kpcamota's profile - activity

yes, the images are on the right path. Sometimes it runs in few seconds but afterwards this error appears. And sometimes I cannot run the program and this error quickly appers.

I am trying to make the freak_demo.cpp from samples to be in real time.

But I am having this error: https://www.dropbox.com/s/x61oc9xy2wtzmqh/freak.png

@steven I have Intel Mobile HD Graphics 3000 which is shown here: http://www.intel.com/support/graphics/sb/CS-033757.htm

and GPU support are for nVidia graphics card right? so not possible for me. I want to make sure my laptop is support by gpu or opencl before I rebuild opencv w/ gpu and opencl

i tested surf for feature extraction and flann to match descriptors to a certain image. I was able to do it in real time having 3 different source image to compare. It was working but the performance was very slow on 640x480, decreasing the resolution by 320x240 increases the performance but unfortunately I need to work on 640x480 because of Kinect Sensor. I have a good pc specs: intel core i7, 6gb ram but still the performance slow.

i had been reading about multi-threading. But OpenCV's GPU and OpenCL does not support my Intel HD graphics 3000. So how could I do multi-threading to improve surf performance. Note: I am using Kinect Sensor as my camera, VC++, OpenCV 2.4.5

I try to make a CLR console app and I just want to display an image. I got a grey window and it freezes.

it works. I added the opencv_photo245d.lib :D

I think linker settings was correct since I already used opencv functions like resize etc... so which file does the inpaint method belongs?

Hello, I am trying to filter my depth data captured from kinect. Look at the image below. unknown values are colored with black:

Now I want to use the cv::inpaint function but still I have no luck. I followed this article: but I am using different kinect drivers. I am using Kinect SDK.

here are my code:

int drawDepth(HANDLE h, IplImage* depth)
{
const NUI_IMAGE_FRAME * pImageFrame = NULL;
HRESULT hr = NuiImageStreamGetNextFrame( h, 0, &pImageFrame );

Mat depthMat(Size(640,480), CV_16UC1);
Mat depthf(Size(640,480), CV_8UC1);


if( FAILED(hr))
{
cout<<"Get Image Frame Failed"<<endl;
return -1;
}

INuiFrameTexture * pTexture = pImageFrame->pFrameTexture;
NUI_LOCKED_RECT LockedRect;
pTexture->LockRect( 0, &LockedRect, NULL, 0 );

if( LockedRect.Pitch != 0 )
{
BYTE *pBuffer = (BYTE*)LockedRect.pBits;
cvSetData(depth, pBuffer, LockedRect.Pitch);
//cvShowImage("Depth Image", depth); // show normal depth maps

depthMat = depth;
depthMat.convertTo(depthf, CV_8UC1, 255.0/2048.0);

Mat _tmp, _tmp1;
Mat (depthMat-400.0).convertTo(_tmp1, CV_64FC1);

Point minLoc; double minval,maxval;
minMaxLoc(_tmp1, &minval, &maxval, NULL,NULL);
_tmp1.convertTo(depthf, CV_8UC1, 255.0/maxval);

//use a smaller version of the image
Mat small_depthf; 
resize(depthf, small_depthf, Size(), 0.2, 0.2);

//inpaint only the "unknown" pixels
cv::inpaint(small_depthf,( small_depthf == 255), _tmp1, 5.0, INPAINT_TELEA);

resize(_tmp1, _tmp, depthf.size());
_tmp.copyTo(depthf, (depthf==255));

cv::imshow("test", depthf); // show inpainted depth maps
}
NuiImageStreamReleaseFrame(h, pImageFrame);
return 0;
}

THANK YOU SO MUCH! It works. :)

this for the display purposes only. I just want the 8x4pixels to be shown on a bigger window. So there is no other way I can achieve this?

I managed to scaled down a 640x480 pixels to 8x4 using the cv::Resize function, but as expected it will display a 8x4 window size right?

Now, I resized the window to a bigger size, but the image is still at 8x4pixels. I want it to fit on the bigger size.

Check my code below.

How can I process a depth data from the kinect using Emgu CV and display it in another image box.

I am trying to scale the 640x480 pixels depth data down to an 8x4 pixels using the Emgu CV Resize Method.

.Resize(8, 4, Emgu.CV.CvEnum.INTER.CV_INTER_LINEAR);

See the image below.

Note: I am new to Kinect Programming and EmguCV

On the code below. image1.Source displays the 640x480 depth stream on the image box. Now I want to display another depth stream with 8x4 pixels in another image box.

What should I do?

does the resize function will produce the same result as the Image 2?

How to scale an 640x480 pixels down to 8x4 pixels?

The same as what they did in here:

Image 1 is 640x480 pixels and then they scaled it down to 8x4 pixels.

Note: I am new to OpenCV.

does OpenCV has a function capable of doing this? I'd been reading about the Geometric Image Transformations in OpenCV.