Segmentation Using Invariant Color Features,” Computer Vision and Image Understanding, vol. 95, issue 2, pp. 238-259, Aug. 2004.
[4] G Sharma, “Digital Color Imaging”, Journal of Image Processing, IEEE Transactions on Vol. 6, Issue 7, pp. 901-932, 1997.
[5] J. R. Parker, “Algorithms for Image Processing and Computer Vision,” 2nd Edition, wiley Publishing, Inc., New York, 2010.
[6] K. Kim, T. H. Chalidabhongse, D. Harwood, and L. S. Davis, “Background modeling and subtraction by codebook construction,” International Conference on Image Processing, vol. 5, pp. 3061-3064, 2004.
[7] M. Heikkila, M. Pietikainen, and J. Heikkila, “A Texture-Based Method for Detecting Moving Objects,” Proceedings of British Machine Vision Conference, British, pp. 187-196, 2004.
[8] S. Pumrin, “A framework for dynamically measuring mean vehicle speed using un-calibrated cameras,” Technical report UWEETR-2002-0005, Univ. Washington Dept. of Elect. Engr., 2002.
[9] Shang-Wen Luan, Jen-Hao Teng, Shun-Yu Chan, and Lain-Chyr Hwang,” Development of a Smart Power Meter for AMI Based on ZigBee Communication,” in proc. IEEE the 8th International Conference on Power Electronics and Drive Systems, PEDS, 2009.
[10] T. H. Chalidabhongse, K. Kim, D. Harwood and L. Davis, “A Perturbation Method for Evaluating Background Subtraction Algorithms”, Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS), 2003.
[11] T. Horprasert, D. Harwood, and L.S. Davis, “A statistical approach for real-time robust background subtraction and shadow detection,” IEEE Frame-Rate ApplicationsWorkshop, Kerkyra, Greece, 1999.
[12] T. Kohonen, “Improved versions of learning vector quantization,” International Joint Conference on Neural Networks(IJCNN '90), vol. 1, pp. 545-550 1990.
[13] Z. Yi, and F. Liangzhong, “Moving object detection based on running average background and temporal difference,” Intelligent Systems and Knowledge Engineering (ISKE), pp. 270-272, 2010.
[14] 何信威，“智慧插座電源偵測系統”，電子工程系，國立臺灣科技大學，台北市，2010。
[15] 昨日,“資料結構操作與運算-CvRect,CvBox2D資料結構”, http://yester-place.blogspot.tw/2008/07/cvrectcvbox2d.html, Last accessed 2013.
[16] 高誌謙，“基於Android與ZigBee之智慧家庭設計與實現”，電訊工程系，國立高雄海洋科技大學，高雄市，2011。
[17] 張振榮，“智慧型系統在移動物體辨識上之應用”，資訊工程系，國立大同大學，台北市，2005。
[18] 陳祥瑋，“以異質多網建構居家電能環控系統”，電訊工程系，聖約翰科技大學，台北市，2012。
[19] 陳源謙，“Ubuntu Linux管理與架站實務”，博碩出版社，2010。
[20] 彭亦暄、陳彥文，“Android應用程式開發與設計實務”，博碩出版社，2013。
[21] 劉冠廷，“基於運動歷史影像實現行人追蹤與計數系統”，電子工程系，國立臺灣科技大學，台北市，2010。
[22] 蔡志明、盧傳富、李立夏，“精通Qt4視窗介面程式開發與設計”，博碩出版社，2011。
[23] 戴悅如，“監控影像之行人攜帶物偵測”，電子工程系，國立臺灣科技大學，台北市，2013。
[24] 顏春煌，“資料庫系統原理與應用”，第三版，碁峰出版社，2013。
[25] 鐘國亮，“影像處理與電腦視覺”，東華出版社，2006。