Abstract
We propose a hybrid method for stereo disparity estimation by combining block and region-based stereo matching approaches. It generates dense depth maps from disparity measurements of only 18 % image pixels (left or right). The methodology involves segmenting pixel lightness values using fast K-Means implementation, refining segment boundaries using morphological filtering and connected components analysis; then determining boundaries’ disparities using sum of absolute differences (SAD) cost function. Complete disparity maps are reconstructed from boundaries’ disparities. We consider an application of our method for depth-based selective blurring of non-interest regions of stereo images, using Gaussian blur to de-focus users’ non-interest regions. Experiments on Middlebury dataset demonstrate that our method outperforms traditional disparity estimation approaches using SAD and normalized cross correlation by up to 33.6 % and some recent methods by up to 6.1 %. Further, our method is highly parallelizable using CPU–GPU framework based on Java Thread Pool and APARAPI with speed-up of 5.8 for 250 stereo video frames (4,096 × 2,304).
Graphical Abstract
Similar content being viewed by others
References
Lazaros, N., Sirakoulis, G., & Gasteratos, A. (2008). Review of stereo vision algorithms: from software to hardware. International Journal of Optomechatronics, 2(4), 435–462.
Xiao, J. Xia, L., Lin, L., & Zhang, Z. (2010). A segment-based stereo matching method with ground control points. International Conference on Environmental Science and Information Application Technology (ESIAT), 2010 (Vol. 3, pp. 306–309). 17–18 July 2010. doi: 10.1109/ESIAT.2010.5568363.
Zhang, Z., Wang, Y., & Dahnoun, N. (2010). A novel algorithm for disparity calculation based on stereo vision. 4th European Education and Research Conference (EDERC), 2010 (pp. 180–184). 1–2 Dec 2010.
Sunyoto, H., Van der Mark, W., & Gavrila, D. M. (2004) A comparative study of fast dense stereo vision algorithms. IEEE Intelligent Vehicles Symposium, 2004 (pp. 319–324). 14–17 June 2004. doi: 10.1109/IVS.2004.1336402.
Tippetts, B., Lee, D., Lillywhite, K., & Archibald, J. (2013). Review of stereo vision algorithms and their suitability for resource-limited systems. Journal of Real-Time Image Processing 1–21. doi:10.1007/s11554-012-0313-2.
Popkin, T., Cavallaro, A. & Hands, D. (2011). Efficient depth blurring with occlusion handling. 18th IEEE International Conference on Image Processing (ICIP), 2011 (pp. 2585–2588). 11–14 Sept 2011. doi: 10.1109/ICIP.2011.6116193.
Hirschmuller, H. & Scharstein, D. (2007). Evaluation of cost functions for stereo matching. IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR ‘07. (pp. 1–8) 17–22 June 2007. doi: 10.1109/CVPR.2007.383248.
Tombari, F., Mattoccia, S., Di Stefano, L., & Addimanda, E. (2008). Classification and evaluation of cost aggregation methods for stereo correspondence. IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008 (pp. 1–8). 23–28 June 2008. doi: 10.1109/CVPR.2008.4587677.
Abdollahifard, M., Faez, K., & Pourfard, M. (2009). Fast stereo matching using two stage color-based segmentation and dynamic programming. 6th International Symposium on Mechatronics and its Applications, 2009. ISMA ‘09 (pp. 1–6) .23–26 March 2009. doi: 10.1109/ISMA.2009.5164848.
Kim, C. (2005). Segmenting a low-depth-of-field image using morphological filters and region merging. IEEE Transactions on Image Processing, 14(10), 1503–1511. doi:10.1109/TIP.2005.846030.
Wang, X., Song, Y., & Zhang, Y. (2013). Natural Scene Text Detection with Multi-channel Connected Component Segmentation. 12th International Conference on Document Analysis and Recognition (ICDAR), 2013 (pp. 1375–1379). 25–28 Aug 2013. doi: 10.1109/ICDAR.2013.278.
