Similar articles

Abstract: In this paper, multiresolution critical-point filters (CPFs) are employed to image matching for frame rate up-conversion (FRUC). By CPF matching, the dense motion field can be obtained for representing object motions accurately. However, the elastic motion model does not hold in the areas of occlusion, thus resulting in blur artifacts in the interpolated frame. To tackle this problem, we propose a new FRUC scheme using an occlusion refined CPF matching interpolation (ORCMI). In the proposed approach, the occlusion refinement is based on a bidirectional CPF mapping. And the intermediate frames are generated by the bidirectional interpolation for non-occlusion pixels combined with unidirectional projection for the occlusion pixels. Experimental results show that ORCMI improves the visual quality of the interpolated frames, especially at the occlusion regions. Compared to the block matching based FRUC algorithm, ORCMI can achieve 1~2 dB PSNR gain for standard video sequences.

[1] Altnubasak, Y., Tekalp, A.M., 1997. Occlusion-adaptive, content-based mesh design and forward tracking. IEEE Trans. on Image Processing, 6(9):1270-1280.

[2] Beller, E.B., van Gurp, J.W., Janssen, J.G.W.M., Braspenning, R., Wittebrood, R., 2007. Solving Occlusion in Frame-rate Up-conversion. IEEE Int. Conf. Consumer Electronics, p.1-2.

[3] Castagno, R., Haavisto, P., Ramponi, G., 1996. A method for motion adaptive frame rate up-conversion. IEEE Trans. on Circuits Syst. Video Technol., 6(5):436-446.

[4] Chambers, B., Durand, J., Gans, N., Hutchinson, S., 2003. Dynamic Feature Point Detection for Visual Servoing Using Multiresolution Critical-point Filters. Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, p.504-509.

[5] Choi, B.D., Han, J.W., Kim, C.S., Ko, S.J., 2006. Frame rate up-conversion using perspective transform. IEEE Trans. on Consum. Electron., 52(3):975-982.

[6] Choi, B.D., Han, J.W., Kim, C.S., Ko, S.J., 2007. Motion-compensated frame interpolation using bilateral motion estimation and adaptive overlapped block motion compensation. IEEE Trans. on Circuits Syst. Video Technol., 17(4):407-416.

[7] Durand, J., Hutchinson, S., 2003. Real-time Object Tracking Using Multiresolution Critical Point Filters. Proc. IEEE Int. Conf. Robots and Automation, 2:1682-1687.

[8] Ha, T., Lee, S., Kim, J., 2004. Motion compensated frame interpolation by new block-based motion estimation algorithm. IEEE Trans. on Consum. Electron., 50(2):752-759.

[9] Haavisto, P., Juhola, J., Neuvo, Y., 1989. Fractional frame rate up-conversion using weighted median filters. IEEE Trans. on Consum. Electron., 35(3):272-278.

[10] Habuka, K., Shinagawa, Y., 2004. Image interpolation using enhanced multiresolution critical-point filters. Int. J. Comput. Vision, 58(1):19-35.

[11] Lee, S.H., Shin, Y.C., Yang, S.J., Moon, H.H., Park, R.H., 2002. Adaptive MC interpolation for frame rate up-conversion. IEEE Trans. on Consum. Electron., 48(3):444-450.

[12] Sanchez, O., 2003. Tracking of an Occluded Object in a Video Sequence. 7th Int. Symp. Signal Processing and Its Application, 2:231-234.

[13] Shinagawa, Y., Kunii, K.L., 1998. Unconstrained automatic image matching using multiresolutional critical-point filters. IEEE Trans. on Pattern Anal. Machine Intell., 20(9):994-1010.

[14] Wittebrood, R.B., de Haan, G., Lodder, R., 2003. Tackling Occlusion in Scan Rate Conversion Systems. IEEE Int. Conf. Consumer Electronics, p.344-345.

[15] Yang, Y.T., Tung, Y.S., Wu, J.L., 2007. Quality enhancement of frame rate up-converted video by adaptive frame skip and reliable motion extraction. IEEE Trans. on Circuits Syst. Video Technol., 17(12):1700-1713.

[16] Zhai, J., Yu, K., Li, J., Li, S., 2005. A Low Complexity Motion Compensated Frame Interpolation Method. Proc. IEEE Int. Symp. on Circuits and Systems, 5:4927-4930.