基于Kalman预测的自适应De-interlace算法

本文提出一种基于Kalman预测的自适应De-interlace算法.它包括运动块检测、自适应的运动估计以及对运动块的运动补偿和对静止块的场复制等模块.其中,运动块检测用了连续的4场图像,能够更精确地实现运动检测;对检测到的运动块用Kalman滤波进行自适应地运动估计,并根据估计到的运动矢量进行运动补偿;对静止块,用场复制法进行De-interlace处理.该算法在de-interlace性能接近全搜索算法的前提下,运算量降低了三个数量级.

Adaptive De-interlacing algorithm based on Kalman forecast

An adaptive de-interlacing algorithm based on Kalman forecast is presented in this paper. It consists of 3 modules, the detection of motion blocks, the adaptive motion estimation with Kalman filtering, and the motion compensation for motion blocks and field repetition for static blocks. The motion blocks can be accurately detected by using successive 4-field images. The motion estimation module with Kalman filtering searches motion vector only for motion blocks, and the search model is adaptive to motion velocity and acceleration. Two de-interlacing strategies are adopted to meet the different requirements of motion blocks and static blocks respectively. Compared with full search algorithm, the proposed algorithm greatly reduces the computational cost with keeping the de-interlacing performance approximately.