Motion Estimations based on Invariant Moments for Frames Interpolation in Stereovision

Abstract At present, stereo video sequences are actively used in the movie industry, in geographical information systems, and in navigation systems, among others. A novel method improves the frames interpolation by forming an invariant set of local motion vectors. First, the motion in a scene is estimated by block-matching algorithm. Second, accurate estimations by using Hu moments (for a noisy video sequence Zernike moments) are calculated. Such approach provides smooth motion that significantly improves the resulting stereo video sequence. Experimental results show the efficiency of frames interpolation based on such approach. The detection of local motion vectors achieves 86% accuracy.

[1]  Bao-Long Guo,et al.  Image Registration Using Feature Points Extraction and Pseudo-Zernike Moments , 2008, 2008 International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[2]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[3]  Lei Pei,et al.  Fast algorithm of subpixel edge detection based on Zernike moments , 2011, 2011 4th International Congress on Image and Signal Processing.

[4]  Gang Chen,et al.  Quaternion Zernike moments and their invariants for color image analysis and object recognition , 2012, Signal Process..

[5]  Dimitris E. Koulouriotis,et al.  A unified methodology for the efficient computation of discrete orthogonal image moments , 2009, Inf. Sci..

[6]  Jinsong Leng,et al.  Analysis of Hu's moment invariants on image scaling and rotation , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[7]  Atilla Baskurt,et al.  Improving Zernike Moments Comparison for Optimal Similarity and Rotation Angle Retrieval , 2009, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  M. Favorskaya.  Motion Estimation for Objects Analysis and Detection in Videos , 2012 .

[9]  Huazhong Shu,et al.  Blurred Image Recognition by Legendre Moment Invariants , 2010, IEEE Transactions on Image Processing.

[10]  H. R. Boveiri.  On Pattern Classification Using Statistical Moments , 2010 .

[11]  B. Chandra Mohan,et al.  Content Based Image Retrieval Using Exact Legendre Moments and Support Vector Machine , 2010, ArXiv.

[12]  Mark S. Nixon,et al.  Zernike velocity moments for sequence-based description of moving features , 2006, Image Vis. Comput..

[13]  Zen Chen,et al.  A Zernike Moment Phase-Based Descriptor for Local Image Representation and Matching , 2010, IEEE Transactions on Image Processing.

[14]  Raveendran Paramesran,et al.  Fast computation of geometric moments using a symmetric kernel , 2008, Pattern Recognit..

[15]  Priti P. Rege,et al.  Geometric transform Invariant Texture Analysis based on Modified Zernike Moments , 2008, Fundam. Informaticae.

[16]  C. Singh,et al.  Face recognition using Zernike and complex Zernike moment features , 2011, Pattern Recognition and Image Analysis.

[17]  Yue Zhang,et al.  Affine Legendre Moment Invariants for Image Watermarking Robust to Geometric Distortions , 2011, IEEE Transactions on Image Processing.

[18]  D. Frejlichowski.  Application of Zernike Moments to the problem of General Shape Analysis , 2011 .

[19]  Truong Q. Nguyen,et al.  Real-Time Affine Global Motion Estimation Using Phase Correlation and its Application for Digital Image Stabilization , 2011, IEEE Transactions on Image Processing.