Schawn's profile - activity

I am trying to set up MS Visual Studio 2012 (64 bit machine) with OpenCV 2.4.10. I have ready many tutorials on how to set up Visual Studio with OpenCV, but I seem to keep getting this error. Most of my searches for this error and how to fix have come up empty. In fact most of the errors I see people having is with "cannot open file 'opencv_XXX2410d.lib' but not with .obj

I have double check all of the following:

• I have an OPENCV_BUILD environment variable set to C:\opencv2410\build
• I have my PATH set to include %OPENCV_BUILD%\x64\vc11\bin\
• I have a OPENCV_DEBUG and OPENCV_RELEASE properties sheet for my Solution with the following settings: - VC++ Directories: Executable Directories set to c:\opencv2410\build\x64\vc11\bin - VC++ Directories: Library Directories set to c:\opencv2410\build\x64\vc11\lib - C/C++: Additional Include Directories set to c:\opencv2410\build\include - Linker/General : Additional Library Directories set to : c:\opencv2410\build\x64\vc11\lib - Linker/Input: Additional Dependencies, has all of the opencv_XXX2410d listed (OPENCV_RELEASE properites does not have the *d on the filenames)

Does anyone know why I am still getting this error? And why is it looking for the .obj vs. the .lib. I assumed the .lib has all of the .obj files in them. Any ideas on how to fix this would be awesome.

I am seeing a similar notification. What puzzles me is that most of the discussions online that I have found most people are seeing this very early in the training process (like at the beginning - Stage 0). I have had 2 runs where one terminated at Stage 14 and another at Stage 15. All of the online discussion of this termination states that it has to do with some error in either the -bg parameter or the actual negatives.txt file itself. But in my case, since it got to a later stage, I have to assume it is something else. Right now I am trying to decipher the code base to determine what is causing this to happen for me. I will post something if I can figure it out.

Thanks I will take a look at these links. According to the documentation, during opencv_createsamples a -h and -w parameter is used. The documentation also states that these -h and -w value should be used in the training (opencv_traincascade). Couple of follow up questions:

1. Does it matter what the starting size of your positive images happens to be, prior to running the opencv_createsamples? For example, see the original post, my default pixel size of my positive image was 2592X1458. Should I resize this to something smaller before I run the opencv_createsamples

2. Can i assume that this is telling the opencv_createsamples to create positive samples with this -h and -w value?

3. Is there a preferred value that works best or does this depend on what you are trying to detect?

Recently I have been experimenting with trying to train my own cascade classifiers to use in building my own detector. I am using OpenCV 2.4.10. I have seen many different tutorials to help with this processes (always looking for more though). I have not been successful to this date. I have gotten through the training process in some cases, but the detector does not detect the image in the scene.

I ran into a couple of questions when preparing my samples that I would like to ask:

1. For positive and negative images do the sizes (pixels width and height) matter? When I take samples pics with my tablet I am getting sizes like: 2592 pixels (width) by 1458 pixels (height). I have been resizing these large pics (pixel wise) down to smaller sizes like 48x26. Does the size of the pictures matter?

2. For creating positive samples, I have experimented with cropping out an image from a scene that I am interested in, where the scene has a lot in it and I have experimented with where the image I am interested in takes up the entire picture frame. With the first case I do provide the coordinates of the image I have cropped. Does it matter how these samples get created, would either way work? Will one work better than the other.

3. Do the negative samples and positive samples image size need to be the same or similar. For example can my positive samples be small (48x26) but my negative images large (2592x1458). Or should both sets be similar in size

I would appreciate any suggestions, best practices or guidance to help me get through this process and build a successful classifier.

Thank you

I just ran into the same problem with the same error (mine after stage 9). My pos images are -w 48 -h 36, my negative images are -w 640 -h 480. I have 1000 negative images and using 38 positive images. My negative images do not have the positive image that I am looking for in them.

I am using OpenCV 2.4.10 and this is the command i was running:

opencv_traincascade -data classifier -vec samples.vec -b negatives.txt -numPos 38 -numNeg 1000 -numStages 20 -w 48 -h 36 -featureType LBP

Really stuck here, cannot figure out why it failed. If more information is needed please let me know.

That is what I thought, but that folder is empty. I created a whole new directory structure to do the second run and made sure it was empty. Not sure what would cause this.

Do you know of a newer or up-to-date tutorial that I could be using? I am using OpenCV 2.4.9

I am using OpenCV 2.4.9 to try and build my own classifier. I am following the instructions on this site: http://coding-robin.de/2013/07/22/tra...

I was successful in creating a classifier XML file. I went to try an build a new different classifier and ran into the following error:

Training parameters are loaded from the parameter file in data folder! Please empty the data folder if you want to use your own set of parameters

I could not find any parameter file anywhere to empty. When I ran the second time I created a whole new directory structure from the first successful run.

Any help or understanding of how to fix this error?