Optimizing human model reconstruction from RGB-D images based on skin detection
- 389 Downloads
This paper reconstructs human model from multi-view RGB-D images of an Xbox One Kinect. We preprocess the depth images by implicit surface de-noising and then part-wisely register them into a point cloud. A template model is selected from the human model database to fit the registered point cloud of a human body by Laplacian deformation. Skin detection of RGB-D images helps to tightly constrain the skin parts of human body in template fitting step in order to get more precise and lifelike human model. We propose a robust skin detection method that is not affected by clothing pattern and background. Experiments demonstrate the effectiveness of our method.
KeywordsHuman model reconstruction Kinect RGB-D image Skin detection
This work was partially supported by National Natural Science Foundation of China (51575481, 61379096) and Project of Public Technology Research in Industry of Zhejiang Province (2014C31048).
- Chang W, Zwicker M (2011) Global registration of dynamic range scans for articulated model reconstruction. ACM Trans Graph 30:171–179Google Scholar
- Hasler N, Ackermann H, Rosenhahn B, Thormahlen T, Seidel H-P (2010) Multilinear pose and body shape estimation of dressed subjects from image sets. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR), pp 1823–1830Google Scholar
- Izadi S et al (2011) KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: Proceedings of the 24th annual ACM symposium on user interface software and technology, pp 559–568Google Scholar
- Lee JY, Yoo SI (2002) An elliptical boundary model for skin color detection. In: Proceedings of the 2002 international conference on imaging science, systems, and technologyGoogle Scholar
- Li J, Wang Y (2007) Automatically constructing skeletons and parametric structures for polygonal human bodies. In: Proceedings of the 25th computer graphics international conferenceGoogle Scholar
- Mitra NJ, Flöry S, Ovsjanikov M, Gelfand N, Guibas L, Pottmann H (2007) Dynamic geometry registration. In: Symposium on geometry processing, pp 173–182Google Scholar
- Newcombe RA et al (2011) KinectFusion: real-time dense surface mapping and tracking. In: 2011 10th IEEE international symposium on mixed and augmented reality (ISMAR), pp 127–136Google Scholar
- Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11:23–27Google Scholar
- Weiss A, Hirshberg D, Black MJ (2011) Home 3D body scans from noisy image and range data. In: Proceedings of the 2011 international conference on computer vision, pp 1951–1958Google Scholar
- Zeng M, Zheng J, Cheng X, Liu X (2013) Templateless quasi-rigid shape modeling with implicit loop-closure. In: 2013 IEEE conference on computer vision and pattern recognition (CVPR), pp 145–152Google Scholar