Vishwanath, N., Somasundaram, S., Ravi, M. R. R., & Nallaperumal, N. K. (2012). Connected component analysis for Indian license plate infra-red and color image character segmentation. IEEE International Conference on Computational Intelligence & Computing Research (ICCIC), 2012 (pp. 1–4). 18–20 Dec 2012. doi: 10.1109/ICCIC.2012.6510323.
Zirari, F.; Ennaji, A.; Nicolas, S.; Mammass, D. (2013) “A Document Image Segmentation System Using Analysis of Connected Components. 12th International Conference on Document Analysis and Recognition (ICDAR), 2013 (pp. 753–757) 25–28 Aug 2013. doi: 10.1109/ICDAR.2013.154.
Li, M., Zheng, X., Wan, X., Luo, H., Zhang, S., & Tan, L. (2011). Segmentation of brain tissue based on connected component labeling and mathematic morphology. 4th International Conference on Biomedical Engineering and Informatics (BMEI), 2011, 1, 482–485. doi:10.1109/BMEI.2011.6098294.
Moftah, H. M., ella Hassanien, A. & Shoman, M. (2010). 3D brain tumor segmentation scheme using K-mean clustering and connected component labeling algorithms. 10th International Conference on Intelligent Systems Design and Applications (ISDA), 2010 (pp. 320–324). Nov 29 2010–Dec 1 2010. doi: 10.1109/ISDA.2010.5687244.
Bellala Belahbib, F. Z., & Souami, F. (2012). Color image segmentation by a genetic algorithm based clustering and Connected Component Labeling. 24th International Conference on Microelectronics (ICM), 2012 (pp. 1–4). 16–20 Dec 2012. doi: 10.1109/ICM.2012.6471432.
Choi, K. -S. (2012). Hierarchical block-based disparity estimation. IEEE 1st Global Conference on Consumer Electronics (GCCE), 2012 (pp. 493–494). 2–5 Oct 2012. doi: 10.1109/GCCE.2012.6379668.
Zhu, S., & Yu, Y. (2012). Virtual view rendering based on self-adaptive block matching disparity estimation. International Conference on Industrial Control and Electronics Engineering (ICICEE), 2012 (pp. 947–950). 23–25 Aug 2012. doi: 10.1109/ICICEE.2012.251.
Wang, Z. -F., & Zheng, Z. -G. (2008). A region based stereo matching algorithm using cooperative optimization. IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008 (pp. 1–8). 23–28 June 2008. doi: 10.1109/CVPR.2008.4587456.
Lu, D., & Du, Y. (2013). A two-step stereo correspondence algorithm based on combination of feature-matching and region-matching. 8th International Forum on Strategic Technology (IFOST), 2013, 2, 51–55. doi:10.1109/IFOST.2013.6616858.
Tkalcic, M., & Tasic, J. F. (2003). Colour spaces: perceptual, historical and applicational background. EUROCON 2003. Computer as a Tool. The IEEE Region 8 1, 304–308. 10.1109/EURCON.2003.1248032.
Docampo, J., Ramos, S., Taboada, G. L., Exposito, R. R., Tourino, J. & Doallo, R. (2013). Evaluation of Java for general purpose GPU computing. 27th International Conference on Advanced Information Networking and Applications Workshops (WAINA), 2013 (pp. 1398–1404). 25–28 March 2013. doi: 10.1109/WAINA.2013.234.
Kolmogorov, V., & Zabih, R. (2001). Computing visual correspondence with occlusions using graph cuts. Proceedings of the Eighth IEEE International Conference on Computer Vision ICCV 2001, 2, 508–515. doi:10.1109/ICCV.2001.937668.
Miled, W.; Pesquet, J. C. (2006). Disparity map estimation using a total variation bound. The 3rd Canadian Conference on Computer and Robot Vision, 2006. (p 48) 7–9 June 2006. doi: 10.1109/CRV.2006.28.
Scharstein, D., Szeliski, R., & Zabih, R. (2001). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision, 2001 (SMBV 2001) (pp. 131–140). doi: 10.1109/SMBV.2001.988771.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mukherjee, S., Guddeti, R.M.R. Depth-Based Selective Blurring in Stereo Images Using Accelerated Framework. 3D Res 5, 14 (2014). https://doi.org/10.1007/s13319-014-0014-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13319-014-0014-7