This dissertation presents an efficient multilayer background modeling approach to distinguish among midground objects, the objects whose existence occurs over varying time scales between the extremes of short-term ephemeral appearances (foreground) and long-term stationary persistences (background). Traditional background modeling separates a given scene into foreground and background regions. However, the real world can be much more complex than this simple classification, and object appearance events often occur over varying time scales. There are situations in which objects appear on the scene at different points in time and become stationary; these objects can get occluded by one another, and can change positions or be removed from the scene. Inability to deal with such scenarios involving midground objects results in errors, such as ghost objects, miss-detection of occluding objects, aliasing caused by the objects that have left the scene but are not removed from the model, and new objects’ detection when existing objects are displaced. Modeling temporal layers of multiple objects allows us to overcome these errors, and enables the surveillance and summarization of scenes containing multiple midground objects.

我們提出的智慧型睡眠監測系統，是基於影像分析技術進行睡眠品質觀測，並利用所得到的數據來推斷最佳的喚醒時間。此系統命名為iWakeUp，利用非接觸式的方法來收集影像資料並進行後續處理，此裝置將被安裝在一般的臥室來幫助睡眠者，以期成為增進智慧家庭生活品質的一環。在此論文中，我們將會描述iWakeUp的各個模組包括測定動作量、推斷睡眠階段乃至於如何建立喚醒機制。更特別的是，我們考慮了喚醒時間與喚醒機制的關係，於較早的時間喚醒必須具有更高的信心度，否則將付出較大的代價，反之亦然。另外為了處理晨間臥室中的光影變化，不同的背景模型也已被整合測試，以期讓系統可以提升長時間觀測的準確度。最後，我們也進行了使用iWakeUp的臨床實驗，結果指出使用iWakeUp喚醒的睡眠者具有較低的嗜睡感與更好的活力。 / We present a video-based monitoring system to determine the sleep status and optimal wakeup time in this thesis. We envision a smart living space in which a data collection and processing module named iWakeUp is installed in the bedroom to record and monitor sleep in a non-invasive manner. We describe the overall structure of the iWakeUp system, including the procedure to measure amount of motion, the method for inferring wake/sleep status from the acquired video and the logics for deciding the optimal wakeup time. In particular, a time-dependent decision rule has been incorporated to account for unequal penalties when classification error occurs. Furthermore, various background modeling techniques have been examined to address lighting changes at dawn in the bedroom for long-term monitoring. Validation experiments are carried out to compare the alertness level upon awakening with/without reported a lower level of sleepiness and higher level of vigorousness in comparison to the control group.