kelvin00's profile - activity

thank you very much， Median. I'll have a try to use the 128X64 and tell you the result.

Iam trying to train my own SVM using features extracted using HoG. Now i have one question. should the size of positve image must be 64x128? if the positive pictures are small ,and i can resize them to 64*128. however,the targets are wide.how can i build the positive picture? Dose the positive picture only include the target? thanks a lot.

thanks a lot , GilLevi.

There are more than 10000 pictures in the dataset, but only about 5000 annotations there. what can i do ? add annotations by myself? are there any good idea? thanks a lot

I want to use the PASCAL VOC image dataset2012.The pictures includes boats are my favorite. but I find that not every picture has one annotation. Should I make the annotations by myself? Thank you .

thank you .best wishes!

but why i can not get the right codec? are there some things wrong with my code? thank you ?

VideoCapture vido_file("D:\1.avi");

    if(vido_file.isOpened()==NULL)
            return -1;
    int ex = static_cast<int>(vido_file.get(CV_CAP_PROP_FOURCC));

i copy the codes from user manul,but i doesn't work. ex=1196444237,why ? thank you for help .