一种基于对称差分和背景消减的运动检测方法

该文提出一种综合利用对称差分和背景消减来进行运动检测的方法。首先通过建立一个可靠的背景更新模型，由背景消减法得到基本准确的前景图像，然后和对称差分法得到的差分图像综合，得到完整可靠的运动目标图像，最后用形态学滤波和连通区域面积检测进行后处理，以消除噪声和背景扰动带来的影响，并用区域填充算法来填补目标区域的小孔，从而将视频序列中的运动目标比较可靠地检测出来。实验结果表明，该方法快速、准确，有一定的实际应用价值。

A Motion Detection Algorithm Based on Background Subtraction and Symmetrical Differencing

A novel motion detection algorithm which employs adaptive background su btraction and symmetrical differencing is presented in this paper. A modified se lective updating model is proposed as the reliable adaptive background updating method, and we combine the background subtraction with symmetrical differencing to detect the motion information. After the motion detection operation, morpholo gic filtering and connected region area measurement are introduced to suppress t he noise and solve the background disturbance problem. Then the area filling alg orithm is used to fill the small hole in the detected object. Finally the moving objects are extracted reliably. The result of the experiment demonstrates that the pres ented algorithm runs quickly and veraciously.