Matlab 进阶学习记录

时间 2019-11-05

原文原文链接

Matlab 进阶学习记录css

最近在看 Faster RCNN的Matlab code，发现不少matlab技巧，活到老，学到老。。。html

1. conf_proposal = proposal_config('image_means', model.mean_image, 'feat_stride', model.feat_stride);python

function conf = proposal_config(varargin)
% conf = proposal_config(varargin)
% --------------------------------------------------------
% Faster R-CNN
% Copyright (c) 2015, Shaoqing Ren 
% Licensed under The MIT License [see LICENSE for details]
% --------------------------------------------------------
    
    ip = inputParser ; 
    
    %% training
 ip.addParamValue('use_gpu', gpuDeviceCount > 0, ... @islogical);
                                    
    % whether drop the anchors that has edges outside of the image boundary
    ip.addParamValue('drop_boxes_runoff_image', ...
                                        true,           @islogical);
    
    % Image scales -- the short edge of input image                                                                                                
    ip.addParamValue('scales',          600,            @ismatrix);
    % Max pixel size of a scaled input image
    ip.addParamValue('max_size',        1000,           @isscalar);
    % Images per batch, only supports ims_per_batch = 1 currently
    ip.addParamValue('ims_per_batch',   1,              @isscalar);
    % Minibatch size
    ip.addParamValue('batch_size',      256,            @isscalar);
    % Fraction of minibatch that is foreground labeled (class > 0)
    ip.addParamValue('fg_fraction',     0.5,           @isscalar);
    % weight of background samples, when weight of foreground samples is
    % 1.0
    ip.addParamValue('bg_weight',       1.0,            @isscalar);
    % Overlap threshold for a ROI to be considered foreground (if >= fg_thresh)
    ip.addParamValue('fg_thresh',       0.7,            @isscalar);
    % Overlap threshold for a ROI to be considered background (class = 0 if
    % overlap in [bg_thresh_lo, bg_thresh_hi))
    ip.addParamValue('bg_thresh_hi',    0.3,            @isscalar);
    ip.addParamValue('bg_thresh_lo',    0,              @isscalar);
    % mean image, in RGB order
    ip.addParamValue('image_means',     128,            @ismatrix);
    % Use horizontally-flipped images during training ?
    ip.addParamValue('use_flipped',     true,           @islogical);
    % Stride in input image pixels at ROI pooling level (network specific)
    % 16 is true for {Alex,Caffe}Net, VGG_CNN_M_1024, and VGG16
    ip.addParamValue('feat_stride',     16,             @isscalar);
    % train proposal target only to labled ground-truths or also include
    % other proposal results (selective search, etc.)
    ip.addParamValue('target_only_gt',  true,           @islogical);

    % random seed                    
    ip.addParamValue('rng_seed',        6,              @isscalar);

    
    %% testing
    ip.addParamValue('test_scales',     600,            @isscalar);
    ip.addParamValue('test_max_size',   1000,           @isscalar);
    ip.addParamValue('test_nms',        0.3,            @isscalar);
    ip.addParamValue('test_binary',     false,          @islogical);
    ip.addParamValue('test_min_box_size',16,            @isscalar);
    ip.addParamValue('test_drop_boxes_runoff_image', ...
                                        false,          @islogical);
    
    ip.parse(varargin{:}); conf = ip.Results;
    
    assert(conf.ims_per_batch == 1, 'currently rpn only supports ims_per_batch == 1');
    
    % if image_means is a file, load it...
    if ischar(conf.image_means)
        s = load(conf.image_means);
        s_fieldnames = fieldnames(s);
        assert(length(s_fieldnames) == 1);
        conf.image_means = s.(s_fieldnames{1});
    end
end

The inputParser object allows you to manage inputs to a function by creating an input scheme. To check the input, you can define validation functions for required arguments, optional arguments, and name-value pair arguments. Optionally, you can set properties to adjust the parsing behavior, such as handling case sensitivity, structure array inputs, and inputs that are not in the input scheme.ios

After calling the parse method to parse the inputs, the inputParser saves names and values of inputs that match the input scheme (stored in Results), names of inputs that are not passed to the function and, therefore, are assigned default values (stored in UsingDefaults), and names and values of inputs that do not match the input scheme (stored in Unmatched).json

Check the validity of required and optional function inputs.

