在官方示例中,Motion-Based Multiple Object Tracking和Using Kalman Filter for Object Tracking都使用了下面两个算法进行物体的识别
1、vision.ForegroundDetector
原理:The ForegroundDetector System object compares a color or grayscale video frame to a background model to determine whether individual pixels are part of the background or the foreground. It then computes a foreground mask. By using background subtraction, you can detect foreground objects in an image taken from a stationary camera.
将每一帧和一个背景帧进行对比,判断每个像素点是属于背景,还是属于罩子(罩子就是不属于背景的意思)。通过这种对比,就能识别出后面帧中运动的物体。适用范围:一个固定的摄像头所拍摄的视频。
算法:Gaussian mixture models (GMM).,呵呵,又是高斯。
使用方法见官方文档、示例。
参数,也是最重要的部分:
AdaptLearningRate,默认true,解释:
Enables the object to adapt the learning rate during the period specified by the NumTrainingFrames property. When you set this property to