Motion Estimations based on Invariant Moments for Frames Interpolation in Stereovision

AbstractAt 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