基于混合粒子群算法的运动估计研究
|
摘要
针对块匹配运动估计算法中传统搜索方法的不足,提出了一种新的基于混合粒子群的块匹配运动估计算法。在保留系统随机搜索性能的同时根据运动矢量特性合理地设计初始搜索种群,并通过混沌差分进化搜索协同粒子群算法迭代寻优,混沌序列用于优化差分变异算子,以提高算法的精细搜索能力。通过相同点检测技术和恰当的终止计划有效地降低了系统的运算复杂度。经实验测试与验证,该算法在搜索质量和运算复杂度中达到了一种动态平衡的状态,其整体性能高于传统的快速运动估计算法,效果更逼近于穷举搜索法。
For the shortcomings of the traditional block matching motion estimation algorithms,we propose a new block matching motion estimation algorithm based on hybrid particle swarm optimization.The algorithm designs the initial search population according to the characteristics of motion vector while maintaining the performance of random search.The cooperative particle swarm optimization algorithm is iterated through the chaotic differential evolution search,and the chaos sequence is used to optimize the differential mutation operator so as to enhance the algorithm's fine search ability.The computational complexity of the algorithm is effectively reduced through the same point detection technology and an appropriate termination plan.Experimental results show that the algorithm achieves a dynamic balance between searching accuracy and computational complexity.Its overall performance is higher than the fast motion estimation algorithm,and the effect is closer to the exhaustive search method.
For the shortcomings of the traditional block matching motion estimation algorithms,we propose a new block matching motion estimation algorithm based on hybrid particle swarm optimization.The algorithm designs the initial search population according to the characteristics of motion vector while maintaining the performance of random search.The cooperative particle swarm optimization algorithm is iterated through the chaotic differential evolution search,and the chaos sequence is used to optimize the differential mutation operator so as to enhance the algorithm's fine search ability.The computational complexity of the algorithm is effectively reduced through the same point detection technology and an appropriate termination plan.Experimental results show that the algorithm achieves a dynamic balance between searching accuracy and computational complexity.Its overall performance is higher than the fast motion estimation algorithm,and the effect is closer to the exhaustive search method.
引文
[1]Yang P,He Y W,Yang S Q.An unsymmetrical-cross multiresolution motion search algorithm for MPEG4-AVC/H.264coding[C]∥Proc of IEEE International Conference on Multimedia and Expo,2004:531-534.
[2]Tekalp A M.Digital video processing[M].2nd Edition.New Jersey:Prentice Hall PTR,1998.
[3]Choudhury H A,Saikia M.Survey on block matching algorithms for motion estimation[C]∥Proc of IEEE International Conference on Communications and Signal Processing,2014:36-40.
[4]Zhang Ping,Wei Ping.Fast motion estimation algorithm based on particle swarm optimization with mutation[J].Journal of Electronic Measurement and Instrument,2011,25(1):23-28.(in Chinese)
[5]Cuevas E,Zaldívar D,Pérez-Cisneros M,et al.Block matching algorithm for motion estimation based on artificial bee colony(ABC)[J].Applied Soft Computing,2013,13(6):3047-3059.
[6]Cuevas E,Zaldívar D,Pérez-Cisneros M,et al.Block-matching algorithm based on differential evolution for motion estimation[J].Engineering Applications of Artificial Intelligence,2013,26(1):488-498.
[7]Liu X P,Xuan S B,Liu F.Single-dimension perturbation glowworm swarm optimization algorithm for block motion estimation[J].Mathematical Problems in Engineering 2013,2013(8):633-654.
[8]Pandian S I A,Bala G J,Anitha J.A pattern based PSO approach for block matching in motion estimation[J].Engineering Applications of Artificial Intelligence,2013,26(8):1811-1817.
[9]Liu B,Wang L,Jin Y H,et al.Designing neural networks using hybrid particle swarm optimization[C]∥Proc of International Symposium on Neural Networks,2005:391-397.
[10]Yang Chun-hua,Qian Xiao-shan,Gui Wei-hua.Hybrid algorithm of chaotic differential evolution and particle swarm optimization[J].Application Research of Computers,2011,28(2):439-441.(in Chinese)
[11]Liu Jian-ping.Hybrid particle swarm optimization algorithm based on chaos and differential evolution[J].Computer Simulation,2012,29(2):208-212.(in Chinese)
[12]Eberhart R C,Kennedy J.A new optimizer using particle swarm theory[C]∥Proc of the 6th International Symposium on Micro Machine and Human Science,1995:39-43.
