自適性背景更新的動態偵測系統

Abstract

本篇文章提出一個簡單且強健的方法在即時畫面或預錄影像中進行移動物件的偵測。有別於過去利用統計的方式訓練出背景模型來偵測移動物件，我們採用一個複雜度較低且不需要預先建立背景圖的方式對於背景進行修補及更新。再透過背景消去的方式來找出畫面中移動的物件資訊。在所提出的背景更新方式下結合物體的運動資訊來動態的決定適當的更新率，不但可以準確的更新背景還可以適用於移動式的攝影機。對於許多即時偵測系統或是監控環境(如：停車場)可以提供較好的方法。

We proposed a simple and robust method to detect moving objects in real-time video. Instead of using statistics to train out a background model in the past, we use a method which is less complexity and don’t need any pre-saved background images to patch and update the background. Then find out the motion information of moving objects in the frames by background subtraction. The proposed method also can determine a proper updating rate dynamically by combining the motion information of the moving objects, which can not only update the background precisely but also suitable for the PTZ camera and provide a better choice for many real-time detection system or surveillance system. (Ex: a parking lot)