一种新型自适应嵌入式流形去噪视频运动目标分割算法

A New Adaptive Embedded Manifold Denoising Algorithm for Video Motion Object Segmentation

针对目前运动目标分割算法在复杂场景中适应性较差,时间复杂度较高等缺陷,提出一种新的运动目标分割算法,该算法通过自适应流形去噪实现刚性和非刚性对象的运动分割.首先,引入一种自适应核空间,如果两个特征轨迹属于同一刚性对象,则将其映射到相同点上;然后,采用一种基于自适应内核的嵌入式流形去噪算法,分割出刚性和非刚性对象的运动;最后,在多个数据集上与几种传统算法进行对比实验.实验结果表明,该算法在不同场景中均能取得更好的分割与跟踪效果.

Due to the algorithm for motion object segmentation had poor adaptation of complicated scene,and the time complexity was too high,we proposed a new motion object segmentation algorithm,which used adaptive manifold denoising to achieve motion segmentation between rigid and non-rigid objects.We first introduced an adaptive kernel space in which two feature trajectories were mapped to the same point if they belonged to the same rigid object.Then,we adopted an embedded manifold denoising algorithm based on the adaptive kernel to segment the motions of rigid and non-rigid objects.Finally,we did contrast experiments with several traditional algorithms on several datasets.Experimental results show that the algorithm can achieve better segmentation and tracking effects in different scenes.