Caba's profile - activity

I don't understand where the smoothing problem appears. Are you grouping the pixel simply by color? E.g. all black pixel

Hi! have the same issue, did you manage to solve it?

Thanks for the link! I had misunderstood the BING algorithm exatcly as the person of that discussion. I am interesting in detect how many objects (whatever objects) there are in an image; so now I'm not sure I can use BING for that purpose (since the objects are novel obejcts, I should use use more object detection). But in the paper, the author got an image of a person and a ship detecting both, so, how did they do that? Using two different detectors and evaluating all the ROI given by the BING?

About the missing files, I don't know. I didn't try because I don't have a video to work with, so I just copied the interesting part of code to use the BING algorithm. With the code I posted it is working perfectly.

Hi all,

I am trying to use the cv::saliency::ObjectnessBING class to detect object in a frame, but I am not able to do it properly. There is an example of code here but with the BING algorithm, it does not display any result.

This is my code:

    String saliency_algorithm = "BING";
    String training_path = "../ObjectnessTrainedModel";
    vector<Vec4i> saliencyMap;

    Ptr<Saliency> saliencyAlgorithm = Saliency::create( saliency_algorithm );
    saliencyAlgorithm.dynamicCast<cv::saliency::ObjectnessBING>()->setTrainingPath( training_path );
    //saliencyAlgorithm.dynamicCast<cv::saliency::ObjectnessBING>()->setBBResDir( training_path + "/Results" );

if( saliencyAlgorithm->computeSaliency( image, saliencyMap ) )
{
       std::cout << "Objectness done" << std::endl;
}

        std::vector<float> values = saliencyAlgorithm.dynamicCast<cv::saliency::ObjectnessBING>()->getobjectnessValues();

for (int i = 0; i < saliencyMap.size(); ++i)
 {
            cv::rectangle(image, Point (saliencyMap[i][0],saliencyMap[i][1]), Point(saliencyMap[i][2],saliencyMap[i][3]) , Scalar(255,0,0),1,8, 0);
}

 cv::namedWindow( "Saliency Map", WINDOW_AUTOSIZE );// Create a window for display.
 cv::imshow( "Saliency Map", image );                   // Show our image inside it.

 cv::waitKey(0);

So, saliencyMap is the vector containing all the rectangle, and my vector values contains the score of each reactangle. How can I use that information for drawing the result? I Tried to draw the rectangle with the highest score but the resutls made no sense. Have I to use some more options? There are more methods to use in the class but I don't understand what they are useful for, also reading the original paper of the algorithm.

Thanks, It worked perfectly. Both compilation and building with no errors, and the usr/locacl/include/opencv2 folder contains knwo the headers files of the modules.

I don't know very well how it works, but if you write it as an answer I will accept it!

Thanks, I will try in a while

Hi all,

I'm facing several hours on installing opencv_contrib modules for opencv 3 beta. I can build and install opencv 3 beta correctly without problems and is working too. Then, looking at this answer I donwloaded the version of opencv_contrib for the opencv beta version. The to compile I run the command how specified in the repository of opencv_contrib, that is:

$ cmake -DOPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules ..

Where the opencv_contrib folder is placed in the same folder where the opencv-3.0.0-beta is located. Doing that command I got the error:

  Unknown CMake command "ocv_include_modules_recurse".

The person on that question resolved this problem simply by donwloading the opencv_contrib for the beta version (before he was using the master). But for me this is not working (I tried also with both).

To resolve that error I found this question that suggests to use the command:

   $ cmake -DOPENCV_EXTRA_MODULES_PATH=opencv_contrib/modules .

This is working well, I can then build with make but it seems that is not building anything because it tries to build all the opencv "standards" modules that I have previously built. But, in the folder build/modules/ the folders of the modules of the opencv_contrib have appeared (then the cmake -DOP.......), but they are empty, the have no headers, also then the building.

Hi to everyone,

i was trying to do the tutorial HDR (using openCV 3.0):

http://docs.opencv.org/trunk/doc/tutorials/photo/hdr_imaging/hdr_imaging.html#hdrimaging

and it works but the results, the fusion and the tonemapped image doesn't seem to be good, doesn't work like the tutorial.

I used a software to do an HDR on the same list of images and the result of the software is quite far from the images ldr,fusion of the HDR using OpenCV functions, moreover ldr and fusion images outputs are really different, no as in the tutorial that are "quite" similares.

Moreover i tried to run the program giving it as inputs images in .png and .jpg and the result with .jpg is a little bit more satisfactory ( you will find the both result in the file)

Images and result (35,21 MB): http://www.sendspace.com/file/cbuxlc

I hope you can help me, Thanks!

I got the same problem, i solved it installing the packet: ocl-icd-opencl-dev