CVPR18_TM_codes

本文档主要用于图像的倾斜矫正，通过建立透视变换矩阵和强角点检测实现畸变图形的矫正(This document is mainly used for Image tilt correction, through the establishment of perspective transformation matrix and strong corner detection, to achieve distortion correction)

说明：  图像重建算法当中的FDK、ART和TV算法，以及算法评估的SSIM和MSE的评估代码(FDK, ART and TV algorithms in image reconstruction algorithms, and the evaluation codes of SSM and MSE for algorithm evaluation)

使用山头(hill)标记法，对显著图寻找显著区域,(hill mark)

自己编写的关于2013年的文章 a variational method for multi-source remote-sensing image fusion 的程序，基本实现了相关功能。(I have written a progrma about a variational method for multi-source remote-sensing image fusion publish in 2013,and the basic functions of the problems have been solved.)

说明：  应用于fluent的UDF程序，用于修正液滴表面轮廓(The UDF is applied fluent procedures for correcting the droplet surface contour)

％通过耦合神经网络结合中值滤波实现图像的降噪源代码( Through the combination of coupled neural network filtering image noise source code)

图像处理效果评价,评价指标包括峰值信噪比，熵，以及均方误差，具体公式请参考相关文献(photo)

转辙机图像采集板区域参数设置上位机界面程序，转辙机通信协议，多项式拟合参数及阈值设置。(Switch machine image acquisition board area parameter set PC interface program, switch machine communication protocols, polynomial fitting parameters and the threshold value is set.)

说明：  matlab输入CAD图像文件，matlab中图形导入CAD，matlab与CAD互转(Matlab Input CAD Image File or graphics Import into CAD in matlab or matlab and CAD Interchange)

该代码用于实现视觉目标跟踪研究中的协方差跟踪，能够把多种时空特征融合于统一的模型中，在实现视觉目标跟踪时具有较好的鲁棒性，而且其维数等于使用特征的数量，与各个特征的维数无关，因此，其计算复杂度较小，实时性较好。(This code is used to realize covariance tracking in the research field of visual object tracking of computer vision. It enables fusion of various spatial-temporal features into an unified object feature model, hence robust to noise. In addition, its dimension is equal to the number of the features used and independent of the dimensions of the features used. Therefore, it satisfies the requirement of real-time application due to its low computation cost.)