2019-06-08 16:04:37 -0600 | received badge | ● Notable Question (source) |
2018-10-17 07:24:29 -0600 | received badge | ● Popular Question (source) |
2017-03-28 01:28:59 -0600 | asked a question | TrainCascade: Choise of parameters and positive image Hello, I want to detect an pen and I used juliu5.com/full.jpg as the positive image. To generate a few hundred positives I used these github.com/handaga/tutorial-haartraining/tree/master/data/negatives and this command. For the -w and -h parameters I divided the with and height of my original positive image. Now I have 1000 positives and 2000 negatives so I am ready to train the classifier. (Linux Server) However in each Stage there are 3 lines (trained features?) max and my tracking results are really bad... I am still confused by the -w and -h parameters although I read several explanations within the forum. Are my parameters alright? When I was using -featureType HOG I got about 8 lines of features in each Stage. However this Type is not supported in OpenCV > 3.0. Is my test object just not detailed enough? Thank you really much for your help! |
2017-03-14 02:09:50 -0600 | received badge | ● Enthusiast |
2017-03-09 06:13:19 -0600 | commented question | findContours: Assertion failed Just to make sure: Additional Library Directories: build/lib/Debug (directory contains several libs) and Additional Dependencies: *d.lib files that are present in build/lib/Debug? Alright, I forgot to use INSTALL for Debug in the VS Solution... Thank you! |
2017-03-09 05:48:26 -0600 | commented question | findContours: Assertion failed Thank you for your input. So for debug purposes I should use the libs ending with "d", right? However in this path: "build\install\x64\vc15\lib" there aren't those files. I guess I should use the files from build\lib\Debug and build\lib\Release? |
2017-03-09 04:34:18 -0600 | asked a question | findContours: Assertion failed Hi, I am using the latest OpenCV 3 Version with Visual Studio 2017. x64, Compiled using CMake and opencv_contrib. My program crashes when I call findContours. I saw that some people have problemes with this function, but I wasn't able to fix my problem with theire solutions... Hopefully I did something wrong with my Includes etc... C/C++ -> General-> Additional Include Directories: build\install\include Linker -> General -> Additional Library Directories: build\install\x64\vc15\lib Linker -> Input -> Additional Dependencies: everything from the directorie above Exception: include\xmemory0 template<class _alloc,="" class="" _ptr="typename" _wrap_alloc<_alloc="">::pointer> inline void _Destroy_range1(_Ptr _First, _Ptr _Last, _Wrap_alloc<_Alloc>& _Al, false_type) { // destroy [_First, _Last), no special optimization for (; _First != _Last; ++_First) _Al.destroy(_Unfancy(_First)); //Exception thrown: read access violation. } Call Stack opencv_core320.dll!std::_Destroy_range1<std::allocator<std::vector<unsigned char,std::allocator<unsigned="" char=""> > >,std::vector<unsigned char,std::allocator<unsigned="" char=""> > * __ptr64>(std::vector<unsigned char,std::allocator<unsigned="" char=""> > * _First, std::vector<unsigned char,std::allocator<unsigned="" char=""> > * _Last, std::_Wrap_alloc<std::allocator<std::vector<unsigned char,std::allocator<unsigned="" char=""> > > > & _Al, std::integral_constant<bool,0> __formal) Line 1201 C++ Thank you really much for your help! Greetings! |
2017-03-06 08:01:27 -0600 | commented question | g_object_set: assertion 'G_IS_OBJECT (object)' failed You are right, I am using gstreamer. I installed some additional plugins and now I get an other error: Webm Format is working fine...The error message is still cryptic to me :/ |
2017-03-06 07:39:48 -0600 | asked a question | g_object_set: assertion 'G_IS_OBJECT (object)' failed Hello, I am using OpenCV (2.4.11) on Windows (Cygwin). I want to open a video file but I get this error message:
Editing images works great, so my installation in general should be fine. Maybe I am missing a Codec? My code looks like this: I already searched for a solution, but I didn't found any useful ideas... Thank you for your help! |