Adaptive dictionary learning for distributed compressive video sensing

作者：Wu Minghu; Zhu Xiuchang^*; Gan Zongliang; Li Xin

来源：International Journal of Digital Content Technology and Its Applications, 2012, 6(4): 141-149.

DOI：10.4156/jdcta.vol6.issue4.17

• Compressed video
• Compressive sensing
• Computation burden
• Data sampling
• Dictionary learning
• Distributed video coding
• Dynamic measurement
• Low-complexity
• Non-adaptive learning
• Rate allocation
• Sparse representation
• Video applications

Compressive sensing (CS) is a new technique for data sampling and compression simultaneously. In this paper, we propose a novel distributed video coding algorithm with dynamic measurement rate allocation based on compressive sensing principles, where almost all computation burdens can be shifted to the decoder, resulting in a very low-complexity encoder. So the proposed algorithm can be useful in those video applications that require very low complex encoders. At the decoder, the compressed video can be efficiently reconstructed with adaptive dictionary learning. The simulation results show that the proposed algorithm outperforms the distributed compressive video sensing with non-adaptive learning local dictionary and global dictionary.

• 出版日期2012
• 单位南京邮电大学