Fast and low memory usage coding for image and video based on wavelet transform
Abstract
A new video codec based on three-dimensional wavelet subband coding with 3-D BCWT is presented. This new video codec has almost identical PSNR performance to the well-known 3-D SPIHT video codec. However, it is much more computationally efficient and uses much less internal memory than 3-D SPIHT. Implementation results of 3-D BCWT show that it can achieve real time decoding with strictly software implementation on a PC. Application of the 3-D BCWT algorithm to volumetric medical images shows that it can also achieve good performance.
Although the BCWT algorithm itself uses much less memory than the SPIHT algorithm, the total system memory usage in BCWT coding is still high due to the large memory consumption of the wavelet transform. In this dissertation, the line-based BCWT algorithm is also presented, which utilizes the line-based wavelet transform to achieve BCWT coding. Due to the backward coding feature of the BCWT algorithm, the line-based BCWT algorithm can significantly reduce the overall system memory usage. Depending upon the image size, the memory usage of the line-based BCWT algorithm can be less than 1% of the memory usage of the SPIHT algorithm. Compared with the original BCWT algorithm, the line-based BCWT algorithm can use less than 2% of the memory that the BCWT algorithm consumes, thus making this algorithm extremely suitable for implementation on resource-limited platforms.