A Novel Joint Chaining Graph Model for Human Pose Estimation on 2D Action Videos and Facial Pose Estimation on 3D Images

Full Text (PDF, 654KB), PP.21-32

Views: 0 Downloads: 0

Author(s)

D.Ratna kishore 1 M. Chandra Mohan 2 Akepogu. Ananda Rao 3

1. Department of Computer Science & Engineering Andhrapradesh,India.

2. Department of Computer Science & Engineering JNTUH, Hyderabad, Telangana State, India

3. Academic & Planning JNTUA,anantapuramu, Andhrapradesh,India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2017.03.03

Received: 23 Nov. 2016 / Revised: 23 Dec. 2016 / Accepted: 26 Jan. 2017 / Published: 8 Mar. 2017

Index Terms

Human Pose Estimations, Chaining graph models, Edge based Filtering

Abstract

Human pose detection in 2D/3D images plays a vital role in a large number of applications such as gesture recognition, video surveillance and human robot interaction. Joint human pose estimation in the 2D motion video sequence and 3D facial pose estimation is the challenging issue in computer vision due to noise, large deformation, illumination and complex background. Traditional directed and undirected graphical models such as the Bayesian Markov model, conditional random field have limitations with arbitrary pose estimation in 2D/3D images using the joint probabilistic model. To overcome these issues, we introduce an ensemble chaining graph model to estimate arbitrary human poses in 2D video sequences and facial expression evaluation in 3D images. This system has three main hybrid algorithms, namely 2D/3D human pose pre-processing algorithm, ensemble graph chaining segmented model on 2D/3D video sequence pose estimation and 3D ensemble facial expression detection algorithm. The experimental results on public benchmarks 2D/3D datasets show that our model is more efficient in solving arbitrary human pose estimation problem. Also, this model has the high true positive rate, low false detection rate compared to traditional joint human pose detection models. 

Cite This Paper

D.Ratna kishore, M. Chandra Mohan, Akepogu. Ananda Rao,"A Novel Joint Chaining Graph Model for Human Pose Estimation on 2D Action Videos and Facial Pose Estimation on 3D Images", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.9, No.3, pp.21-32, 2017. DOI: 10.5815/ijigsp.2017.03.03

Reference

[1]http://tosca.cs.technion.ac.il/data/face.zip

[2]Y. Freund and R. E. Schapire. A decision-theoretic generalization on on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119–139, 1997.

[3]A. H. Gee and R. Cipolla. Determine the gaze of faces in images. Image and Vision Computing, 12(10):639–647, 1994.

[4]C. Dharmagunawardhana, S. Mahmoodi, M. Bennett and M. Niranjan, "Gaussian Markov random field based improved texture descriptor for image segmentation", Image and Vision Computing, vol. 32, no. 11, pp. 884-895, 2014.

[5]B. Sun and J. He, "Discriminative dictionary based representation and classification of image texture", Sixth International Conference on Digital Image Processing (ICDIP 2014), 2014.

[6]N. Wang, "Color Image Edge Detection Based on Cube Similarity", 2015 IEEE International Conference on Computational Intelligence & Communication Technology, 2015.

[7]X. Zhang and C. Liu, "An ideal image edge detection scheme", Multidimensional Systems and Signal Processing, vol. 25, no. 4, pp. 659-681, 2013.

[8]K. Zhang and K. Lam, "A Level Set Approach to Image Segmentation With Intensity Inhomogeneity", IEEE Trans. Cybern., vol. 46, no. 2, pp. 546-557, 2016.

[9]E. Murphy Chutorian and M. Manubhai Trivedi, Head Pose Estimation in Computer: A Survey, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 31. No.4, pp. 607627, 2009. 

[10]G. Fanelli, J. Gall, and L. Van Gool, "Real time head pose estimation with random regression forests," in CVPR, 2011.

[11]K.I. Chang, K.W. Bowyer, P.J. Flynn, "An evaluation of multi-model 2D+3D biometrics", IEEE Transactions on Pattern Analysis and Machine Intelligence 27 (4) (2005) 619–624. 

[12]P. S. Hiremath, Manjunatha Hiremath,"Depth and Intensity Gabor Features Based 3D Face Recognition Using Symbolic LDA and AdaBoost", IJIGSP, vol.6, no.1, pp.32-39, 2014.DOI: 10.5815/ijigsp.2014.01.05.

[13]K.I. Chang, K.W. Bowyer, P.J. Flynn, "Multiple nose region matching for 3D face recognition under varying facial expression", IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (10) (2006) 1695–1700.

[14]P. S. Hiremath, Manjunatha Hiremath,"3D Face Recognition based on Radon Transform, PCA, LDA using KNN and SVM", IJIGSP, vol.6, no.7, pp.36-43, 2014.DOI: 10.5815/ijigsp.2014.07.05.

[15]Kevin W. Bowyer, Kyong Chang, Patrick Flynn, "A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition", Computer Vision and Image Understanding 101, 1–15 (2006).