Create a custom function with required and optional inputs in the file findArea.m.

function a = findArea(width,varargin)
   p = inputParser;
   defaultHeight = 1;
   defaultUnits = 'inches';
   defaultShape = 'rectangle';
   expectedShapes = {'square','rectangle','parallelogram'};

   addRequired(p,'width',@isnumeric); addOptional(p,'height',defaultHeight,@isnumeric); addParameter(p,'units',defaultUnits); addParameter(p,'shape',defaultShape,... @(x) any(validatestring(x,expectedShapes)));

   parse(p,width,varargin{:});
   a = p.Results.width .* p.Results.height;

The input parser checks whether width and height are numeric, and whether the shape matches a string in cell array expectedShapes. @ indicates a function handle, and the syntax @(x) creates an anonymous function with input x.

Call the function with inputs that do not match the scheme. For example, specify a nonnumeric value for the width input:

findArea('text')
Error using findArea (line 14)
The value of 'width' is invalid. It must satisfy the function: isnumeric.
Specify an unsupported value for shape:

findArea(4,'shape','circle')
Error using findArea (line 14)
The value of 'shape' is invalid. Expected input to match one of these strings:

square, rectangle, parallelogram

The input, ''circle'', did not match any of the valid strings.

　http://www.cnblogs.com/heleifz/p/matlab-function-handle.html　网络

2. assert 语句的使用：app

　　assert： Generate an error when a condition is violated.　　dom

　　assert(EXPRESSION, ERRMSG) evaluates EXPRESSION and, if it is false,　displays the string contained in ERRMSG. When ERRMSG is the last input to　assert, MATLAB displays it literally, without performing any substitutions　on the characters in ERRMSG.ide

　　例如：若是 contion 不成立，则会输出对应的：提示错误信息。函数

    assert(mod(conf.batch_size, num_images) == 0, ...
        sprintf('num_images %d must divide BATCH_SIZE %d', num_images, conf.batch_size));

3. permute 函数：

　Permute array dimensions.

B = permute(A,ORDER) rearranges the dimensions of A so that they

are in the order specified by the vector ORDER.

　　从新安排矩阵的x,y,z , 在二维中就至关于把x,y 对换，在三维中至关于能够把三个坐标的位置互换。


好比A = 
A(:,:,1)=repmat(1,3,3);
A(:,:,2)=repmat(2,3,3);
A(:,:,3)=repmat(3,3,3);
disp(A);

A(:,:,1) =

     1     1     1
     1     1     1
     1     1     1


A(:,:,2) =

     2     2     2
     2     2     2
     2     2     2


A(:,:,3) =

     3     3     3
     3     3     3
     3     3     3

At = permute(A,[3,2,1]);
disp(At);

At(:,:,1) =

     1     1     1
     2     2     2
     3     3     3


At(:,:,2) =

     1     1     1
     2     2     2
     3     3     3

At(:,:,3) =

     1     1     1
     2     2     2
     3     3     3
permute(A,[3,2,1])

4. cellfun 函数:

　　cellfun: Apply a function to each cell of a cell array. A = cellfun(FUN, C) applies the function specified by FUN to the contents of each cell of cell array C, and returns the results in the array A.

5. 从列表 A 中去搜索列表 B 中是否存在有相交元素，即：求　A and B 的差。

select = importdata('/home/wangxiao/Documents/Sun-80-dataset/VGG_16/iter_1/SUN80_50%_selected_without_HD.txt');
Unlabel = importdata('/home/wangxiao/Documents/Sun-80-dataset/iter_1/Sun_100_UnLabel_Train_0.5_.txt');

fid = fopen('/home/wangxiao/Documents/Sun-80-dataset/VGG_16/iter_1/SUN80_50%_Unselected_data.txt', 'a') ;

selected_list = [] ;  
unselected_list = [] ; 

