Abstract
At present, stereo video sequences are actively used in the movie industry, geographical information systems, and in navigation systems, among others. A novel motion estimation method simplifies the frames interpolation by forming an accurate set of local motion vectors in neighbour frames. First, the motion in a scene is estimated by block-matching algorithm roughly. Second, the accurate estimations are calculated according to type and velocity of motion. The Hu moments are used for a fast and transition motion in a scene. The Zernike moments are applied for fast and noisy scenes with a transition/rotation motion. The high statistical moments (kurtosis particularly) are reasonable for the accurate analysis of a slow motion. Such approach provides a smooth motion into additional interpolated frames that improves significantly the final stereo video sequence. Experimental results show the efficiency of the proposed method for frames interpolation. The detection of local motion vectors achieves 86% accuracy by usage the Zernike moments and 88% accuracy by a kurtosis calculation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Winkler, S., Min, D.: Stereo/multiview picture quality: Overview and recent advances. Signal Processing: Image Communication 28(10), 1358–1373 (2013)
Hu, M.K.: Visual Pattern Recognition by Moment Invariant. IRE Trans Info Theory IT-8, 179–187 (1962)
Yang, Z.L., Guo, B.L.: Image Registration Using Feature Points Extraction and Pseudo-Zernike Moments. In: Int. Conf. on Intelligent Information Hiding and Multimedia Signal Proc, pp. 752–755 (2008)
Revaud, J., Lavoue, G., Baskurt, A.: Improving Zernike moments comparison for optimal similarity and rotation angle retrieval. IEEE Trans on Pattern Analysis and Machine Intelligence 31(4), 627–636
Favorskaya, M.: Motion Estimation for Object Analysis and Detection in Videos. In: Kountchev, R., Nakamatsu, K. (eds.) Advances in Reasoning-Based Image Processing, Analysis and Intelligent Systems, vol. 29, pp. 211–253 (2012)
Richardson, I.E.: H.264 and MPEG-4 Video Compression: Video Coding for Next-generation Multimedia, 281 p. John Wiley and Sons, England (2003)
Zhu, C., Lin, X., Chau, L., Po, L.M.: Enhanced Hexagonal Search for Fast Block Motion Estimation. IEE Trans on Circuits and Systems for Video Technology 14(10), 1210–1214 (2004)
Cai, J., Pan, W.D.: On fast and accurate block-based motion estimation algorithms using particle swarm optimization. Info. Sci. 197, 53–64 (2012)
Jing, X., Chau, L.P.: An efficient three-step search algorithm for block motion estimation. IEEE Trans Multimedia 6(3), 435–438 (2004)
Po, L., Ma, W.: A novel four-step search algorithm for fast block motion estimation. IEEE Trans. Circuits Syst. Video Technol. 6(3), 313–317 (1996)
Li, R., Zeng, B., Liou, M.: A new three-step search algorithm for block motion estimation. IEEE Trans Circuits Syst Video Technol 4(4), 438–442 (1994)
Liu, L., Feig, E.: A block-based gradient descent search algorithm for block motion estimation in video coding. IEEE Trans. Circuits Syst. Video Technol. 6(4), 419–422 (1996)
Zhu, S., Ma, K.K.: A new diamond search algorithm for fast block-matching motion estimation. IEEE Trans. on Image Proc. 9(2), 287–290 (2000)
Cheung, C.H., Po, L.M.: A novel cross-diamond search algorithm for fast block motion estimation. IEEE Trans on Circuits and Systems for Video Technology 12(12), 1168–1177 (2002)
Cheung, C., Po, L.: A novel small-cross-diamond search algorithm for fast video coding and video conferencing applications. IEEE ICIP 12, 681–684 (2002)
Lam, C., Po, L., Cheung, C.: A novel kite-cross-diamond search algorithm for fast video coding and video conferencing applications. IEEE ICASSP-2004 3, 365–368 (2004)
