Abstract
In this paper, we propose a direct depth map acquisition method for the arc camera array as well as the parallel camera array. In conventional stereo matching algorithms, image rectification is necessary where disparity values are obtained by identifying correspondences in the identical horizontal line of stereo images. The acquired disparity values are then transformed to depth values. However, image rectification may fabricate unwanted outcomes related to the arc camera array. Thus, the proposed method excludes image rectification and directly extracts depth values using an epipolar constraint. In particular, occlusion detection and handling processes are inserted to increase depth map accuracy. Further, belief propagation-based energy optimization is employed to confirm occlusion regions. Then, reasonable depth values are assigned to obtained occlusion regions using distances and color differences of neighbor pixels. Experimental results show that compared to the conventional methods, the proposed method generate more stable depth maps with fewer limitations.
Similar content being viewed by others
References
ISO/IEC JTC1/SC29/WG11: Applications and requirements on FTV. N9466 (2007)
ISO/IEC JTC1/SC29/WG11: Vision on 3D video. N10357 (2009)
Zhang, L., Tam, W.J.: Stereoscopic image generation based on depth images for 3DTV. IEEE Trans. Broadcast. 51(2), 191–199 (2005)
Fieseler, M., Jiang, X.: Discontinuity-based registration of depth and video data in depth image based rendering. Signal Image Video Process. 5(3), 353–361 (2011)
Frick, A., Kellner, F., Bartczak, B., Koch, R.: Generation of 3D-TV LDV-content with time of flight camera. In: Proceedings of IEEE International Conference on 3DTV, pp. 45–48. Potsdam, Germany, May 4–6 (2009)
Shin, I.Y., Ho, Y.S.: Disparity estimation at virtual viewpoint for real-time intermediate view generation. In: Proceedings of International Conference on 3D Systems and Applications, pp. 195–198. Seoul, Korea, June 20–22 (2011), paper S6–2
Jang, W.S., Ho, Y.S.: Efficient disparity map estimation using occlusion handling for various 3D multimedia applications. IEEE Trans. Consumer Electron. 57(4), 1937–1943 (2011)
Lee, E.K., Ho, Y.S.: Generation of high-quality depth maps using hybrid camera system for 3-D video. J. Visual Commun. Image Represent. 22(1), 73–84 (2011)
Sharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. In: IEEE Workshop on Stereo and Multi-Baseline Vision, Kauai, Hawaii, Dec 9–10, 131–140 (2001)
Raghavendra, U., Makkithaya, K., Karunakar, A. K.: Anchor-diagonal-based shape adaptive local support region for efficient stereo matching. Signal Image Video Process. 1–9 (2013). doi:10.1007/s11760-013-0524-4
Kang, Y.S., Ho, Y.S.: An efficient image rectification method for parallel multi-camera arrangement. IEEE Trans. Consumer Electron. 57(3), 1041–1048 (2011)
Robert, L., Deriche, R.: Dense depth map reconstruction: a minimization and regularization approach which preserves discontinuities. In: Proceedings of European Conference on Computer Vision, Cambridge, pp. 439–451, April 15–18 (1996)
Lopez, A., Pla, F.: A minimization approach for 3D recovery in region-based stereo vision. In: Proceedings of Image Processing and its Applications, Bangalore, India, pp. 47–51, July 13–15 (1999)
Kang, Y.S., Ho, Y.S.: Geometrical calibration of stereo images in convergent camera arrangement. In: Proceedings of IEEE-RIVF International Conference on Computing and Communication Technologies, Ho Chi Minh, Vietnam, pp. 44–47, Feb 27–Mar 1 (2012)
Wang, L., Jin, H., Yang, R.: Search space reduction for MRF stereo. In: Proceedings of 10th European Conference on Computer Vision, Marseille, pp. 576–588, Oct 12–18 (2008)
Hirschmuller, H., Innocent, P.R., Garibaldi, J.M.: Real-time correlation-based stereo vision with reduced border errors. Int. J. Comput. Vision 47(1/2/3), 229–246 (2002)
Kang, Y.S., Ho, Y.S.: Disparity Map Generation for color image using a TOF depth camera. In: Proceedings of 3DTV Conference, Antalya, Turkey, pp. 46(1–4), May 16–18 (2011)
Yang, Q., Wang, L., Ahuja, N.: A constant-space belief propagation algorithm for stereo matching. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, pp. 1458–1465, June 13–18 (2010).
Yang, Q., Engels, C., Akbarzadeh, A.: Near real-time stereo for weakly-textured scenes. In: Proceedings of British Machine Vision Conference, Leeds, England, pp. 80–87, Sept 1–4 (2008)
Jung, J.-I., Ho, Y.-S.: Color correction algorithm based on camera characteristics for multi-view video coding. Signal Image Video Process. (2012). doi:10.1007/s11760-012-0341-1
Zhang, Z.: A Flexible New Technique for Camera Calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Tappen, M.F., Freeman, W.T.: Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In: Proceedings of IEEE International Conference on Computer Vision, Nice, pp. 900–906, Oct 13–16 (2003)
Acknowledgments
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. 2012-0009228).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jang, WS., Ho, YS. Efficient depth map generation with occlusion handling for various camera arrays. SIViP 8, 287–297 (2014). https://doi.org/10.1007/s11760-013-0550-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-013-0550-2