for i = 1:size(Unlabel.data, 1)
    disp(['deal with: ', num2str(i) , '/' , num2str(size(Unlabel.data, 1))]) ;
    unlabel_name = Unlabel.textdata{i, 1};  % Unlabel image name
    unlabel_label = Unlabel.data(i, 1) ;    % Unlabel image label 
    count = 0; 
    for j = 1:size(select.textdata, 1)
        select_name = select.textdata{j, 1};  % selected image name 
        
        if strcmp(unlabel_name, select_name) % if have selected, jump it. 
            selected_list = [selected_list; unlabel_name];
            % break; 
        else
            count = count + 1; 
        end 
        if count == size(select.textdata, 1)
            fprintf(fid, '%s ', num2str(unlabel_name));
            fprintf(fid, '%s \n', num2str(unlabel_label));
        end
    end 
    
end

6. containers.Map() 的用法

　　matlab中的containers.Map()有点相似于C++ STL中的map容器，具备key/value映射的功能.

　　 num = containers.Map({1, 2, 3}, {'one', 'two', 'three'})

　　myMap = containers.Map(KEYS, VALUES) constructs a Map object myMap that contains one or more keys and a value for each of these keys, as specified in the KEYS and VALUES arguments.

　　例如：从 Map 上提取一个值：myValue = myMap(key) ;

　　修改键值对 (key-values pairs): myMap(key) = newValue ;

　　增长一个新的键值对：myMap(key) = newValue ;

　　能够经过 remove 的方法将　values 删除掉。

7. try catch end　机制：

　　该机制能够防止因为程序中可能出现的错误而终止运行的状况：

　　try

　　　ld 　　　　= load(anchor_cache_file) ;

　　 anchors 　= ld.anchors ;

　　catch

　　　base_anchor　　= [1, 1, opts.base_size, opts.base_size] ;

　　 ratio_anchors = ratio_jitter(base_anchor, opts.ratios) ;

　　end

8. About change the gray image into 3 channel RGB image:

 1 clc; close all; clear all;  2 image = imread('/home/wangxiao/Documents/mnist_dataset/mnist_0_.png');  3 image = im2double(image);  4 image = double(image);  5 width = size(image, 1); height = size(image, 2);  6 
 7 synthetic = zeros([224, 224]);  8 
 9 for i = 1:size(image, 1) 10 for j = 1:size(image, 2) 11 
12 synthetic(i, j) = image(i, j); 13 synthetic(i, j) = image(i, j); 14 synthetic(i, j) = image(i, j); 15 end 16 end 17 synthetic = im2uint8(synthetic); 18 imshow(synthetic); 19 figure; imshow(image); 20 
21 %% 
22 synthetic2 = zeros([224, 224, 3]); 23 
24 for i = 1:size(image, 1) 25 for j = 1:size(image, 2) 26 
27 synthetic2(i, j, 1) = image(i, j, 1); 28 synthetic2(i, j, 2) = image(i, j, 2); 29 synthetic2(i, j, 3) = image(i, j, 3); 30 end 31 end 32 synthetic2 = im2uint8(synthetic2); 33 imshow(synthetic2);

synthetic is a single channel image, and synthetic2 is a three channel image.

Another Solution is:

% if grayscale repeat one channel to match filters size
if(size(im, 3)==1)
im = repmat(im, [1 1 3]);
end

9. Divided the image into specific patches using matlab function: mat2cell

　　This is a really cool function. For example, you read one image and divide it into 3*3 = 9 patches, and we assume the resolution of the image is: 100*100, you just need set the vectors M = [20, 30, 50]; N = [20, 20, 60] ;

Actually, as long as the sum of three values you set equal to 100 (here is 20, 30, 50), it will be ok. The other vector N have the same reason.