Li, S., Xu, W., Zheng, N., Wang, H.: A novel fast motion estimation method based on genetic algorithm. Acta Electronica Sinica 28(6), 114–117 (2000)
Chu, W., Gao, X., Sorooshian, S.: A new evolutionary search strategy for global optimization of high-dimensional problems. Info. Sci. 181(22), 4909–4927 (2011)
Wang, H., Wu, Z., Rahnamayan, S., Liu, Y., Ventresca, M.: Enhancing particle swarm optimization using generalized opposition-based learning. Information Sciences 181(20), 4699–4714 (2011)
Alzoubi, H., Pan, W.: Fast and accurate global motion estimation algorithm using pixel subsampling. Info. Sci. 178(17), 3415–3425 (2008)
Yin, S., Na, J., Choi, J., Oh, S.: Hierarchical Kalman-particle filter with adaptation to motion changes for object tracking. Comput. Vision Image Understand. 115(6), 885–900 (2011)
Cui, Z., Jiang, G., Yang, S., Wu, C.: A new fast motion estimation algorithm based on the loopepipolar constraint for multiview video coding. Signal Process and Image Commun 27(2), 172–179 (2012)
Tedmori, S., Al-Najdawi, N.: Hierarchical stochastic fast search motion estimation algorithm. IET Comput. Vis. 6(1), 21–28 (2012)
Cuevasa, E., Zaldivara, D., Perez-Cisnerosa, M., Sossab, H., Osunab, V.: Block matching algorithm for motion estimation based on artificial bee colony (ABC). Appl in Soft Comput 13(6), 3047–3059 (2013)
Je, C., Park, H.M.: Optimized hierarchical block matching for fast and accurate image regis-tration. Signal Process Image Commun 28(7), 779–791 (2013)
Lowe, D.: Distinctive image features from scale-invariant key points. Int. J. of Computer Vision 60(2), 91–110 (2004)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Computer Vision and Image Understanding 110(3), 346–359 (2008)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Image Rochester NY, Technical Report CMU: 91–132 (1991)
Doshi, A., Bors, A.G.: Smoothing of optical flow using robustified diffusion kernels. Image and Vision Computing 28(12), 1575–1589 (2010)
Huang, A.M., Nguyen, T.: Correlation-based motion vector processing with adaptive interpolation scheme for motion-compensated frame interpolation. IEEE Trans on Image Proc. 18(4), 740–752 (2009)
Guo, D., Shao, L., Han, J.: Feature-based motion compensated interpolation for frame rate up-conversion. Neurocomputing 123, 390–397 (2014)
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. Proc. 7th Int Joint Conf on Artificial Intelligence 2, 674–679 (1981)
Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)
Mochizuki, Y., Kameda, Y., Imiya, A., Sakai, T., Imaizumi, T.: Variational method for super-resolution optical flow. Signal Processing 91(7), 1535–1567 (2011)
Yan, B., Chen, Y.: Low complexity image interpolation method based on path selection. J. Vis. Commun. Image R 24(6), 661–668 (2013)
Nisar, H., Malik, A.S., Choi, T.S.: Content adaptive fast motion estimation based on spatio-temporal homogeneity analysis and motion classification. Pattern Recognition Letters 33(1), 52–61 (2012)
Chen, W., Mied, R.P.: Optical flow estimation for motion-compensated compression. Image and Vision Computing 31(3), 275–289 (2013)
Chen, Y., Cai, C., Mab, K.-K., Wang, X.: Layered moving-object segmentation for stereoscopic video using motion and depth information. J Vis Commun. Image R 24(7), 829–837 (2013)
Park, C.S.: Level-set-based motion estimation algorithm for multiple reference frame motion estimation. J Vis Commun Image R 24(8), 1269–1275 (2013)
Huang, Z., Leng, J.: Analysis of Hus Moment Invariants on Image Scaling and Rotation. In: 2nd Int Conf on Computer Engineering and Technology (ICCET), vol. 7, pp. 476–480 (2010)
Zhang, H., Shu, H., Coatrieux, G., Zhu, J., Wu, Q.M.J., Zhang, Y., Zhu, H., Luo, L.: Affine Legendre Moment Invariants for Image Watermarking Robust to Geometric Distortions. IEEE Transactions on Image Processing 20(8), 2189–2199 (2011)
