全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

结合同场景立体图对的高质量深度图像重建

DOI: 10.11834/jig.20150101

Keywords: 深度图像,飞行时间深度相机,立体匹配,自适应权值匹配,局部权值滤波

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的越来越多的应用依赖于对场景深度图像准确且快速的观测和分析,如机器人导航以及在电影和游戏中对虚拟场景的设计建模等。飞行时间深度相机等直接的深度测量设备可以实时的获取场景的深度图像,但是由于硬件条件的限制,采集的深度图像分辨率比较低,无法满足实际应用的需要。通过立体匹配算法对左右立体图对之间进行匹配获得视差从而得到深度图像是计算机视觉的一种经典方法,但是由于左右图像之间遮挡以及无纹理区域的影响,立体匹配算法在这些区域无法匹配得到正确的视差,导致立体匹配算法在实际应用中存在一定的局限性。方法结合飞行时间深度相机等直接的深度测量设备和立体匹配算法的优势,提出一种新的深度图像重建方法。首先结合直接的深度测量设备采集的深度图像来构造自适应局部匹配权值,对左右图像之间的局部窗立体匹配过程进行约束,得到基于立体匹配算法的深度图像;然后基于左右检测原理将采集到的深度图像和匹配得到的深度图像进行有效融合;接着提出一种局部权值滤波算法,来进一步提高深度图像的重建质量。结果实验结果表明,无论在客观指标还是视觉效果上,本文提出的深度图像重建算法较其他立体匹配算法可以得到更好的结果。其中错误率比较实验表明,本文算法较传统的立体匹配算法在深度重建错误率上可以提升10%左右。峰值信噪比实验结果表明,本文算法在峰值信噪比上可以得到10dB左右的提升。结论提出的深度图像重建方法通过结合高分辨率左右立体图对和初始的低分辨率深度图像,可以有效地重建高质量高分辨率的深度图像。

References

[1]  Riyad A, Huang j, Michael Y. Study on the use of microsoft kinect for robotics applications [C]//The Position Location and Navigation Symposium. South Carolina: IEEE Single Processing Society, 2012: 1280-1288.
[2]  Ishida Y, Izuoka H, Chinthaka H, et al. Study on plane extraction from distance images using 3D hough transform [C]//The 13th International Symposium on Advanced Intelligent Systems. Kobe: Japan Society for Fuzzy Theory and intelligent informatics, 2012: 812-816.
[3]  Rodriguez J, Burrus N, Abderrahim M. A-contrario detection of aerial target using a Time-of-Flight camera [C]//Proceedings of Sensor Signal Processing for Defence. London, United Kingdom: IEEE Single Processing Society, 2012: 1-5.
[4]  Fabian J, Young T, Jones J, et al. Integrating the Microsoft Kinect with simulink: real-time object tracking example [J]. IEEE Transactions on Mechatronics, 2012, 19(1): 249-257.
[5]  Ding J T, Du X, Zhou W H, et al. High performance implementation of stereo vision matching based on FPGA [J]. Jounal of Electronics & Information Technology, 2011, 33(3): 597-603.[丁菁汀,杜歆,周文晖,等. 基于FPGA的立体视觉匹配的高性能实现 [J]. 电子与信息学报, 2011, 33(3): 597-603.]
[6]  Veksler O. Stereo correspondence with compact windows via minimum ratio cycle [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002, 24(12): 1654-1660.
[7]  Veksler O. Fast variable window for stereo correspondence using integral images [C]//Proceeding of the 16th International Conference on Computer Vision and Pattern Recognition. Madison, Wisconsin: IEEE Computer Society, 2003: 556-561.
[8]  Yoon K, Kweon S. Adaptive support-weight approach for correspondence search [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(4): 650-656.
[9]  Tombari F, Mattoccia S, Di Stefano L. Segmentation-based adaptive support for accurate stereo correspondence [J]. IEEE Pacific-Rim Symposium on Image and Video Technology, 2007, 427-438.
[10]  Hosni A, Rhemann C, Bleyer M, et al. Fast cost-volume filtering for visual correspondence and beyond [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2012, 35(2): 504-511.
[11]  Zheng Z G, Wang Z F. A region based stereo matching algorithm using cooperative optimization [J]. Acta Automatica Sinica, 2009, 35(5): 469-477.[郑志刚, 汪增福. 基于区域间协同优化的立体匹配算法 [J]. 自动化学报, 2009, 35(5): 469-477.]
[12]  Wang Z F, Zheng Z G. A region based stereo matching algorithm using cooperative optimization [C]//Proceedings of the 21th International Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE Computer Society, 2008: 1-8.
[13]  He K M, Sun J, Tang X O. Guided image filtering [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.
[14]  Buades A, Coll B, Morel J M. A non-local algorithm for image denoising [C]//Proceedings of the 18th International Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE Computer Society, 2005: 60-65.
[15]  Dong W S, Shi G M, Lin X, et al. Image reconstruction with locally adaptive sparsity and nonlocal robust regularization [J]. Signal Processing: Image Communication, 2012, 27(10): 1109-1122.
[16]  Dong W S, Zhang L, Lukac R, et al. Sparse representation based image interpolation with nonlocal autoregressive modeling [J]. IEEE Trans. on Image Processing,2013, 22(4):1382-1394.
[17]  Dong W S, Zhang L, Shi G M, et al. Nonlocally centralized sparse representation for image restoration [J]. IEEE Transactions on Image Processing, 2013, 22(4):1620-1630.
[18]  Favaro P. Recovering thin structures via nonlocal-means regularization with application to depth from defocus [C]//Proceedings of the 23th International Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA: IEEE Computer Society, 2010: 1133-1140.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133