摘要
针对在航空航天遥感领域中使用CCD相机对景物进行成像时 ,由于像元尺寸的限制导致图像分辨率低的问题 ,提出了采用人工神经网络映射图像重构过程非线性特性的方法 .在相机参数已知的情况下 ,用后向误差传播 (BP)神经网络融合从不同角度对同一景物重复拍照得到的多帧低分辨率图像的冗余信息 ,重构得到较高分辨率的图像 .在模拟成像仿真实验中得到了分辨率提高 4倍、信噪比接近
The reconstruction of super-resolution image based on backpropagation neural network algorithm is proposed to provide a higher quality reconstructed image with the resolution improved by 4 times to avoid error accumulating of CG iterations and to get high-resolution image by using backpropagation neural network to map the nonlinear processing of reconstruction. It differs from those methods based on equation iterative solution and can greatly improve the quality of super-resolution image.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2003年第6期707-710,共4页
Journal of Harbin Institute of Technology