Rao, C.H.S., Kumar, S.S., Mohan, B.C.: Content Based Image Retrieval using Exact Legendre Moments and Support Vector Machine. Int J of Multimedia & Its Applications 2(2), 69–79 (2010)
Zhang, H., Shu, H.Z., Han, G.N., Coatrieux, G., Luo, L.M., Coatrieux, J.L.: Blurred image recognition by Legendre moment invariants. IEEE Trans Image Process 19(3), 596–611 (2010)
Chen, Z., Sun, S.K.: A Zernike moment phase-based descriptor for local image representation and matching. IEEE Trans Image Process 19, 205–219 (2010)
Shutler, J.D., Nixon, M.S.: Zernike velocity moments for sequence-based description of moving features. Image and Vision Computing 24(4), 343–356 (2006)
Yang, H., Pei, L.: Fast algorithm of subpixel edge detection based on Zernike moments. 4th Int Congress on Image and Signal Processing (CISP) 3, 1236–1240 (2011)
Sanjeev, K., Haleh, A., Mainak, B., Truong, N.: Real-Time Affine Global Motion Estimation Using Phase Correlation and its Application for Digital Image Stabilization. IEEE Transactions on Image Processing 20(12), 3406–3418 (2011)
Vyas, V.S., Rege, P.P.: Geometric transform Invariant Texture Analysis based on Modified Zernike Moments. J Fundamenta Informaticae 88(1–2), 177–192 (2008)
Frejlichowski, D.: Application of Zernike Moments to the problem of General Shape Analysis. Control & Cybernetics 40(2), 5–15 (2011)
Chandan, S., Neerja, M., Ekta, W.: Face recognition using Zernike and complex Zernike moment features. Pattern Recognition and Image Analysis 21(1), 71–81 (2011)
Chen, B.J., Shu, H.Z., Zhang, H., Chen, G., Toumoulin, C., Dillenseger, J.L., Luo, L.M.: Quaternion Zernike moments and their invariants for color image analysis and object recognition. Signal Processing 92(2), 308–318 (2012)
Guo, L.Q., Zhu, M.: Quaternion Fourier-Mellin moments for color image. Pattern Recognit 44(2), 187–195 (2011)
Wee, C.Y., Paramesran, R., Mukundan, R.: Fast computation of geometric moments using a symmetric kernel. Pattern Recognition 41(7), 2369–2380 (2008)
Papakostas, G.A., Koulouriotis, D.E.: A unified methodology for the efficient computation of discrete orthogonal image moments. Inform Sci 176(20), 3619–3633 (2009)
Boveiri, H.R.: On Pattern Classification Using Statistical Moments. Int J of Signal Pro-cessing, Image Processing and Pattern Recognition 3(4), 15–24 (2010)
Mukundan, R., Ong, S.H., Lee, P.A.: Image analysis by Tchebichef moments. IEEE Trans on Image Proc 10(9), 1357–1364 (2001)
Yap, P.T., Paramedran, R., Ong, S.H.: Image analysis by Krawtchouk moments. IEEE Trans on Image Proc 12(11), 1367–1377 (2003)
Yap, P.T., Paramedran, R., Ong, S.H.: Image analysis using Hahn moments. IEEE Trans on Pattern Analysis and Machine Intelligence 29(11), 2057–2062 (2007)
Mukundan, R.: A new class of rotational invariants using discrete orthogonal moments. In: 6th IASTED Conf on Signal and Image Processing SIP 2004, pp. 80–84 (2004)
Han, J.W., Suryanto, K., Kim, J.H., Sull, S., Ko, S.J.: New edge-adaptive image interpolation us-ing anisotropic Gaussian filters. Digital Signal Processing 23(1), 110–117 (2013)
Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vis. 43(1), 29–44 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Favorskaya, M., Pyankov, D., Popov, A. (2015). Accurate Motion Estimation Based on Moment Invariants and High Order Statistics for Frames Interpolation in Stereo Vision. In: Tweedale, J., Jain, L., Watada, J., Howlett, R. (eds) Knowledge-Based Information Systems in Practice. Smart Innovation, Systems and Technologies, vol 30. Springer, Cham. https://doi.org/10.1007/978-3-319-13545-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-13545-8_19
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13544-1
Online ISBN: 978-3-319-13545-8
eBook Packages: EngineeringEngineering (R0)