理學院: 數學研究所指導教授: 陳宜良黃乾宗Huang, Chien-TsungChien-TsungHuang2017-03-062018-06-282017-03-062018-06-282016http://ntur.lib.ntu.edu.tw//handle/246246/276751在雜亂的環境中，從背景模型穩健地分割前景是困難的一個難題。我們提出能穩健地推定背景和在這樣的環境中檢測感興趣區域的方法。大部分舊有方法是利用大量的疊代運算去計算前景與背景的能量模型，但這樣會很依賴好的初始條件，並耗費大量的運算時間以分析影像。針對這些限制，在此提出了有效率的能量模型計數基於馬可夫隨機場為主要架構。首先建立有效前景預估，再來更精細地標記前景背景，最後得到快於其他方法的前景背景分離。Robust foreground object segmentation via background modelling is a difficult problem in cluttered environments, where obtaining a clear view of the background to model is almost impossible. We propose a method capable of robustly estimating the background and detecting regions of interest in such environments. Most existing techniques thus adapt an iterative approach for foreground and background appearance modeling. However, these approaches may rely on good initialization and can be easily trapped in local optimal. In addition, they are usually time consuming for analyzing videos. To address these limitations, we propose an efficient appearance modeling technique for automatic primary video object segmentation in the MRF framework. We create an efficient initial foreground estimation. Then we use foreground-background labelling refinement. Finally, we can get the foreground from video faster than other approaches.論文使用權限: 不同意授權馬可夫隨機場光流法超像素內外分割圖能量函數Markov random fieldsOptical flowSuperpixelInside-outside mapsEnergy functionthesis10.6342/NTU201601244