三维运动图像多参考帧边缘差异动态分割仿真  

Dynamic Segmentation Simulation of Multi-reference Frame Edge Difference in 3D Motion Image

作　　者：李波 弋玮玮[1] LI Bo;YI Wei-wei(Chongqing Institute of Engineering,Chongqing 400900,China;Southwest University,Chongqing 400715,China)

机构地区：[1]重庆工程学院,重庆400900 [2]西南大学,重庆400715

出　　处：《计算机仿真》2020年第6期365-368,373,共5页Computer Simulation

基　　金：重庆市教育科学规划项目(2017-GX-142)。

摘　　要：传统视频运动对象分割方法虽然具有较高的分割精确度,但是无法满足实时性需求。提出一种三维运动图像多参考帧边缘差异动态分割方法。首先根据多参考帧边缘差异动态提取运动目标所在区域,利用小波变换法对三维运动图像进一步实施分解,获得1个低频子图像和3个高频子图像,分别得到运动目标主要特征与细节特征,再将待处理图像的RGB空间转换为HSV空间,并根据色度、亮度以及饱和度提取到运动目标封闭的轮廓图,然后运用图像内动态部分和静态部分两者间的帧差掩模图像联系,把图像分成3个不同形态的部分,最终使用边缘检测算子对运动目标的边缘准确分割,从而获得高精度的分割结果。仿真结果表明:所提方法的分割精度更高,具有准确性、实时性和优质的鲁棒性。Although traditional method has high segmentation accuracy,it cannot meet the real-time requirements.Therefore,a dynamic segmentation method for multi-reference frame edge difference in three-dimensional moving image was proposed.Firstly,the region of moving object was extracted dynamically according to the edge difference of multi-reference frames.Secondly,the three-dimensional moving image was further decomposed by wavelet transform.After that,a low-frequency sub-image and three high-frequency sub-images were obtained.The main features and details of moving object were also obtained.And then,the RGB space of image that would be processed was converted into HSV space.According to the color,brightness and saturation,the closed contour image of moving object was extracted.Moreover,the frame difference between the dynamic part and the static part in image was used to mask the image correlation and the image was divided into three different parts.Finally,the edge detection operator was used to segment the edge of moving object accurately,and thus to obtain the segmentation result with high precision.Simulation results show that the proposed method has higher segmentation accuracy.Furthermore,this method has high accuracy,excellent real time performance and good robustness.

关 键 词：三维运动图像 多参考帧边缘 差异动态分割 边缘检测算子 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]