OALib Journal期刊
ISSN: 2333-9721
费用:99美元
|
|
|
红外遮挡人体目标模板图像的MeanShift分割算法
DOI: 10.11834/jig.20090925
Keywords: 红外图像,遮挡人体目标分割,均值漂移,分水岭算法
Abstract:
提出了一种红外图像中遮挡人体目标的分割方法。首先通过传统的阈值选取方法或直方图聚类等红外图像分割的方法,获取遮挡区域目标的二值化模板。用目标像素在模板中的相对行列坐标作为特征集使用MeanShift算法分别计算各像素在行列方向的收敛位置并使用复数向量进行联合表达,再次以所有的复数向量作为特征集进行MeanShift聚类,根据各像素位置对应的复数向量所属类别对其进行划分,完成遮挡目标的分割。与分水岭算法相比,该算法的分割结果完整保留了目标模板的外形,并且可以通过MeanShift带宽参数的选择完成不同精细程度的分割。
References
[1] | 陈东.黄勇杰.沈振康 红外图像目标分割方法研究 [J].-系统工程与电子技术2002(1)
|
[2] | Yon Ting-jin,Guo Yong-cal,Gao Chao,Human detection in far-infrared images baaed on histograms of maximal oriented energy map,北京,2007.
|
[3] | Fang Y,Yamada K,Ninomiya Y,Comparison between infraredimage-baaed and visible-image-baaed approaches for pedestrian detection,Columbus,OH,USA,2003.
|
[4] | Yang Xuan,Pei Ji-hong,Head location based on fuzzy weighted projection histogram in infrared thermal sequences,HongKong,China,2004.
|
[5] | Meyer,Fernand,Topographic distance and watershed lines,SIGNAL PROCESSING,1994(1).
|
[6] | Roerdink J B T M,Meijster A,The watershed transform:definitions,algorithms and parallelization strategies,FUNDAMENTA INFORMATICAE,2000(1-2).
|
[7] | Eomaniciu D,Meet P,Mean shift analysis and applications,Kerkyra,Corfu,Greece,1999.
|
[8] | Comaniciu D,Meer P,Mean Shift:a robust approach toward feature space analysis,IEEE Transactions on Pattern Analysis and Machine Intelligence,2002(5).
|
[9] | Chcn H,Meer P,Robust computer vision through kernel density estimation,Copenhagen,Denmark,2002.
|
[10] | Comanieiu D,Meer P,Robust analysis of feature spaces:color image segmentation,Puerto Rico,1997.
|
[11] | Chen J,Pappas T,Mojsilovic A,Adaptive image segmentation based on color and texture,Rochester,NY,USA,2002.
|
Full-Text
|
|
Contact Us
service@oalib.com QQ:3279437679 
WhatsApp +8615387084133
|
|