Ask Your Question

Andyrey's profile - activity

2016-03-24 07:36:58 -0600 commented answer how to restore front view of inclined plane from 3 vector projections

Thanks,Tetragramm, I will try. I have no idea about camera matrix members, I will fill them with "1"s or something trivial. Neither I know about where the corresponding "1"s are in my image, so I expect to obtain rectangle with rectangular shape (and it will be a good result itself!), but further stretching along X or Y will do from some other features.

2016-03-23 09:43:30 -0600 asked a question how to restore front view of inclined plane from 3 vector projections

I see some plane P in my image I(x,y),which has unknown angle with my image plane. In my image I I can extract 3 projections of vectors a, b ,c, all them are perpendicular to each other in real 3D, so that a and b lie in that plane P, and c is normal to that plane. I do not have that vectors directly, but only their projections to my image plane. How can I get frontal view of that plane P from that vectors projections, if it is possible?

2016-02-11 10:25:21 -0600 commented answer CascadeClassifier::detectMultiScale alogical influence of minSize parameter

Thank you for the answers, Steven. So far, there is no sense to set minSize less then model's size.

2016-02-11 08:50:04 -0600 commented answer CascadeClassifier::detectMultiScale alogical influence of minSize parameter

So, my image consecutively shrinks by detecMultiScale function (not enlarged) and detection happens in step when object in image becomes equal to model's size, which is fixed. Thus, minSize and maxSize together with -scaleFactor define only number of steps in this loop, not actual minimum (or maximum) possible object size?

2016-02-11 08:20:18 -0600 received badge  Supporter (source)
2016-02-11 05:50:17 -0600 received badge  Editor (source)
2016-02-11 05:48:20 -0600 asked a question CascadeClassifier::detectMultiScale alogical influence of minSize parameter

I work with OpenCV 2.4.9. When I downsize whole image with, lets say, k=0.6 koefficient (both width and height reduced proportionally), I do the same with parameter minSize=minSize(minSize_original_width x k, minSize_original_height x k), the same with maxSize.

I visualize detecting result. The detection rate of bigger objects stay the same in reduced image, but smaller objects are not detected anymore as they were in the original, larger image.

Is there any other, hidden constraint, which I don't know? I use pre-trained model.

2015-10-16 11:53:52 -0600 received badge  Teacher (source)
2015-07-22 03:52:33 -0600 received badge  Necromancer (source)
2015-07-21 09:39:30 -0600 answered a question Machine learning save/load problem

Just check up loading before using your svm classifier:

Blockquote

CvSVM *mySVM = new CvSVM;

mySVM->load("mySVM.xml");

int in= mySVM->get_support_vector_count();

if(in)

mySVM->predict(DataRow);

Blockquote

get_support_vector_count() retuns 0 if your resource isn't loaded.