[13]Zhu S,Ma K K.A new diamond search algorithm for fast block-matching motion estimation[J].IEEE Transactions on Image Processing,2000,9(2):287-290.
[14]Cheung C H,Po L M.A novel cross-diamond search algorithm for fast block motion estimation[J].IEEE Transactions on Circuits&Systems for Video Technology,2002,12(12):1168-1177.
[15]Ma K K,Hosur P I.Performance report of motion vector field adaptive search technique(MVFAST):MPEG2000/m5851[R].Singapore:Nanyang Technological University,2000.
[16]Storn R,Price K.Minimizing the real functions of the ICEC’96contest by differential evolution[C]∥Proc of IEEE International Conference on Evolutionary Computation,1996:842-844.
[4]张萍,魏平.基于变异粒子群的快速运动估计算法[J].电子测量与仪器学报,2011,25(1):23-28.
[10]阳春华,钱晓山,桂卫华.一种混沌差分进化和粒子群优化混合算法[J].计算机应用研究,2011,28(2):439-441.
[11]刘建平.基于混沌和差分进化的混合粒子群优化算法[J].计算机仿真,2012,29(2):208-212.
[2]Tekalp A M.Digital video processing[M].2nd Edition.New Jersey:Prentice Hall PTR,1998.
[3]Choudhury H A,Saikia M.Survey on block matching algorithms for motion estimation[C]∥Proc of IEEE International Conference on Communications and Signal Processing,2014:36-40.
[4]Zhang Ping,Wei Ping.Fast motion estimation algorithm based on particle swarm optimization with mutation[J].Journal of Electronic Measurement and Instrument,2011,25(1):23-28.(in Chinese)
[5]Cuevas E,Zaldívar D,Pérez-Cisneros M,et al.Block matching algorithm for motion estimation based on artificial bee colony(ABC)[J].Applied Soft Computing,2013,13(6):3047-3059.
[6]Cuevas E,Zaldívar D,Pérez-Cisneros M,et al.Block-matching algorithm based on differential evolution for motion estimation[J].Engineering Applications of Artificial Intelligence,2013,26(1):488-498.
[7]Liu X P,Xuan S B,Liu F.Single-dimension perturbation glowworm swarm optimization algorithm for block motion estimation[J].Mathematical Problems in Engineering 2013,2013(8):633-654.
[8]Pandian S I A,Bala G J,Anitha J.A pattern based PSO approach for block matching in motion estimation[J].Engineering Applications of Artificial Intelligence,2013,26(8):1811-1817.
[9]Liu B,Wang L,Jin Y H,et al.Designing neural networks using hybrid particle swarm optimization[C]∥Proc of International Symposium on Neural Networks,2005:391-397.
[10]Yang Chun-hua,Qian Xiao-shan,Gui Wei-hua.Hybrid algorithm of chaotic differential evolution and particle swarm optimization[J].Application Research of Computers,2011,28(2):439-441.(in Chinese)
[11]Liu Jian-ping.Hybrid particle swarm optimization algorithm based on chaos and differential evolution[J].Computer Simulation,2012,29(2):208-212.(in Chinese)
[12]Eberhart R C,Kennedy J.A new optimizer using particle swarm theory[C]∥Proc of the 6th International Symposium on Micro Machine and Human Science,1995:39-43.
[13]Zhu S,Ma K K.A new diamond search algorithm for fast block-matching motion estimation[J].IEEE Transactions on Image Processing,2000,9(2):287-290.
[14]Cheung C H,Po L M.A novel cross-diamond search algorithm for fast block motion estimation[J].IEEE Transactions on Circuits&Systems for Video Technology,2002,12(12):1168-1177.
[15]Ma K K,Hosur P I.Performance report of motion vector field adaptive search technique(MVFAST):MPEG2000/m5851[R].Singapore:Nanyang Technological University,2000.
[16]Storn R,Price K.Minimizing the real functions of the ICEC’96contest by differential evolution[C]∥Proc of IEEE International Conference on Evolutionary Computation,1996:842-844.
[4]张萍,魏平.基于变异粒子群的快速运动估计算法[J].电子测量与仪器学报,2011,25(1):23-28.
[10]阳春华,钱晓山,桂卫华.一种混沌差分进化和粒子群优化混合算法[J].计算机应用研究,2011,28(2):439-441.
[11]刘建平.基于混沌和差分进化的混合粒子群优化算法[J].计算机仿真,2012,29(2):208-212.