摘要
为了避免全零DCT(离散余弦变换)系数进行变换与量化产生的冗余计算,从H.264中的DCT公式与量化原理出发,结合视频图像残差系数的分布规律,在分析现有算法存在的误判与漏判的基础上,提出了一种预先判断全零DCT系数块的方法。实验结果表明,与文献中的经典算法相比较,新提出的方法应用在中低比特率的视频序列中可以减少12%~37%的平均编码时间,平均压缩率提高了6%~10%。
An innovative algorithm for detecting all-zero discrete cosine transform (DCT) coefficient blocks prior to DCT and quantization forvideocodingstandardofH.264/AVCispresented. A mathematic model for predetermination is established based on the characteristics of float/integer DCT formula and quantization, the distribution of the residual pixel values, analysis of the false-judgment and miss-judgment of prevent algorithms. The simulation results show that compared to conventional methods, the proposed algorithm achieves averagely an 12%-37% encoding time saving and an 6%-10% improvement of compression rate with a little PSNR loss for low or middle bit-rate video sequences.
出处
《计算机工程与设计》
CSCD
北大核心
2011年第11期3745-3749,共5页
Computer Engineering and Design
基金
国家自然科学基金项目(50975019)