10. Read images from disks and save these frames into avi video files.

 1 %% change the frame to videos to save.  2 clc; close all; clear all;  3 path = '/home/wangxiao/Downloads/files/Visual_Tracking/MDNet-CVPR2016/saved_tracking_results_MDNet_OTB100/Biker/';  4 files = dir([path, '*.png']);  5 count = 0;  6  
 7 for i=1:size(files, 1)  8     xxx =  strtok(files(i).name, 'M');  9     name = xxx(7:end-1); 10     image = imread([path, files(i).name]); 11     index = sprintf('%04d', str2double(name)); 12     newName = [ index,'.jpg']; 13     
14 %    a = sprintf('%04d',i); 15     
16  imwrite(image, [path, newName]); 17 end
18 
19 disp('==>> deal with image done !') 20  
21  
22 jpgFiles = dir([path, '*.jpg']); 23 videoName = '/home/wangxiao/Videos/Biker_MDNet_OTB100.avi'; 24 fps = 25; %帧率 25 startFrame = 1; %从哪一帧开始 26 endFrame = size(jpgFiles, 1); %哪一帧结束 27 
28 %生成视频的参数设定 29 aviobj=VideoWriter(videoName);  %建立一个avi视频文件对象，开始时其为空 30 aviobj.FrameRate=fps; 31 
32 open(aviobj);%Open file for writing video data 33 
34 for i=startFrame:endFrame 35     frames = imread([path, jpgFiles(i).name]); 36     frames = im2frame(frames); 37  writeVideo(aviobj, frames); 38 end
39 close(aviobj); 40 
41 disp('==>> saved the video !')

11. Matlab中save实现保存数据到mat文件的正确使用参考：http://blog.csdn.net/fx677588/article/details/52836348

 1 1. 普通保存在当前文件夹下  2 
 3 　　save matPath.mat A B;   % A B都是生成的数据矩阵  4 
 5 　　须要注意这种方式只能将数据保存在当前文件夹下的第一个参数文件中，下面这样写并不能将数据保存到你想要的文件夹中的。  6 
 7 　　saldir = './result/';  8 　　savePath = [saldir imnames(len).name(1:end-4) '_KSD'];  9 　　save savePath A; 10 
11 　　上面程序也只能实如今当前文件夹下生成savePath.mat文件，而后数据保存到该文件中。并不能保存到须要的文件夹中。正确的写法是下面的方式。 12 
13 2. 保留数据到其余文件夹下 14 
15 　　saldir = './result/'; 16 　　savePath = [saldir imnames(len).name(1:end-4) '_KSD' '.mat']; 17 　　save(savePath,'A');  % 保存到其余文件夹的写法 18 
19     这里也须要注意，保存的数据矩阵，即save函数的第二个参数不能够忘记单引号。

12. 根据 attention maps 置信度的高低，生成对应的 bounding box ：

clc;close all;clear all; Img=imread('/home/wangxiao/Documents/files/Visual_Tracking/MDNet-CVPR2016/MDNet-master/attentionMap/Basketball/0001.png'); if ndims(Img)==3 I=rgb2gray(Img); else I=Img; end I=im2bw(I,graythresh(I)); [m,n]=size(I); imshow(I);title('binary image'); txt=get(gca,'Title'); set(txt,'fontsize',16); L=bwlabel(I); stats=regionprops(L,'all'); set(gcf,'color','w'); set(gca,'units','pixels','Visible','off'); q=get(gca,'position'); q(1)=0;%设置左边距离值为零 q(2)=0;%设置右边距离值为零 set(gca,'position',q); for i=1:length(stats) hold on; rectangle('position',stats(i).BoundingBox,'edgecolor','y','linewidth',2); temp = stats(i).Centroid; plot(temp(1),temp(2),'r.'); drawnow; end frame=getframe(gcf,[0,0,n,m]); im=frame2im(frame); imwrite(im,'a.jpg','jpg');%能够修改保存的格式

Python Implementation: (from: https://www.jianshu.com/p/7693222523c0 )

import numpy as np
import scipy.ndimage as ndi
from skimage import measure,color
import matplotlib.pyplot as plt

#编写一个函数来生成原始二值图像
def microstructure(l=256):
    n = 5
    x, y = np.ogrid[0:l, 0:l]  #生成网络
    mask = np.zeros((l, l))
    generator = np.random.RandomState(1)  #随机数种子
    points = l * generator.rand(2, n**2)
    mask[(points[0]).astype(np.int), (points[1]).astype(np.int)] = 1
    mask = ndi.gaussian_filter(mask, sigma=l/(4.*n)) #高斯滤波
    return mask > mask.mean()

data = microstructure(l=128)*1 #生成测试图片

labels=measure.label(data,connectivity=2)  #8连通区域标记
dst=color.label2rgb(labels)  #根据不一样的标记显示不一样的颜色
print('regions number:',labels.max()+1)  #显示连通区域块数(从0开始标记)

