Volume 48 Issue 5
May  2019
Turn off MathJax
Article Contents
Article Navigation >  Infrared and Laser Engineering  > 2019  >  48(5): 524001-0524001(8)

Fan Xiaoting, Li Yi, Luo Xiaowei, Zhang Ning, Han Mengxin, Lei Jianjun. Depth estimation based on light field structure characteristic and multiview matching[J]. Infrared and Laser Engineering, 2019, 48(5): 524001-0524001(8). doi: 10.3788/IRLA201948.0524001
Citation: Fan Xiaoting, Li Yi, Luo Xiaowei, Zhang Ning, Han Mengxin, Lei Jianjun. Depth estimation based on light field structure characteristic and multiview matching[J]. Infrared and Laser Engineering, 2019, 48(5): 524001-0524001(8). doi: 10.3788/IRLA201948.0524001
shu

Depth estimation based on light field structure characteristic and multiview matching

doi: 10.3788/IRLA201948.0524001
  • 1.

    School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China

  • Received Date: 2018-12-15
  • Rev Recd Date: 2019-01-20
  • Publish Date: 2019-05-25
  • The existing light field image depth estimation technique cannot make a balanced estimation between major object and background. In this paper, a novel depth estimation method based on light field structure characteristic and multiview matching was proposed for light field image. The light field structure guided method was used as the basis of depth estimation. In order to maintain a smooth transition of the depth changing region and consider that the light field image has multiview subaperture image arrays, the multiview matching was presented to optimize the depth estimation. In the Markov random field domain, a smooth term was constructed based on the characteristics of the light field structure and a data term was constructed based on multiview stereo matching. Then, an optimization method utilizing the above two terms was proposed to balance object depth boundary and background depth estimation, so as to improve the depth estimation of light field images. Experimental results show that the proposed method can produce high quality depth estimation results with clear depth boundary and accurate depth in background.
  • [1] Lei J, Li L, Yue H, et al. Depth map super-resolution considering view synthesis quality[J]. IEEE Transactions on Image Processing, 2017, 26(4):1732-1745.
    [2] Liu Ziwei, Xu Tingfa, Wang Hongqing, et al. Theory and implementation of depth photography[J]. Infrared and Laser Engineering, 2016, 45(7):0726001. (in Chinese)刘子伟, 许廷发, 王洪庆, 等. 深度成像理论与实现[J]. 红外与激光工程, 2016, 45(7):0726001.
    [3] Lei J, Zhang C, Fang Y, et al. Depth sensation enhancement for multiple virtual view rendering[J]. IEEE Transactions on Multimedia, 2015, 17(4):457-469.
    [4] Wanner S, Goldluecke B. Globally consistent depth labeling of 4D light fields[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2012:1-8.
    [5] Yu Z, Yu J, Lumsdaine A, et al. Plenoptic depth map in the case of occlusions[C]//Proceedings of Mobile Computational Photography, 2013:8667-8676.
    [6] Yu Z, Guo X, Ling H, et al. Line assisted light field triangulation and stereo matching[C]//IEEE International Conference on Computer Vision, 2013:2792-2799.
    [7] Kim C, Zimmer H, Pritch Y, et al. Scene reconstruction from high spatio angular resolution light fields[J]. ACM Transactions on Graphics, 2013, 32(4):1-12.
    [8] Held R T, Cooper E A, Banks M S. Blur and disparity are complementary cues to depth[J]. Current Biology, 2012, 22(5):426-431.
    [9] Tao M W, Hadap S, Malik J, et al. Depth from combining defocus and correspondence using light-field cameras[C]//IEEE International Conference on Computer Vision, 2013:673-680.
    [10] Cao Y, Kai R, Jing Z, et al. Fast response aggregation for depth estimation using light field camera[C]//IEEE International Conference on Acoustics, Speech and Signal Processing, 2016:1636-1640.
    [11] Suzuki T, Takahashi K, Fujii T. Disparity estimation from light fields using sheared EPI analysis[C]//IEEE International Conference on Image Processing, 2016:1444-1448.
    [12] Li Yigui, Yan Ping, Huang Yuan, et al. Fabrication of PMMA micro lens array based on X-ray moving lithography[J]. Infrared and Laser Engineering, 2016, 45(6):0620001. (in Chinese)李以贵, 颜平, 黄远, 等. 基于X光移动光刻技术的PMMA微透镜阵列制备[J]. 红外与激光工程, 2016, 45(6):0620001.
    [13] Buades A, Facciolo G. Reliable multiscale and multiwindow stereo matching[J]. SIAM Journal on Imaging Sciences, 2015, 8(2):888-915.
    [14] Brox T, Bruhn A, Papenberg N, et al. High accuracy optical flow estimation based on a theory for warping[C]//European Conference on Computer Vision, 2004:25-36.
    [15] Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.
    [16] Wanner S, Goldluecke B. Globally consistent depth labeling of 4D light fields[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2012:1-8.
    [17] Jeon H-G, Park J, Choe G, et al. Accurate depth map estimation from a lenslet light field camera[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2015:1547-1555.
    [18] Wang T C, Efros A A, Ramamoorthi R. Occlusion-aware depth estimation using light-field cameras[C]//IEEE International Conference on Computer Vision, 2015:3487-3495.
    [19] Navarro J, Buades A. Reliable light field multiwindow disparity estimation[C]//IEEE International Conference on Image Processing, 2016:1449-1453.
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
Get Citation
PDF
XML

Article Metrics

Article views(448) PDF downloads(57) Cited by()

Related
Proportional views

Depth estimation based on light field structure characteristic and multiview matching

doi: 10.3788/IRLA201948.0524001
  • 1. School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China
  • Received Date: 2018-12-15
  • Rev Recd Date: 2019-01-20
  • Publish Date: 2019-05-25

Abstract: The existing light field image depth estimation technique cannot make a balanced estimation between major object and background. In this paper, a novel depth estimation method based on light field structure characteristic and multiview matching was proposed for light field image. The light field structure guided method was used as the basis of depth estimation. In order to maintain a smooth transition of the depth changing region and consider that the light field image has multiview subaperture image arrays, the multiview matching was presented to optimize the depth estimation. In the Markov random field domain, a smooth term was constructed based on the characteristics of the light field structure and a data term was constructed based on multiview stereo matching. Then, an optimization method utilizing the above two terms was proposed to balance object depth boundary and background depth estimation, so as to improve the depth estimation of light field images. Experimental results show that the proposed method can produce high quality depth estimation results with clear depth boundary and accurate depth in background.

    HTML

Reference (19)

Catalog

    版权所有 © 2019 《红外与激光工程》编辑部｜ Address: 58 Zhonghuan West Road, Tianjin Airport Economic Zone｜ Post Code: 300308

    津ICP备19007885号-1

    Supported by: Beijing Renhe Information Technology Co. Ltd  

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return