Open Access Open Access  Restricted Access Subscription or Fee Access

Depth Map Compression by Contour Networks for Video Sequences

Ankush Rai


The advancing fields in video technology like that of 3D TV and Free Viewpoint Video essentially requires more information to transmit in addition with the 2D color maps. This information is the depth maps of the accompanying scenes from the videos sequences in order to facilitate rendering of arbitrary viewpoints within it. In this study, we present a novel algorithm to determine the contours from the given video sequences and form a network of it in the run-time and thereby create a new-data format accompanied by the color scheme with the contour network exhibiting the depth maps and the dynamically adjusting with changes it experienced while the object remain in motion. Preserving the depth maps and portraying its continuity is crucial for the synthesis of high quality view. This study will facilitate the divisionm of features derivable from RGB color visions to extract precise and hidden visual information of superior visual quality with low geometric distortions.

Keywords: Contours, computer vision, video sequences, depth determination

Cite this Article
Rai A. Depth Map Compression by Contour Networks for Video Sequences.
Recent Trends in Parallel Computing. 2015; 2(2): 9–13p.

Full Text:



Fehn C, Schuur K, Kauff P, et al. Proposed experimental conditions for EE4 in MPEG3DAV. Coding of Moving Pictures and Associated Audio

Information (ISO/IEC JTC1/SC29/WG11 M); 2002 Oct; Shanghai, China.

Krishnamurthy R, Chai B, Tao H, et al. Compression and transmission of depth maps for image-based rendering. Proceedings of the International Conference on Image Processing; 2001 Oct 7–10; Thessaloniki, Greece. 828–31p.

Liu S, Lai P, Tian D, et al. Sparse dyadic mode for depth map compression. Proceedings of the 17th IEEE International Conference on Image Processing (ICIP); 2010 Sep 26–29; Hong Kong. 3421–4p.

Morvan Y, de With PHN, Farin D. Platelet-based coding of depth maps for the transmission of multiview images. Proceedings of SPIE, Stereoscopic Displays and Applications; 2006 Jan 16–19; San Jose, California, USA. 93–100p.

Sarkis M, Zia W, Diepold K. Fast depth map compression and meshing with compressed tritree. Lecture Notes in Computer Science. 2010; 5995: 44–55p.

Shen G, Kim W, Ortega A, et al. Edgeaware intra prediction for depth-map coding. Proceedings of the 2010 17th IEEE International Conference on Image Processing (ICIP); 2010 Sep 26–29; Hong Kong. 3393–6p.

Arbelaez P, Maire M, Fowlkes C, et al. Contour detection and hierarchical image segmentation. IEEE Trans PAMI. 2011; 33(5): 898–916p.

Everingham M, Van Gool L, Williams CKI, et al. The PASCAL Visual Object Classes Challenge—a Retrospective. Int J Comp Vision. 2015; 111(1): 98–136p. Available from: VOC/voc2008/

Shotton J, Winn J, Rother C, et al. Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. Lecture Notes in Computer Science. 2006; 3951:


Silberman N, Fergus R. Indoor scene segmentation using a structured light sensor. Proceedings of the IEEE Workshop on 3D Representation and Recognition (3dRR); 2011 Nov 7; Barcelona, Spain.


  • There are currently no refbacks.

This site has been shifted to