Human body segmentation based on independent component analysis with reference at two-scale superpixel

Human body segmentation based on independent component analysis with reference at two-scale superpixel
复制标题

参考两尺度超像素的基于独立分量分析的人体分割

DOI:
10.1049/iet-ipr.2010.0367
复制
发表时间:
2012-10
影响因子:
2.3
通讯作者:
Chen, Y.-W
Chen, Y.-W
中科院分区:
计算机科学4区
文献类型:
--
作者:
Li, S;Lu, H.-C;Ruan, X;Chen, Y.-W

文献摘要

参考文献

被引文献

相似文献

本文提出了一种基于参考独立分量分析(ICA-R)的二尺度超像素静态图像人体分割方法。在这项工作中,任务主要分为躯干和下半身的恢复。利用检测到的人脸,在基于一尺度超像素的增强变形躯干模型估计的粗躯干区域中获得躯干的参考信号。在第二尺度超像素上,根据分割的躯干来估计臀部区域,以作为下半身参考。在我们的数据集上的实验表明,该方法具有鲁棒性,可以准确地在各种姿势、背景和服装的图像中分割人体。
In this study, a novel method to segment human body in static image is proposed based on independent component analysis with reference (ICA-R) at two-scale superpixel. In this work, the task is mainly decomposed into torso and lower body recovery. With the detected face, we obtain the reference signal of torso in the coarse torso region estimated by an augmented deformable torso model on the basis of the first-scale superpixel. The hip region is estimated based on the segmented torso for the lower body reference at the second-scale superpixel. Experiments on our dataset show that the proposed approach is robust and can accurately segment human body in images with a variety of poses, backgrounds and clothing.
DOI: 10.1016/s0893-6080(00)00026-5
发表时间: 2000-05-01
期刊: NEURAL NETWORKS
影响因子: 7.8
作者:
Hyvärinen, A;Oja, E
通讯作者: Oja, E
DOI: 10.1109/34.868688
发表时间: 2000-08-01
影响因子: 23.6
作者:
Shi, JB;Malik, J
通讯作者: Malik, J
DOI: 10.1109/tpami.2007.1062
发表时间: 2007-08-01
影响因子: 23.6
作者:
Gavrila, Dariu M.
通讯作者: Gavrila, Dariu M.
DOI: 10.1109/cvpr.2004.204
发表时间: 2004-06
期刊: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
影响因子: --
作者:
Greg Mori;Xiaofeng Ren;Alexei A. Efros;Jitendra Malik
通讯作者: Greg Mori;Xiaofeng Ren;Alexei A. Efros;Jitendra Malik
DOI: 10.1109/cvpr.2008.4587420
发表时间: 2008-06
期刊: 2008 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
M. Maire;Pablo Arbeláez;Charless C. Fowlkes;Jitendra Malik
通讯作者: M. Maire;Pablo Arbeláez;Charless C. Fowlkes;Jitendra Malik