In order to implement real-time tracking of motion object in complex scene of image sequence, a novel tracking method based on Unscented Kalman filtering motion estimation with Camshift theory was introduced. Above all, the motion state of selected object in present frame was estimated with Unscented Kalman filtering, and then the possible position of selected object in next frame was predicted. Finally, the tracked object center was search in adjacent area of the possible position and the object was oriented with histogram color matching principia of Camshift method. Experiment results show that the proposal algorithm can not only effectively solve object sheltered problem induced by sudden motion, but also the tracking performance owing to pose movement is improved. It is very useful for machine controller to provide more precise coordinate error indication.
A novel algorithm of motion blur image restoration based on PSF half-blind estimation with Hough transform was
introduced on the basis of full analysis of the principle of TDICCD camera, with the problem that vertical uniform linear
motion estimation used by IBD algorithm as the original value of PSF led to image restoration distortion. Firstly, the
mathematical model of image degradation was established with the transcendental information of multi-frame images,
and then two parameters (movement blur length and angle) that have crucial influence on PSF estimation was set
accordingly. Finally, the ultimate restored image can be acquired through multiple iterative of the initial value of PSF
estimation in Fourier domain, which the initial value was gained by the above method. Experimental results show that
the proposal algorithm can not only effectively solve the image distortion problem caused by relative motion between
TDICCD camera and movement objects, but also the details characteristics of original image are clearly restored.