一种基于小波域的运动估计方法

A Motion Estimation Algorithm Based on the Wavelet Domain

提出了一种基于多尺度边缘检测(MED)与连续小波变换(CWT)相结合的运动目标估计方法。首先,利用多尺度边缘检测算法,得到抗噪性好、边缘连续清晰的运动目标边缘图像。然后,利用连续小波变换把目标序列图像映射到运动状态参数空间。该方法同时拥有MED和CWT的优良特性。实验表明,该算法是对旋转、遮挡和有噪等复杂运动目标进行运动估计的有效方法。

This paper describes a novel motion object detection and tracking algorithm based on the Multiscale Edges Detection (MED) and Continuous Wavelet Transform (CWT). Multiscale representations are very effective for analyzing the information content of images. First, moving object multiscale edges are detected and characterized from the local maxima of a wavelet transform. Then, the CWT is used to map the input signal space to a motion parameters space. It is designed so as to possess simultaneously the properties of MED and CWT. Experimental results show that the proposed algorithm is effective with robustness for noise, rotation and occlusions.