Wenjing Geng
ABSTRACT
Depth information provides fundamental supports to multimedia applications for both images and videos. Depth acquisition for stereo images has drawn much attention while few approaches are proposed for stereo videos. Conducting stereo matching frame-by-frame is time consuming and the result is temporally inconsistent. As a matter of fact, the redundancy shared by frame sequences may cause extra computational cost. Inspired by rapidly acquiring stereo video depth for some specific applications, we propose a novel bidirectional motion-based interpolation framework, which avoids frame-by-frame matching through making use of the motion estimation and the redundancy between frames. Firstly, comparable accurate depth maps are generated for self-adaptive selected frames via stereo matching. Then rough depth sequences inbetween are calculated using bidirectional motion-based interpolation. To improve the depth accuracy for non-selected frames, we propose a refinement approach to handle cracks and holes. The evaluation on both computer rendered and real world captured datasets show that our approach is competent for fast and accurate binocular video depth acquisition.
- S. Baker, D. Scharstein, J. Lewis, S. Roth, M. J. Black, and R. Szeliski. A database and evaluation methodology for optical flow. IJCV, 92(1):1--31, 2011. Google Scholar
Digital Library
- T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. In ECCV, pages 25--36. Springer, 2004.Google ScholarCross Ref
- A. Bruhn, J. Weickert, and C. Schnörr. Lucas/kanade meets horn/schunck: Combining local and global optic flow methods. IJCV, 61(3):211--231, 2005. Google ScholarCross Ref
- A. Flint, D. Murray, and I. Reid. Manhattan scene understanding using monocular, stereo, and 3d features. In ICCV, pages 2228--2235. IEEE, 2011. Google ScholarDigital Library
- C. H. Hung, L. Xu, and J. Jia. Consistent binocular depth and scene flow with chained temporal profiles. IJCV, 102(1-3):271--292, 2013. Google ScholarDigital Library
- C. Liu et al. Beyond pixels: exploring new representations and applications for motion analysis. PhD thesis, MIT, 2009. Google ScholarDigital Library
- D. Sun, S. Roth, and M. J. Black. A quantitative analysis of current practices in optical flow estimation and the principles behind them. IJCV, 106(2):115--137, 2014. Google ScholarDigital Library
- L. Valgaerts, A. Bruhn, H. Zimmer, J. Weickert, C. Stoll, and C. Theobalt. Joint estimation of motion, structure and geometry from stereo sequences. In ECCV, pages 568--581. Springer, 2010. Google ScholarDigital Library
- W. Wang, J. Zhao, W. J. Tam, F. Speranza, and Z. Wang. Hiding depth map into stereo image in jpeg format using reversible watermarking. In ICIMCS, pages 82--85. ACM, 2011. Google ScholarDigital Library
- A. Wedel, C. Rabe, T. Vaudrey, T. Brox, U. Franke, and D. Cremers. Efficient dense scene flow from sparse or dense stereo data. In ECCV, pages 739--751. Springer, 2008. Google ScholarDigital Library
- H. Zheng, J. Yuan, and R. Gu. A novel method for 3d reconstruction on uncalibrated images. In ICIMCS, pages 138--141. ACM, 2011. Google ScholarDigital Library
Index Terms
- Fast Binocular Depth Inference via Bidirectional Motion Based Interpolation
Recommendations
Temporal frame interpolation for stereoscopic sequences using object-based motion estimation and occlusion detection
ICIP '95: Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2Temporal frame interpolation techniques are presented, based on an object-based algorithm for 3-D motion estimation. This algorithm uses a joint estimation-segmentation scheme to minimize the displaced frame difference between a frame and its motion ...
Generation of high-quality depth maps using hybrid camera system for 3-D video
In this paper, we present a hybrid camera system combining one time-of-flight depth camera and multiple video cameras to generate multi-view video sequences and their corresponding depth maps. In order to obtain the multi-view video-plus-depth data ...
Homography-based block motion estimation for video coding of PTZ cameras
We propose a homography-based search (HBS) algorithm for block motion estimation.We use optical flow tracking algorithm to obtain homography between two frames.Adaptive thresholds are adopted in our method to classify different kinds of blocks. Due to ...
Comments