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4))
ax1.imshow(data, plt.cm.gray, interpolation='nearest')
ax1.axis('off')
ax2.imshow(dst,interpolation='nearest')
ax2.axis('off')

fig.tight_layout()
plt.show()

若是想分别对每个连通区域进行操做，好比计算面积、外接矩形、凸包面积等，则须要调用measure子模块的regionprops（）函数。该函数格式为：

skimage.measure.regionprops(label_image)

返回全部连通区块的属性列表，经常使用的属性列表以下表：

属性名称 类型 描述 area int 区域内像素点总数 bbox tuple 边界外接框(min_row, min_col, max_row, max_col) centroid array　　 质心坐标 convex_area int 凸包内像素点总数 convex_image ndarray 和边界外接框同大小的凸包　　 coords ndarray 区域内像素点坐标 Eccentricity float 离心率 equivalent_diameter float 和区域面积相同的圆的直径 euler_number int　　 区域欧拉数 extent float 区域面积和边界外接框面积的比率 filled_area int 区域和外接框之间填充的像素点总数 perimeter float 区域周长 label int 区域标记

13. 将 video 切割为 frame:

%% Input 2 videos and divide it into frames
clc; clear all; close all;
infraredvideo = 'C:\Users\王逍\Desktop\跟踪数据集\videos\';
savePath = 'C:\Users\王逍\Desktop\跟踪数据集\frames\';

% devide the infrared video into infrared images
videoList1=dir(fullfile(infraredvideo,'*.mp4'));
video_num=length(videoList1);

for j=1:video_num
    
    infraredOutPath = [savePath, videoList1(j).name, '\'];
    mkdir(infraredOutPath);
    
    frames = VideoReader([strcat(infraredvideo,videoList1(j).name)]);
    numFrames =frames.NumberOfFrames;
    for k = 1 : numFrames
        disp(['==>> processing video ',num2str(k),' frames, please waiting....']);
        frame = read(frames,k);
        frame = imresize(frame, [480, 640]);
        % figure(1); imshow(frame);
        imwrite(frame, [infraredOutPath, sprintf('%08d.png',k)]);
    end
    
end

14. divide the total attention maps according to given video frames such as TC128.

 1 %% 
 2 clc; close all; clear all;  3 path = '/media/wangxiao/E1F171026416B63F/tracking_benchmark/Temple-color-128/predicted_attentionMaps-v1/';  4 attentionfiles = dir([path, '*.png']);  5 
 6 videoPath = '/media/wangxiao/E1F171026416B63F/tracking_benchmark/Temple-color-128/videos/';  7 videoFiles = dir(videoPath);  8 videoFiles = videoFiles(3:end);  9 total = 0; 10 savepath = '/media/wangxiao/E1F171026416B63F/tracking_benchmark/Temple-color-128/attentionMaps_per_video-v1/'; 11 
12 
13 for i=1:size(videoFiles, 1) 14     numCount = 0; 15     videoName = videoFiles(i).name; 16     newVideoPath = [videoPath videoName '/img/']; 17     
18     videoframes = dir([newVideoPath, '*.jpg']); 19 
20     savePath = [savepath videoName '/']; 21  mkdir(savePath); 22     
23     disp(['==>> deal with video file: ', num2str(i)]); 24 %     total = total + size(videoframes, 1); 25     
26     for j=1:size(videoframes, 1) 27         if numCount < size(videoframes, 1) 28             total = total + 1; 29             numCount = numCount + 1; 30             img = imread([path attentionfiles(total).name]); 31             % figure(1); imshow(img); 32             
33             temp = sprintf('%04d', numCount); 34             saveName = [temp '.png']; 35  imwrite(img, [savePath saveName]); 36         else 
37             break; 38         end
39 
40     
41 
42     end
43 
44 
45 
46 end
47

View Code

15. count the image list into txt files.

