Abstract
In order to extract the accurate depth map which accords with human vision, a new depth extraction method based on fusion of motion information and geometry information was proposed in the paper. First, to extract the stationary background image from the video sequence with stationary background and moving foreground, the gaussian mixture model algorithm was adopted, then the paper adopted background difference method with adaptive threshold to extract complete moving objects area. Furthermore, the depth map of background image was computed based on geometry information, similarly, the depth map of moving foreground was computed based on motion information. Finally, the complete and precise depth map was obtained using the method based on fusion of the depth map of background image and the depth map of moving foreground.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Han, Y., Zhang, H., Li, L.: Shadow Suppression Algorithm Based on Gaussian Mixture Background Model. In: The 14th National Image Graphics Academic Conferences (2007)
Long, W., Yang, Y.H.: Stationary Background Generation: an Alternative to the Difference of two Images. Pattern Recognition 23(12), 1351–1359 (1990)
Tang, Y., Jiang, Y.: A moving human body segmentation method based on color image. Microelectronics & Computer 23(3) (2006)
Song, S., Liu, D., Ceng, L.: A moving object detection algorithm based on the union of image segmentation and background model. Measurement and Control Technique 25(5) (2006)
Harman, P., Flack, J., Fox, S., Dowley, M.: Rapid 2D to 3D Conversion. In: Proceedings of SPIE, vol. 4660, pp. 78–86 (2002)
Wang, H., Kang, N.: A Adaptive Diamond Algorithm based on Motion Estimation. Computer Engineering and Application 43(26) (2007)
Ideses, I., Yaroslavsky, L.P., Fishbain, B.: Real-time 2D to 3D video conversion. J Real-Time Image Porc. 2, 3–9 (2007)
Sun, Y.: Key Technical Research of 2D to 3D Video Conversion. Shanghai Jiao Tong University 02 (2008)
Huang, X., Huang, J., Wang, L., Li, D., Zhang, M.: A Depth Extraction Method Based on Fusion of Motion Information and Geometry Information. Zhejiang University 8(17) (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wen, L., Qu, Z., Shi, L. (2013). A New Depth Extraction Method Based on Fusion of Motion Information and Geometry Information. In: Yang, G. (eds) Proceedings of the 2012 International Conference on Communication, Electronics and Automation Engineering. Advances in Intelligent Systems and Computing, vol 181. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31698-2_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-31698-2_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31697-5
Online ISBN: 978-3-642-31698-2
eBook Packages: EngineeringEngineering (R0)