摘要：

提出了一种基于小波变换和运动边缘检测的自动视频对象分割方法。该方法对相邻帧分别进行二维小波变换，在小波域进行变化检测和Canny边缘提取，返回空间域后得到鲁棒的相邻帧差分边缘模板。结合当前帧边缘、背景边缘和前一帧的运动边缘，检测出当前帧对象的运动边缘，从而实现对视频对象的提取。通过实验验证，该算法对目标的整体运动和局部形变都有较强的适应性。此外，算法还具有快速、简便、准确性高的特点。

关键词: 视频对象, 小波变换, 运动边缘

Abstract:

An automatic video object segmentation algorithm based on wavelet transform and moving edge detection is proposed. Firstly, the new method makes the two-dimensional wavelet transform for two successive frames. Then change detection method and Canny edge detection are applied in wavelet domain. After merging the different edge masks with the union operation, the robust difference edge map of the inter-frame difference image can be obtained. Combining with the current frame edge map, background edge map and previous frame’s moving edge, the current frame’s moving edge can be calculated to extract video object. The algorithm is robust to the entire motion and local deformation of object. The experiment results show that the proposed algorithm is fast, simple and accurate.

Key words: Video object, Wavelet transform, Moving edge