 1 %%
 2 market1501_path = '/home/wangxiao/Downloads/person-ReID/open-reid/examples/data/market1501/';  3 txtsavePath = '/home/wangxiao/Downloads/person-ReID/open-reid/examples/data/market1501/image_txt_list/';  4 
 5 bounding_box_test = [market1501_path 'bounding_box_test/'];  6 bounding_box_train = [market1501_path 'bounding_box_train/'];  7 gt_bbox = [market1501_path 'gt_bbox/'];  8 gt_query = [market1501_path 'gt_query/'];  9 images = [market1501_path 'images/']; 10 query = [market1501_path 'query/']; 11 
12 
13 % ##################### 
14 bounding_box_test_files = dir([bounding_box_test, '*.jpg']); 15 bounding_box_train_files = dir([bounding_box_train, '*.jpg']); 16 gt_bbox_files = dir([gt_bbox, '*.jpg']); 17 gt_query_files = dir([gt_query, '*.jpg']); 18 images_files = dir([images, '*.jpg']); 19 query_files = dir([query, '*.jpg']); 20 
21 %% image files I 22 fid = fopen([txtsavePath 'bounding_box_test_files_image_list.txt'], 'w'); 23 for i=1:size(bounding_box_test_files, 1) 24     imgName = bounding_box_test_files(i).name; 25     fprintf(fid, '%s \n', imgName); 26 end
27 fclose(fid); 28 disp('==>> done I'); 29 
30 %% image files II 31 fid = fopen([txtsavePath 'bounding_box_train_files_image_list.txt'], 'w'); 32 for i=1:size(bounding_box_train_files, 1) 33     imgName = bounding_box_train_files(i).name; 34     fprintf(fid, '%s \n', imgName); 35 end
36 fclose(fid); 37 disp('==>> done II'); 38 
39 %% image files III 40 fid = fopen([txtsavePath 'gt_bbox_files_image_list.txt'], 'w'); 41 for i=1:size(gt_bbox_files, 1) 42     imgName = gt_bbox_files(i).name; 43     fprintf(fid, '%s \n', imgName); 44 end
45 fclose(fid); 46 disp('==>> done III'); 47 
48 
49 %% image files IV 50 fid = fopen([txtsavePath 'gt_query_files_image_list.txt'], 'w'); 51 for i=1:size(gt_query_files, 1) 52     imgName = gt_query_files(i).name; 53     fprintf(fid, '%s \n', imgName); 54 end
55 fclose(fid); 56 disp('==>> done IV'); 57 
58 
59 %% image files V 60 fid = fopen([txtsavePath 'images_files_image_list.txt'], 'w'); 61 for i=1:size(images_files, 1) 62     imgName = images_files(i).name; 63     fprintf(fid, '%s \n', imgName); 64 end
65 fclose(fid); 66 disp('==>> done V'); 67 
68 
69 
70 
71 %% image files VI 72 fid = fopen([txtsavePath 'query_files_image_list.txt'], 'w'); 73 for i=1:size(query_files, 1) 74     imgName = query_files(i).name; 75     fprintf(fid, '%s \n', imgName); 76 end
77 fclose(fid); 78 disp('==>> done VI');

View Code

16. load json files using matlab code.

　　this used package from: http://blog.csdn.net/sophia_xw/article/details/70141208 　　

　　unzip this file and add path to matlab like this:

clear all; clc  
  
addpath('/home/wangxiao/jsonlab-1.5/jsonlab-1.5');
  
fname='results.json';  
jsonData=loadjson(fname);

17. 伪彩色图像的生成：

%% 
clc; close all; clear all; 
path = '\MotorRolling\';
files = dir([path, '*.png']);
savePath = '\fakeColor_MotorRolling\'; 

ori_img_path = '\Benchmark\MotorRolling\img\';
ori_img = imread([ori_img_path, '0001.jpg']);
oriFiles = dir([ori_img_path, '*.jpg']);
height = size(ori_img, 1); 
width = size(ori_img, 2);

for img_idex =1:length(files)
    im = imread([path, files(img_idex).name]);
    originalImage = imread([ori_img_path, oriFiles(img_idex).name]);
    
