基于帧差法和边缘检测法的视频分割算法
|
摘要
针对目前常用的视频分割方法易受到噪声、亮度突变的影响,很难提取出完整的运动目标这一问题,提出一种基于帧差法和边缘检测法相结合的视频分割算法。该算法首先对连续三帧图像进行差分得到运动区域,然后对当前帧进行Kir-sch边缘检测得到边缘图像,综合二者的检测结果得到更为精准的运动对象边缘。采用边缘连接算法完成对断裂边缘的连接,最后通过区域填充得到运动目标掩模图像,从而分割出完整的运动目标。实验表明,该算法可以实时有效地将运动物体从视频序列中自动地分割出来。
As the commonly-used methods of video segmentation are easily affected by noise and light,it is difficult to extract a complete moving target,so a new video object segmentation algorithm combining edge detection and inter-frame difference is proposed.Firstly,the difference of three consecutive frames is used to obtain motion regions,and then the boundary of current frame is defined by using Kirsch edge detection.The two test results are synthesized to get the more accurate edge of moving objects.Edge linking algorithm is used to connect the breaking edge.Finally,the template of moving object is formed through area filling,and thus a complete moving object is obtained.Experimental results show that this algorithm can effectively segment accurate moving objects in real time.
As the commonly-used methods of video segmentation are easily affected by noise and light,it is difficult to extract a complete moving target,so a new video object segmentation algorithm combining edge detection and inter-frame difference is proposed.Firstly,the difference of three consecutive frames is used to obtain motion regions,and then the boundary of current frame is defined by using Kirsch edge detection.The two test results are synthesized to get the more accurate edge of moving objects.Edge linking algorithm is used to connect the breaking edge.Finally,the template of moving object is formed through area filling,and thus a complete moving object is obtained.Experimental results show that this algorithm can effectively segment accurate moving objects in real time.
引文
[1]PATRAS I,HENDRIKS E A,LAGENDIJK R L.Video segmentationby MAP labeling of watershed segments[J].IEEE Transactions onPattern Analysis and Machine Intelligence,2001,23(3):326-332.
[2]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图像图形学报,2008,13(4):729-734.
[3]THOMAS MEIER,KINGN.Video segmentation for content-basedcoding[J].IEEE Trans on Circuits and Systems for Video Tech-nology,1999,9(8):1190-1201.
[4]杨莉,李玉山.复杂背景下的多运动目标轮廓检测[J].电子与信息学报,2005,2(2):306-309.
[5]吕国亮,赵曙光,赵俊.基于三帧差分和连通性检验的图像运动目标检测新方法[J].液晶与显示,2007,22(1):87-92.
[6]KIRSCH R A.Computer determination of the constituent structureof biological images[J].Computers in Biomedical Research,1971,4(1):315-328.
[7]鲁雯,张光玉,程运福,等.一种改进的Kirsch边缘检测方法[J].医疗设备信息,2007(12):10-12.
[8]RUGUMIRA G,高静怀,汪玲玲,等.基于方向模板的保持边缘平滑后地震图像的不连续性检测[J].地球物理学进展,2008(5):1398-1405.
[9]HARITAOGLU I,HARWOOD D,DAVIS L S.W4:Real-time surveil-lance of people and their activities[J].IEEE Transactions on PatternAnalysis and Machine Intelligence,2000,22(8):809-830.
[2]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图像图形学报,2008,13(4):729-734.
[3]THOMAS MEIER,KINGN.Video segmentation for content-basedcoding[J].IEEE Trans on Circuits and Systems for Video Tech-nology,1999,9(8):1190-1201.
[4]杨莉,李玉山.复杂背景下的多运动目标轮廓检测[J].电子与信息学报,2005,2(2):306-309.
[5]吕国亮,赵曙光,赵俊.基于三帧差分和连通性检验的图像运动目标检测新方法[J].液晶与显示,2007,22(1):87-92.
[6]KIRSCH R A.Computer determination of the constituent structureof biological images[J].Computers in Biomedical Research,1971,4(1):315-328.
[7]鲁雯,张光玉,程运福,等.一种改进的Kirsch边缘检测方法[J].医疗设备信息,2007(12):10-12.
[8]RUGUMIRA G,高静怀,汪玲玲,等.基于方向模板的保持边缘平滑后地震图像的不连续性检测[J].地球物理学进展,2008(5):1398-1405.
[9]HARITAOGLU I,HARWOOD D,DAVIS L S.W4:Real-time surveil-lance of people and their activities[J].IEEE Transactions on PatternAnalysis and Machine Intelligence,2000,22(8):809-830.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心