噪声环境下光流场快速稳健估计方法研究
|
摘要
针对噪声影响下光流计算稳健性较差及收敛速度慢的问题,提出一种噪声环境下光流场快速稳健估计方法。所提算法基于噪声环境下光流场估计方法,引入惩罚因子以增强光流计算稳健性,并在光流计算迭代公式中加入动量因子缩短光流计算收敛时间以加快光流场计算。而后基于变分方法极小化光流能量函数求解欧拉-拉格朗日方程,最后通过迭代方法求得速度场。仿真结果表明,对视频中连续两帧图片加入不同高斯噪声后,与M算法及ML算法相比,所提算法可显著增强光流场计算稳健性,缩短光流计算收敛时间,加快光流场计算。
To address the issue of poor robustness and slow convergence speed in the calculation of optical flow under the influence of noise, a fast robust method for the optical flow field estimation in noisy environment is proposed. Based on the estimation method of optical flow in noisy environment, a penalty factor is introduced to enhance the robustness of the calculation of optical flow, a momentum factor is added to the iterative formula of optical flow calculation to shorten the convergence time of optical flow calculation, and then the calculation of the optical flow field is accelerated. The Euler-Lagrange equation is solved by minimizing the energy function of optical flow on the basis of the variation principle. Finally, the velocity field is obtained by using the iterative method. Simulation results show that, as compared to the M algorithm and the ML algorithm, the proposed algorithm can enhance the robustness of the optical flow considerably, shorten the convergence time of optical flow calculation and speed up the calculation of the optical flow field, after adding two different Gaussian noises to two consecutive frames in the video.
To address the issue of poor robustness and slow convergence speed in the calculation of optical flow under the influence of noise, a fast robust method for the optical flow field estimation in noisy environment is proposed. Based on the estimation method of optical flow in noisy environment, a penalty factor is introduced to enhance the robustness of the calculation of optical flow, a momentum factor is added to the iterative formula of optical flow calculation to shorten the convergence time of optical flow calculation, and then the calculation of the optical flow field is accelerated. The Euler-Lagrange equation is solved by minimizing the energy function of optical flow on the basis of the variation principle. Finally, the velocity field is obtained by using the iterative method. Simulation results show that, as compared to the M algorithm and the ML algorithm, the proposed algorithm can enhance the robustness of the optical flow considerably, shorten the convergence time of optical flow calculation and speed up the calculation of the optical flow field, after adding two different Gaussian noises to two consecutive frames in the video.
引文
[1]HORN B K P,SCHUNCK B G.Determining optical flow[J].Artificial Intelligence,1981,17(1/2/3):185-203.
[2]GOPPERT J,YANTEK S,HWANG I.Invariant Kalman filter application to optical flow based visual odometry for UAVs[C]//The 9th International Conference on Ubiquitous and Future Networks,2017:99-104.
[3]童姜况.光流改进算法研究及其在四旋翼无人机中的应用[D].杭州:浙江大学,2017.
[4]韩月乔.基于改进光流法的超声序列图像超分辨率重建[D].沈阳:东北大学,2015.
[5]叶春明.一种基于全局运动补偿的HS光流检测算法[J].光学与光电技术,2015,13(5):87-92.
[6]蒋菱,程赓.基于LK光流跟踪法的有效目标点增强跟踪[J].微型机与应用,2015,34(6):45-49.
[7]刘恒建,任侃,顾国华,等.基于KLT特征点的LK光流金字塔FPGA实现[J].电视技术,2014,38(15):92-97.
[8]张建明,钱东海.一种局部和全局相结合的光流计算方法[J].计算机工程与科学,2005,27(5):33-35.
[9]DE'RIAN P,ALMAR R.Wavelet-based optical flow estimation of instant surface currents from shore-based and UAV videos[J].IEEE Transactions on Geoscience and Remote Sensing,2017,50(10):5790-5797.
[10]MUKAWA N.Optical-model-based analysis of consecutive images[J].Computer Vision and Image Understanding,1997,66(1):25-32.
[11]马龙,王鲁平,陈小天,等.噪声环境下光流场估计方法[J].信号处理,2012,28(1):87-91.
[12]KUMAR P,KUMAR S,BALASUBRAMANIAN R.A fractional order total variation model for the estimation of optical flow[C]//The 5th National Conference on Computer Vision,Pattern Recognition,Image Processing and Graphics,2015:1-4.
[13]樊勇.基于高斯噪声的图像去噪算法研究[D].成都:西南石油大学,2014.
[14]CHAMBOLLE A,LIONS P L.Image recovery via total variation minimization and related problems[J].Numerische Mathematik,1997,76(2):167-188.
[15]曾凯,陈至坤,RAMAN P,等.基于HS光流法机器人避障策略优化[J].科学技术与工程,2017,17(17):85-89.
[16]张会生,吴微.一种具有自适应动量因子的BP算法[J].大连海事大学学报:自然科学版,2008,34(4):45-47.
[17]BARRON J L,FLEET D J,BEAUCHEMIN S S.Performance of optical flow techniques[J].International Journal of Computer Vision,1994,12(1):43-77.
[2]GOPPERT J,YANTEK S,HWANG I.Invariant Kalman filter application to optical flow based visual odometry for UAVs[C]//The 9th International Conference on Ubiquitous and Future Networks,2017:99-104.
[3]童姜况.光流改进算法研究及其在四旋翼无人机中的应用[D].杭州:浙江大学,2017.
[4]韩月乔.基于改进光流法的超声序列图像超分辨率重建[D].沈阳:东北大学,2015.
[5]叶春明.一种基于全局运动补偿的HS光流检测算法[J].光学与光电技术,2015,13(5):87-92.
[6]蒋菱,程赓.基于LK光流跟踪法的有效目标点增强跟踪[J].微型机与应用,2015,34(6):45-49.
[7]刘恒建,任侃,顾国华,等.基于KLT特征点的LK光流金字塔FPGA实现[J].电视技术,2014,38(15):92-97.
[8]张建明,钱东海.一种局部和全局相结合的光流计算方法[J].计算机工程与科学,2005,27(5):33-35.
[9]DE'RIAN P,ALMAR R.Wavelet-based optical flow estimation of instant surface currents from shore-based and UAV videos[J].IEEE Transactions on Geoscience and Remote Sensing,2017,50(10):5790-5797.
[10]MUKAWA N.Optical-model-based analysis of consecutive images[J].Computer Vision and Image Understanding,1997,66(1):25-32.
[11]马龙,王鲁平,陈小天,等.噪声环境下光流场估计方法[J].信号处理,2012,28(1):87-91.
[12]KUMAR P,KUMAR S,BALASUBRAMANIAN R.A fractional order total variation model for the estimation of optical flow[C]//The 5th National Conference on Computer Vision,Pattern Recognition,Image Processing and Graphics,2015:1-4.
[13]樊勇.基于高斯噪声的图像去噪算法研究[D].成都:西南石油大学,2014.
[14]CHAMBOLLE A,LIONS P L.Image recovery via total variation minimization and related problems[J].Numerische Mathematik,1997,76(2):167-188.
[15]曾凯,陈至坤,RAMAN P,等.基于HS光流法机器人避障策略优化[J].科学技术与工程,2017,17(17):85-89.
[16]张会生,吴微.一种具有自适应动量因子的BP算法[J].大连海事大学学报:自然科学版,2008,34(4):45-47.
[17]BARRON J L,FLEET D J,BEAUCHEMIN S S.Performance of optical flow techniques[J].International Journal of Computer Vision,1994,12(1):43-77.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |