FLY's profile - activity

Error on reading directly from camera When I try to run a video from code camera = cv2.VideoCapture("E:\\true2.mp4")it r

How to find pixel per meter I have a static camera through which I am focusing on the covered area, total covered area b

How to find pixel per meter I have a static camera through which I am focusing on the covered area, total covered area b

How to find pixel per meter I have a static camera through which I am focusing on the covered area, total covered area b

I am trying to save the frames which have entropy >0.78 , i want to save that specific frames from my video file , it may be more than 100 frames , i tried it , Below is my code

if (entropy>0.78)
          {
            detector.detect(pre_img, keypoint2);
            if (keypoint2.size() >= 20)
            {
              RetainBestKeypoints(keypoint2, 20);
              dextract.compute( pre_img, keypoint2, descriptors_2);
              Mat my_img_3 = descriptors_2.reshape(1,1);

              float response = svm.predict(my_img_3);
              if (response==1)
              {
                 count_4++;

                 cv::imwrite("images.jpg", pre_img);

              }
         }
       }

This code is not saving all the images , i want to save it in a specific directory like D:\images\

I am trying to blend two image or you can say put one image on other image , when i apply blending overlay on the image or simple merge two image it show me brightness in it.

here are my two images (first image is empty from inside like PS vignette)

and the other is

The code which i did is

int main( int argc, char** argv )
{
    Mat img=imread("E:\\vig.png",-1); 
    Mat ch[4]; 
    split(img,ch);
    Mat im2 = ch[3];              // here's the vignette
    im2 = 255 - im2; // eventually cure the inversion
    Mat img2 = imread("E:\\ew.jpg");
    Mat out2;
    blending_overlay3(img2 , im2 , out2);
    imshow("image",out2);
    imwrite("E:\\image.jpg",out2);
    waitKey();}

It show me the result like

but i require result like

EDIT

The first image is hollow/empty from center (the vignette one) , but when i read the image (vignette one) with my program then it become solid(bright) from the center , the history behind its implementation is here

There is the only problem and its with first (vignette) image reading , if it read as it is , like hollow/empty from the center , so that the other image with which we merge/blend/weight whatever apply it didn't effect the center part of the image , not even show brightness etc , that's what i want to do

I am trying to draw the circle in the center if the images , like the image below

there may be the images of many shapes/size but i want to draw circle/eclipse every time in the same way.

Below is the code i tried for it

        Mat img = imread ("E:\\test.jpg");
        int center_img = (img.rows*img.cols)/2;
        double radius_img = img.rows/2+img.cols/2;
        circle(img,Point(img.rows/2,img.cols/2), img.rows/2,1, 8,0);
        imshow ("img" , img);
        cvWaitKey(0);

I am trying to make filters like sepia filter in my app like other photo editing applications , till now I don't have any idea about it , Can any one help me out for it about its algorithms and how to do it ? and Can I implement in opencv using native c++ or we have any of its build in functions ?

Below is some part of my code , which is running fine but after a long processing it show me the run time error

Initialization part

std::vector< DMatch > matches;
Ptr<DescriptorMatcher> matcher = DescriptorMatcher::create("FlannBased");
Ptr<DescriptorExtractor> extractor = new SurfDescriptorExtractor();

SurfFeatureDetector detector(500);
std::vector<KeyPoint> keypoints;
int dictionarySize = 1500;
TermCriteria tc(CV_TERMCRIT_ITER, 10, 0.001);
int retries = 1;
int flags = KMEANS_PP_CENTERS;
BOWKMeansTrainer bow(dictionarySize, tc, retries, flags);
BOWImgDescriptorExtractor dextract(extractor,matcher);

// Initialize constant values
const int nb_cars = files.size();
const int not_cars = files_no.size();
const int num_img = nb_cars + not_cars; // Get the number of images

