Adaptive temporal compressive sensing for video with motion estimation
- 105 Downloads
In this paper, we present an adaptive reconstruction method for temporal compressive imaging with pixel-wise exposure. The motion of objects is first estimated from interpolated images with a designed coding mask. With the help of motion estimation, image blocks are classified according to the degree of motion and reconstructed with the corresponding dictionary, which was trained beforehand. Both the simulation and experiment results show that the proposed method can obtain accurate motion information before reconstruction and efficiently reconstruct compressive video.
KeywordsComputational imaging Compressive sensing Image reconstruction Motion estimation
This work is supported by Fundamental Research Funds for the Central Universities and Space Innovation Fund Project, Jiangsu Science and Technology Program (BE2016119).
- 1.Hitomi, Y., Gu, J., Gupta, M., Mitsunaga, T., Nayar, S.K.: Video from a single coded exposure photograph using a learned over-complete dictionary. In: Proc. IEEE International Conference on Computer Vision: (ICCV), pp. 287–294, (2011)Google Scholar
- 4.Nagahara, H., Sonoda, T., Endo, K., Sugiyama, Y., Taniguchi, R.: High-speed imaging using CMOS image sensor with quasi pixel-wise exposure. In Proc. International Conference on Computational Photography, pp. 1–11 (2016)Google Scholar
- 10.Iliadis, M., Spinoulas, L., Katsaggelos, A.K., et al.: Deep fully-connected networks for video compressive sensing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
- 12.Yuan, X., Yang, J., Llull, P., Liao, X., Sapiro, G., Brady, D.J., Carin, L.: Adaptive temporal compressive sensing for video. In: IEEE International Conference on Image Processing: (ICIP), pp. 14–18, (2013)Google Scholar
- 17.Reddy, D., Veeraraghavan, A., Chellappa, R.: P2C2: programmable pixel compressive camera for high speed imaging. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR),pp 329–336, (2011)Google Scholar
- 20.Brox, T., et al.: High accuracy optical flow estimation based on a theory for warping. In: European Conference on Computer Vision, pp 25–36 ,(2004)Google Scholar