一种复杂度约束下基于宏块优先顺序的运动估计优化算法  

An Optimized Motion Estimation Algorithm Based on Macroblock Priorities

作　　者：陆寄远[1,2] 张培钊[1] 段晓华[1] 朝红阳[3] 

机构地区：[1]中山大学信息科学与技术学院,广州510275 [2]广东金融学院计算机科学与技术系,广州510520 [3]中山大学软件学院,广州510275

出　　处：《计算机研究与发展》2011年第3期494-500,共7页Journal of Computer Research and Development

基　　金：国家"八六三"高技术研究发展计划基金项目(2007AA01Z340);广东省自然科学基金项目(07003728)

摘　　要：在实际应用中,视频编码算法不仅需要提供最好的编码效率,而且还需要自动地适应各种平台不同的计算能力约束.这是一个在复杂度约束下的率失真优化问题.针对视频编码消耗计算资源最多的运动估计过程,提出一种复杂度约束下的优化算法.该算法对运动估计的失真度和复杂度建模,并通过该模型决定每个宏块的预测失真度-复杂度斜率(distortion-complexity slope,DC-slope),以此决定各个宏块运动估计的优先顺序,然后通过一个常微分方程建立控制参数与计算复杂度之间的关系,准确地控制运动估计的计算复杂度.通过实验比较,本算法不仅可以自适应地调整运动估计的计算复杂度,而且能在不同的复杂度约束下提供优化的编码性能.In order to deploy highly efficient video coding technologies on different hardware platforms,computational complexity controllable algorithms are required.These algorithms should not only provide controllable computational complexity but also attain high coding performance under different computational complexity constraints.Since one of the significant resource consumers is motion estimation（ME）,we propose herein a computational complexity controllable ME algorithm.Firstly,we give an optimized frame level ME algorithm with adjustable computational complexity by constructing a model of distortion and computational complexity.The ME priority for each macroblocks（MBs）is the priority of distortion-complexity slope（DC-slope）which can be predicted by our proposed distortion and computational complexity model.The computational complexity of this algorithm can be adjusted by setting the number of MBs on which ME should perform.Secondly,an ordinary differential equation is being used to describe the relation between the parameter and the computational complexity of our algorithm.Then we give an efficient technique to adjust the parameter of the algorithm to meet any computational complexity constraints induced by the differing hardware platforms.According to our experimental results,the proposed algorithm precisely controls the complexity of motion estimation.Besides,our algorithm achieves better coding performance compared with other motion estimation algorithms.

关 键 词：视频编码 运动估计 可控复杂度 率失真优化 失真度复杂度模型 

分 类 号：TN919.81[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]