Deep Human Pose Estimation Method Based on Mixture Articulated Limb Model

被引：0

作者：

Liu B. ^{[1
,2
]}

Li Z. ^{[1
,2
]}

Ke X. ^{[1
,2
]}

机构：

[1] College of Mathematics and Computer Science, Fuzhou University, Fuzhou

[2] Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, Fuzhou University, Fuzhou

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2019年 / 32卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Deep Convolutional Neural Network; Deep Learning; Graphical Model; Human Pose Estimation;

D O I：

10.16451/j.cnki.issn1003-6059.201902001

中图分类号：

学科分类号：

摘要：

A flexible mixture model is proposed to solve the problems of human pose estimation. The model is composed of joint appearance and inner-joint relationship models, and it is trained through a deep convolutional neural network (DCNN). Firstly, a graphical model is constructed to represent joints and limbs of human body. Secondly, images are decomposed into several image blocks centered on the joints and used as training input data. Finally, a multiple classification DCNN network is obtained to perform human pose estimation.The proposed method is more flexible for human body representation, and the detection rate of joint points and the correct detection rate are effectively improved. © 2019, Science Press. All right reserved.

引用

页码：97 / 107

页数：10

共 20 条

[1]

Baradel F., Wolf C., Mille J., Human Action Recognition: Pose-Based Attention Draws Focus to Hands, Proc of the IEEE International Conference on Computer Vision Workshop, pp. 604-613, (2017)

[2]

Vasileiadis M., Malassiotis S., Giakoumis D., Et al., Robust Human Pose Tracking for Realistic Service Robot Applications, Proc of the IEEE International Conference on Computer Vision Workshop, pp. 1363-1372, (2017)

[3]

Gong K., Liang X.D., Zhang D.Y., Et al., Look into Person: Self-supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 932-940, (2017)

[4]

Yang Y., Ramanan D., Articulated Pose Estimation with Flexible Mixtures-of-Parts, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1385-1392, (2011)

[5]

Chen X.J., Yuille A., Articulated Pose Estimation by a Gra-phical Model with Image Dependent Pairwise Relations, Advances in Neural Information Processing Systems 27, pp. 1736-1744, (2014)

[6]

Fischler M.A., Elschlager R.A., The Representation and Matching of Pictorial Structures, IEEE Transactions on Computers, 22, 1, pp. 67-92, (1973)

[7]

Johnson S., Everingham M., Learning Effective Human Pose Estimation from Inaccurate Annotation, Proc of the 24th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1465-1472, (2011)

[8]

Tsochantaridis I., Hofmann T., Joachims T., Et al., Su-pport Vector Machine Learning for Interdependent and Structured Output Spaces, Proc of the 21st International Conference on Machine Learning, (2004)

[9]

Chen X.J., Yuille A.L., Parsing Occluded People by Flexible Compositions, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3945-3954, (2015)

[10]

Chu X., Ouyang W.L., Li H.S., Et al., Structured Feature Lear-ning for Pose Estimation, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4715-4723, (2016)

← 1 2 →