nonlin's profile - activity

OpenCV MatchTemplate maxvalues[0] large discrepancy issue. This is in C# with EmguCV. I have contacted their forum for s

OpenCV MatchTemplate maxvalues[0] large discrepancy issue. This is in C# with EmguCV. I have contacted their forum for s

OpenCV MatchTemplate maxvalues[0] large discrepancy issue. This is in C# with EmguCV. I have contacted their forum for s

This is how my tracking looks.

http://puu.sh/rTCI1/a4eb9fcd3e.png

I followed a python guide for tacking cars this one here https://pythonspot.com/en/car-trackin...

My converted C# code looks like this.

http://hastebin.com/obavepipuq.cs

I'm really not sure which part is off or which part would cause that.

I understand that this error occurs whenever your ROI is out of bounds from the image (correct?).

However, my ROI is within bounds, at least as far as I understand. When checking the values my

x = 1062, y = 856 and w = 2560 and h = 1440 (my image height and width).

If I set x = 0 and y = 0 it works.

1062 and 856 are well within the range of 1440 let alone 2560. What am I missing here?

http://puu.sh/phYbG/83fd4dc617.png http://puu.sh/phYh0/e3eb50c609.png

Edit main post to show some code.

with min_neighbours to 2 and output reject levels to true the detectMultiScale doesn't seem to return any faces. Left it running for 20 min and it never finished.

However, if I change min_neighbours to 0 then it will return a crazy amount of faces, I let it run till 150000 but I stopped it at that point.

I read only that a bug was found relating to this? Not sure if it got fixed or if I'm doing something wrong? I have the latest opencv source compiled 3.1.

On a slightly separate note, the reason for me wanting to use the override is so that I can try and find the best image out of multiple images.

Extra Details:

Windows 10 x64

Opencv 3.1 x64 dlls.

Preview of the code.

const double scale_factor = 1.1;
const int min_neighbours = 2;
const int flags = CV_HAAR_FIND_BIGGEST_OBJECT | CV_HAAR_DO_CANNY_PRUNING | CV_HAAR_SCALE_IMAGE;
const Size min_size = Size(48, 48);
const Size max_size = Size();
std::vector<int> rejectLevels;
std::vector<double> levelWeights;
bool outputRejectLevels = true;
cv::Mat crop;
cv::Mat res;
cv::Mat largestFile;
if (cascade.empty() || image.empty()) {
    return Rect();
}

std::vector<Rect> faces;
    //old working code, now commented out
//cascade.detectMultiScale(image, faces, scale_factor, min_neighbours, flags, min_size, max_size);
//current attempt at getting weights and reject levels. 
    cascade.detectMultiScale(image, faces, rejectLevels, levelWeights, scale_factor, min_neighbours, flags, min_size, max_size, outputRejectLevels);

I followed the readme here https://github.com/Itseez/opencv_cont...

but i'm stuck on the last step. "build the opencv core with the method you chose (make and make install if you chose Unix makfile at step 6)"

I'm not sure where the files are needed or how to use them. I already have opencv setup as per the regular download. I've already used cmake GUI to get the source files out of that.

I've built everything as far as I'm aware. I've built build all, install, opencv and various others projects but I'm not sure what it is i'm looking for? I can't find any include folder for what I need. Also it all seems to be in 32 bit but I'm using 64bit opencv, will this cause conflict?

Readme seems a bit vague any help so I can include face.hpp in my project so I can continue the facial recognition tutorial.

EDIT: BTW Just followed this tutorial https://putuyuwono.wordpress.com/2015...

Far more clarity but still no install folder inside builds. http://puu.sh/p6AGp/0430aea73c.png http://puu.sh/p6AJa/063826dc8c.png