基于对焦清晰度的双分辨相机变焦算法研究

双分辨率相机同时兼顾大视场和高分辨，利用同轴光学固定结构避免了变焦镜头运动部件带来的诸多问题，在深空探测目标跟踪和手机等智能终端上具有应用价值。针对现有的基于深度学习的双分辨率图像变焦算法的速度慢，信息量没有提升，图像网络结构适配性差和图像信息修复的伪造性等问题尝试性地提出了加入基于深度信息的解决办法。论证将图像对焦清晰度作为深度信息引入双分辨变焦算法的可行性，探讨对焦深度信息检测精度与效果，分别测试深度学习和基于深度信息的传统方法的双分辨率变焦算法，得到了一种不影响正常成像速度，内存开销降低35%和算法复杂度降低60%，超分辨信息真实可靠，图像结果评价提升10%到50%的全新算法。

Research on zoom algorithm based on dual resolution camera

The dual resolution camera combines large field of view and high resolution. The coaxial optical fixed structure avoids many problems caused by the moving parts of the zoom lens, and has potential application value in deep space detection target tracking and smart terminals such as mobile phones. The existing dual resolution image zoom algorithm based on deep learning has slow speed, no increase in information, poor adaptability of image network structure and forgery of image information restoration. To join a solution in normal image algorithm based on depth information was tentatively proposed in this paper. The feasibility of using image focus sharpness as depth information into the dual resolution zoom algorithm was demonstrated, the accuracy and effect of focus depth information detection was explored by Laplace image evaluation, and the dual resolution zoom algorithm of deep learning and traditional methods based on depth information was tested. The new excellent zoom algorithm used the space during normal focus of the camera which did not affect the imaging speed of normal images. The algorithm complexity is reduced by 60%, the computational memory overhead is reduced by 35%. The spatial relationship super-resolution information is more realistic and reliable, and the image result evaluation is improved by 10% to 50%.