motion object mask 运动对象掩模
Finally, the video object with accurate boundaries is extracted by integrated the motion mask and regions segmented by multi-resolution watershed.
最后，视频对象的准确边界的提取综合运动口罩和地区分割多分辨率的分水岭。
The original motion mask image can be extracted from the high frequency frames which resulting from temporal decomposition of the original video sequence by wavelet transform.
将视频序列进行时间轴一维小波变换，利用变换后的高频帧信息提取出初步的运动掩模图像；
Firstly, a rough motion mask is obtained by introducing a motion area segmentation method based on an improved accumulative frame- difference algorithm and optimal threshold segmentation.
利用小波包分析算法提取出单帧图像的边缘信息并获得细化的目标区域边缘图；
应用推荐