In this paper,an improved optical flow method for image registration is proposed.It is novel in the way that it improves the optical flow method with an initial motion estimator:extended phase correlation technique(EP...In this paper,an improved optical flow method for image registration is proposed.It is novel in the way that it improves the optical flow method with an initial motion estimator:extended phase correlation technique(EPCT),using merits of the latter to compensate deficiencies of the former.In a more detailed manner,it can be said that the optical flow method can reach the sub-pixel accuracy and calculate complex distortion patterns like chirping and tilting but is weak with large-scale movements.Because EPCT covers measurements of large translations and rotations with pixel level accuracy and is efficient in the calculating load,it can be treated as a good initial motion estimator for optical flow method.Tests have proved that this improved method will significantly enhance the registration performance,especially,for images with large-scale movements and robust against random noises.展开更多
Log-polar transformation(LPT)is widely used in image registration due to its scale and rotation invariant properties.Through LPT,rotation and scale transformation can be made into translation displacement in log-polar...Log-polar transformation(LPT)is widely used in image registration due to its scale and rotation invariant properties.Through LPT,rotation and scale transformation can be made into translation displacement in log-polar coordinates,and phase correlation technique can be used to get the displacement.In LPT based image registration,constant samples in digitalization processing produce less precise and effective results.Thus,dynamic log-polar transformation(DLPT)is used in this paper.DLPT is a method that generates several sample sets in axes to produce several results and only the effective results are used to get the final results by using statistical approach.Therefore,DLPT can get more precise and effective transformation results than the conventional LPT.Mutual information(MI)is a similarity measure to align two images and has been used in image registration for a long time.An optimal transform for image registration can be obtained by maximizing MI between the two images.Image registration based on MI is robust in noisy,occlusion and illumination changing circumstance.In this paper,we study image registration using MI and DLPT.Experiments with digitalizing images and with real image datasets are performed,and the experimental results show that the combination of MI with DLPT is an effective and precise method for image registration.展开更多
文摘In this paper,an improved optical flow method for image registration is proposed.It is novel in the way that it improves the optical flow method with an initial motion estimator:extended phase correlation technique(EPCT),using merits of the latter to compensate deficiencies of the former.In a more detailed manner,it can be said that the optical flow method can reach the sub-pixel accuracy and calculate complex distortion patterns like chirping and tilting but is weak with large-scale movements.Because EPCT covers measurements of large translations and rotations with pixel level accuracy and is efficient in the calculating load,it can be treated as a good initial motion estimator for optical flow method.Tests have proved that this improved method will significantly enhance the registration performance,especially,for images with large-scale movements and robust against random noises.
基金the National Natural Science Foundation of China(Nos.61440016,61273225 and 61201423)the Natural Science Foundation of Hubei Province(No.2014CFB247)
文摘Log-polar transformation(LPT)is widely used in image registration due to its scale and rotation invariant properties.Through LPT,rotation and scale transformation can be made into translation displacement in log-polar coordinates,and phase correlation technique can be used to get the displacement.In LPT based image registration,constant samples in digitalization processing produce less precise and effective results.Thus,dynamic log-polar transformation(DLPT)is used in this paper.DLPT is a method that generates several sample sets in axes to produce several results and only the effective results are used to get the final results by using statistical approach.Therefore,DLPT can get more precise and effective transformation results than the conventional LPT.Mutual information(MI)is a similarity measure to align two images and has been used in image registration for a long time.An optimal transform for image registration can be obtained by maximizing MI between the two images.Image registration based on MI is robust in noisy,occlusion and illumination changing circumstance.In this paper,we study image registration using MI and DLPT.Experiments with digitalizing images and with real image datasets are performed,and the experimental results show that the combination of MI with DLPT is an effective and precise method for image registration.
