Abstract
A novel video super-resolution reconstruction algorithm based on correlation learning and spatio-temporal nonlocal similarity is proposed in this paper. Objective high-resolution (HR) estimates of low-resolution (LR) video frames can be obtained by learning LR-HR correlation mapping and fusing the spatio-temporal nonlocal similarity information between video frames. First, the LR-HR correlation mapping between LR and HR patches is established based on semi-coupled dictionary learning. With the aim of improving algorithm efficiency while guaranteeing super-resolution quality, LR-HR correlation mapping is performed only for the salient object region, and then an improved visual saliency-based nonlocal fuzzy registration scheme using the pseudo-Zernike moment feature and structural similarity is proposed for spatio-temporal similarity matching and fusion. Visual saliency and self-adaptive regional correlation evaluation strategies are used in spatio-temporal similarity matching to improve algorithm efficiency further. Experimental results demonstrate that the proposed algorithm achieves competitive super-resolution quality compared to other state-of-the-art algorithms in terms of both subjective and objective evaluations.
Similar content being viewed by others
References
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 275–282
Chen J (2012) Video super-resolution using generalized gaussian markov random fields. Signal Process Lett 19(2):63–66
Chen J, Nunez-Yanez J, Achim A (2012) Video super-resolution using generalized gaussian Markov random fields. IEEE Signal Process Lett 19(2):63–66
Dong C, Change Loy C, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. European Conference on Computer Vision (ECCV), pp. 184–199
Dong W, Zhang L, Lukac R, Shi G (2013) Sparse representation based image interpolation with nonlocal autoregressive modeling. IEEE Trans Image Process 22(4):1382–1394
Dowson N, Salvado O (2011) Hash nonlocal means for rapid image filtering. IEEE Trans Pattern Anal Mach Intell 33(3):485–499
Gao X, Wang Q, Li X (2011) Zernike-moment-based image super resolution. IEEE Trans Image Process 20(10):2738–2747
Gao X, Zhang K, Tao D et al (2012) Image super-resolution with sparse neighbor embedding. IEEE Trans Image Process 21(7):3194–3205
Giachetti A, Asuni N (2012) Real-time artifact-free image upscaling. IEEE Trans Image Process 21(4):2361–2369
He L, Qi H, Zaretzki R (2013) Beta process joint dictionary learning for coupled feature spaces with application to single image super resolution. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 345–352
Heng S, Liang T, Wu Y et al (2012) Spatially adaptive block-based super-resolution. IEEE Trans Image Process 21(3):1031–1045
Jiang J, Hu R, Han Z, Lu T (2014) Efficient single image super-resolution via graph-constrained least squares regression. Multimed Tools Appl 72:2573–2596
Jordi S, Axel K, Siegfried S (2013) Patch-based spatio-temporal super-resolution for video with non-rigid motion. Signal Process Image Commun 28(5):483–493
Lin D, Tang X (2005) Coupled space learning of image style transformation. International Conference on Computer Vision (ICCV), pp. 1699–1706
Lin Z, Zhang L, Mou X, Zhang D (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 20(8):2378–2386
Liu C, Sun D (2014) On Bayesian adaptive video super resolution. IEEE Trans Pattern Anal Mach Intell 36(2):346–360
Lu Z, Lu X, Yang L (2014) A local structure adaptive super-resolution reconstruction method based on BTV regularization. Multimed Tools Appl 71:1879–1892
Maalouf A, Larabi M-C (2012) Colour image super-resolution using geometric grouplets. IET Image Process 6(2):168–180
Mudenagudi U, Banerjee S (2011) Space-time super-resolution using graph-cut optimization. IEEE Trans Pattern Anal Mach Intell 33(5):995–1008
Protter M, Elad M, Takeda H (2009) Generalizing the nonlocal-means to super-resolution reconstruction. IEEE Trans Image Process 18(1):349–366
Su K, Tian Q, Xue Q, Sebe N, Ma J (2005) Neighborhood issue in single-frame image super-resolution. IEEE International Conference on Multimedia and Expo (ICME), pp. 1–4
Timofte R, De V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. International Conference on Computer Vision (ICCV), pp. 1920–1927
Timofte R, De V Smet, Van L Gool (2014) A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution. Asian Conference on Computer Vision (ACCV), pp. 111–126
Wang S, Zhang L, Liang Y, Pan Q (2012) Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2216–2223
Yang J, Lin Z, Cohen S (2013) Fast image super-resolution based on in-place example regression. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1059–1066
Yang C-Y, Ma C, Yang M-H (2014) Single-image super-resolution: a benchmark. European Conference on Computer Vision (ECCV), pp. 372–386
Yang M-C, Wang YCF (2013) A self-learning approach to single image super-resolution. IEEE Trans Multimed 15(3):498–508
Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super-resolution. IEEE Trans Image Process 21(8):3467–3478
Yang J, Wang Z, Lin Z, Shu X, Huang T (2012) Bilevel sparse coding for coupled feature spaces. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2360–2367
Yang J, Wright J, Huang T, Ma Y (2010) Image super resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Zhou F, Yang W, Liao Q (2012) Single image super-resolution using incoherent sub-dictionaries learning. IEEE Trans Consum Electron 58(3):891–897
Zhu W, Liang S, Wei Y, Sun J (2014) Saliency optimization from robust background detection. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2814–2821
Zhu Y, Zhang Y, Yuille AL (2014) Single image super-resolution using deformable patches. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2917–2924
Acknowledgments
This work was supported by National Basic Research Program of China (973 Program) 2012CB821200 (2012CB821206) and the National Natural Science Foundation of China (No. 61320106006, No.61532006, No. 61502042).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liang, M., Du, J. & Li, L. Video super-resolution reconstruction based on correlation learning and spatio-temporal nonlocal similarity. Multimed Tools Appl 75, 10241–10269 (2016). https://doi.org/10.1007/s11042-015-2952-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-2952-3