As my personal approach i think error starts from here

// Initialize your training set.
cv::Mat training_mat(num_img,image_area,CV_32FC1);
cv::Mat labels(num_img,1,CV_32FC1);
std::vector<string> all_names;
all_names.assign(files.begin(),files.end());
all_names.insert(all_names.end(), files_no.begin(), files_no.end());
// Load image and add them to the training set
int count = 0;
Mat unclustered;
vector<string>::const_iterator i;
string Dir;
for (i = all_names.begin(); i != all_names.end(); ++i)
{
    Dir=( (count < files.size() ) ? YourImagesDirectory : YourImagesDirectory_2);

    tmp_img = cv::imread( Dir +*i, 0 );

    resize( tmp_img, tmp_dst, tmp_dst.size() );

    Mat row_img = tmp_dst; // get a one line image.

    detector.detect( row_img, keypoints);

    extractor->compute( row_img, keypoints, descriptors_1);

    unclustered.push_back(descriptors_1);
    //bow.add(descriptors_1);

    ++count;
}

cout<<"second part";
int count_2=0;
vector<string>::const_iterator k;
Mat vocabulary = bow.cluster(unclustered);
dextract.setVocabulary(vocabulary);
for (k = all_names.begin(); k != all_names.end(); ++k)
{
    Dir=( (count_2 < files.size() ) ? YourImagesDirectory : YourImagesDirectory_2);

    tmp_img = cv::imread( Dir +*k, 0 );

    resize( tmp_img, tmp_dst, tmp_dst.size() );

    Mat row_img = tmp_dst; // get a one line image.

    detector.detect( row_img, keypoints);

    dextract.compute( row_img, keypoints, descriptors_1);

    training_mat.push_back(descriptors_1);

    labels.at< float >(count_2, 0) = (count_2<nb_cars)?1:-1; // 1 for car, -1 otherwise*/

    ++count_2;
}

After processing sometime it show me the below runtime error Error :

Edit :

Mat training_mat(0,dictionarySize,CV_32FC1);

to

Mat training_mat(1,extractor->descriptorSize(),extractor->descriptorType());

but didn't solve the problem

I am using opencv c++ for making the blending mode like in photoshop , i want to make overlay mode in it , i search its alternate in opencv in which i found this blending way , but its not the overlay as i want to use the overlay method in it.

overlay method formula from this documentation

(Target > 0.5) * (1 - (1-2*(Target-0.5)) * (1-Blend)) +
(Target <= 0.5) * ((2*Target) * Blend)

Can any one please explain this formula for implementation in opencv c++ , how i can easy understand it for implementation or is there any already build in function for it or any other easy way out :P

As far circle detection concern : Study the curvature of every contour pixel and check if it fits a circle or ellipse. This check may be done by computing a histogram of edge orientations for the contour pixels, or by checking the gradients of orienations from contour pixel to contour pixel. In the second case, for a circle or ellipse, the gradients should be almost uniform . Refrence

For Different color detection

What about first detecting the circles and then with color values you can use detect green , as far as sun shine concern we can give a range of values to green color like if green color having value "1" then lets suppose with sun shine it become more light so cann't we suggest the program like if color goes light from 1 to 0.5 it that particular circle then its green as well .

did you check the path by making it simple like cv::Mat image = cv::imread(C://bottle_label.jpg"); ?

Did you check it with cv::namedWindow("My Image"); by removing 1

I am using OpenCv on Android , when I run the application it give me option of installing OpenCv manager , I don't want to use this option for my application. For this I followed this answer from this forum , I follow the steps but still its asking me for OpenCv manager.

Below is my android.mk

and Properties option

Followed OpenCv this link.

I open the official opencv website for downloading opencv ,

then i clicked on OpenCV for Windows from VERSION 3.0 BETA , then this page open

and when i click on opencv.2.4.11.exe then it start downloading , after completion of downloading dos command runs and I cannt get where my opencv folder is .

As suggested by @StevenPuttemans I cleared my browsing history but still getting this.

@StevenPuttemans yes i did

I will open new thread with snapshots

Thanks @steven , Actually i use the official link as well , i Click on beta version 3.0 (OpenCV for Windows) then next page opens then next page displays Looking for the latest version? Download opencv-2.4.11.exe (367.7 MB) and i click on it.