%     for idx =1:size(im, 1)
%         for jdx = 1:size(im, 2)
%                if im(idx, jdx) <= 30; 
%                    im(idx, jdx) = 0; 
%                end 
%         end 
%     end 
    
    I=double(im);
    [m,n]=size(I);
    L=256;
    for i=1:m
        for j=1:n
            if I(i,j)<=L/4
                R(i,j)=0;
                G(i,j)=4*I(i,j);
                B(i,j)=L;
            else if I(i,j)<=L/2
                    R(i,j)=0;
                    G(i,j)=L;
                    B(i,j)=-4*I(i,j)+2*L;
                else if I(i,j)<=3*L/4
                        R(i,j)=4*I(i,j)-2*L;
                        G(i,j)=L;
                        B(i,j)=0;
                    else
                        R(i,j)=L;
                        G(i,j)=-4*I(i,j)+4*L;
                        B(i,j)=0;
                    end
                end
            end
        end
    end
    for i=1:m
        for j=1:n
            rgbim(i,j,1)=R(i,j);
            rgbim(i,j,2)=G(i,j);
            rgbim(i,j,3)=B(i,j);
        end
    end
    rgbim=rgbim/256;
%     figure;
%     subplot(1,2,1);
%     imshow(gray);
%     subplot(1,2,2);

    fake_color_img = imresize(rgbim, [height, width]); 
    imshow(fake_color_img);
    imwrite(fake_color_img, [savePath, oriFiles(img_idex).name]);
    
    img_idex
    
    
    
end

18. frame to video transformation

%% 
clc; close all; clear all; 
videoPath='\demo_videos\demo_Skater2\';
salVideo = '\Benchmark\Skater2\img\';
resultsPath = '\saved_figure_tracking_results\Skater2\v\'; 
file=dir([videoPath,'*.jpg']);
file_=dir([salVideo,'*.jpg']);
resultsFiles = dir([resultsPath, '*.jpg']);
writerObject = VideoWriter('OUR_Skater2.avi');
writerObject.FrameRate =25; %writerObject.Quality = 50;
open( writerObject );
Num= length(file);
for k =1 : Num
    trackingResults = imread([resultsPath, resultsFiles(k).name]);
    disp(['processing the ',num2str(k),'/',num2str(Num),' frames, please waiting....']);
    frame_1 = imread([videoPath,file(k).name]);
    frame_222 = imread([salVideo,file_(k).name]);
    
    frame_2 = zeros(size(frame_222, 1), size(frame_222, 2), 3); 
    if size(frame_222, 3) == 1 
        frame_2(:,:,1) =  frame_222; 
        frame_2(:,:,1) =  frame_222; 
        frame_2(:,:,1) =  frame_222; 
    end 
    frame_2 = uint8(frame_2); 
    
    frame_3 = frame_1*0.5+frame_2*0.5;
    trackingResults = imresize(trackingResults, [size(frame_2, 1), size(frame_2, 2)]);
    fullframe = [ frame_2, frame_3, trackingResults ];
    writeVideo( writerObject, fullframe );
end
close( writerObject );

19. video to frame transformation:

clear all;close all;

%% video
videoPath='.\2\';
outPath='.\2\';

T=[1.72844 0.0692766 -293
    -0.0692766 1.72844 -94
    0 0 1];

tform = maketform('affine', T');
videoList=dir(fullfile(videoPath,'*.avi'));
video_num=length(videoList);
for j=1:video_num
    
    frames = VideoReader (strcat(videoPath,videoList(j).name));
    numFrames =frames.NumberOfFrames;
    for k = 1 : numFrames
        disp(['processing the ',num2str(k),' frames, please waiting....']);
        frame = read(frames,k);
        transformFrame = imtransform(frame,tform,'XData',[1 320], 'YData',[1 240]);
        %             frame=imresize(frame,[288,384]);
        imwrite(transformFrame,[outPath,sprintf('%08d.png',k)]);
        
    end
    
end