红外图像去斑算法及其实时实现

IR Image Speckle Reduction Algorithm and Its Real-Time Realization

  • 摘要: 针对某型红外观测系统非均匀定标受校正算法、环境变化等因素影响带来的黑斑和细胞状条纹问题,提出了基于神经网络的非均匀校正算法,并利用高速信号处理器和可编程器件研制成功了工程化硬件处理系统.经与红外观测系统联调结果表明,该算法在自适应地去除斑纹的同时可较好地保留图像的细节信息,并可在所研制的硬件系统上实时实现.

     

    Abstract: Regarding the appearance of black speckles and cell like stripes in the IR images of an IR observation system introduced by errors in assembly, environment, and nonuniformity in correction methods etc. after correction of the images for nonuniformity, an algorithm of nonuniformity correction based on neural network is proposed. A real time video signal processing system based on DSP and programmable devices is described in detail. Experimentation with the IR observation system showed that the algorithm is able to despeckle images adaptively and can be realized real time in the hardware system as proposed in this paper.

     

/

返回文章
返回
Baidu
map