Using Camshift And Optical Flows Essay

1558 Words Dec 20th, 2016 7 Pages
In the step of object tracking, we estimated the object poses and object information using CamShift and optical flows. Each of the object pose is evaluated and confirmed by object information, comprising several elements such as feature points, descriptors, and object within the sub-window, the expected object pose, and its histogram. The tracked objects are estimated from the credibility for learning of object information, and is described below.
In this study, to evaluate the credibility of the object, information of the tracked object is compared to the initial information, which is detected by the previous detection module. This information comprises two parts: the feature points and its histogram, indicating a standard information, named Level-1. This information is used in defining sub-windows, morphological analysis of the object, and labeling the feature points. When sub-windows are selected, the histogram of the expected object is compared to the standard object’s histogram, based on CamShift and optical flow. Each of the sub-window is divided into positive and negative according to the highest rate of histogram, and we select and update the information of the object histogram by the positive sub-windows, including the matching key points. Figure 7 shows the sub-windows containing the highest rate of the object information.

Then, to define the shape of the object, morphological analysis of the object is performed from computing the distribution of positive and…

Related Documents