claycau's profile - activity

You can check this paper,"Using vanishing points to correct camera rotation in images". Obviously, it's time consuming to estimate the rotation between two images, and the result is not accurate.Maybe you should consider use another device.

Maybe you don't need to 'compute for all detected blobs the distace to the tracked object', you can just limit a region in previous location and predict the location by its path( you know the shortest may not be the best)

3Q I will try it later~~

Got it! I misunderstand your point. Your suggestion is right~

Hmm .... Maybe , in my code there is the same problem and I try to solve it by find where the “imread” is. And I find it in the opencv2\highgui.hpp. Obviously, I should cover it in my program.... and it really work in my code = =!

try to add #include <opencv2\highgui.hpp> in your code and recompile it

Maybe I should try to clip each picture by myself……

I try to make out the detail about how to run train_softcascade.exe. The source code seems it need a config.xml. But there is no doc about how to write it. I try to explain the code , but when I found the dictionary about the "trainPath", as follow

It confused me! Look, there are only walkmen in the picture but no landmark about where the walkman is. It has no info.txt like haartraining need to restrict the object's location in the picture.

Is there anybody who knows the reason?

3Q U :) Look I should try to learn more about opencv, it's really cool~

By use the getList function of class "Algorithm" we can know which algorithm can invoke.But when I use the latest version of opencv the getList result only have one algorithm "CLANE" The code I use as below:

 #include <opencv\cv.h>
#include <opencv\highgui.h>
#include <opencv2\core\core.hpp>
#include <vector>

using namespace std;


int main( int argc, char** argv )
{
    std::vector<cv::String> algorithms;
    cv::Algorithm::getList(algorithms);
    cout << "Algorithms: " << (int)algorithms.size() << endl;
    for (int i=0; i<(int)algorithms.size(); i++) {
        cout << algorithms[i] << endl;
    }

    getchar();
    return 0;
}

=======

Did U have the same problems?

Obviously, it need a config file. I try to read the source code to list the format of config file. However, I think the easiest way is to ask somebody who know it ...... heihei
whatever , 3Q U again :) Let me try it ~

According with the exp result I review your code，if add a "grouprectangles" function for the output location may be better. I found that the training of soft cascade is independent with adaboost. Can I train a detector by myself use haar or hog feature by the latest opencv?

3Q for your response! ^ ^ Hope it will help others~~

Hi, I have already download the latest opencv from github and successed compile it. I notice that the latest version realize the soft cascade algorithm and I want to test it. But I don't know how to detect a pedestrian use this method. Is there anybody know it? My platform is vs2010+win64+opencv3.00 ，