I'm not sure if this is the right place for asking these kind of question but I have no better place in mind.
After LOTS of coding in OpenCV, I'm trying to migrate to new C++ interface of openCV which has been introduced in OpenCV 2.0. but I keep getting strange errors.
For example:
trying to use pre-built dlls and libs, I got exceptions in "cv::warpAffine" and "findContours" cv::function at runtime. I compiled the openCV, used my own build of libs and dlls and everything got fixed!
the same problem happened in linux.
linking the "Debug" built dlls with "Release" built of program cause some unexpected runtime errors, and vice versa.
and some other errors.
can anyone helping me with what I'm doing wrong? (please keep in mind that I coded alot with older version of openCV).
When I migrated to C++ interface I couldnt make openCV work until I compiled the source by myself. Probably DLL's and Libs that are installed with opencv are good only to a specific machine.
Another thing. Try to do the following if you use Visual Studio
go to Project Properties->Click the C/C++ folder->Code Generation->Runtime Library and change it to /MDd in Debug configuration and /MD in release
It solves a problem with esceptions related to STL
Some of the functions ave moved out to new libs (especially some of the stereo functions are in calib3d) and the header file structure is completely changed in 2.2
There are some guides to the configuration eg for visual studio
Related
Some weird stuff here. I'm trying to build a KMDF sample driver with VS2019 16.11.5 and WDK 10.0.19041.685 (also called version 2004 Dec 2020 update).
First, I got compilation error saying that I need to download Spectre-mitigated MSVC library.
Well, I try it, but got a new problem. The VS2019(16.11.5) installer does not show MSVC Spectre-mitigated MSVC library version for exact 16.11. Looks like the latest one it provides is 16.10 (🙁).
Download the 16.10 one and resume trying, still compilation error.
I peek into my D:\VSIDE\VS2019\VC\Tools\MSVC folder, and see two versions of MSVC libs listed, 14.29.30133 and 14.29.30037 . The later is the one with spectre libs(so it's 600MB+ larger).
However, the KMDF build tool insists to find MSVC libs in the newer 14.29.30133 folder, so Spectre-mitigated libs still CANNOT be found.
I know I can manually copy the required files from 14.29.30037 to 14.29.30133 to make things go on. BUT is it the decent way to do so, or is it a Microsoft toolset bug?
I'd like to ask how other kernel driver developers solve this issue. Thank you.
Well, several days later, I find out two workarounds for this issue.
First, as Hans Passant stated, disable the Spectre lib in .vcxproj. This can be configured from UI.
Second, explicitly select a MSVC library version for current project. This can also be configured in project settings UI.
==== 2022.02.11 UPDATE ====
Finally got it，the Spectre-lib with version number 14.29.30133 is called "(Latest)", so it is listed above the oldest version, and this defeats the novice. Use this and problem solved.
Sure, it is stupid enough to mark it as merely "(Lastest)". He should have named it MSVC v142 - VS2019 C++ x64/x86 Spectre-mitigated libs (v14.29-16.11)(Latest)" .
I'm doing a simple AR-Project for school and have to use opencv for it. I found it quite tricky to install in visual studio but now it's working fine. Now I want to use the aruco module, I tried this tutorial, but after building the bin folder is missing and the includes in my code don't work anymore... Is there a (preferably easy) way of adding the contrib modules into my (saved and functioning) opencv-folder?
EDIT: I successfully build opencv with modules (using cmake gui and vs14) and the includes for my old code are working fine, but when I try to use the aruco module I get these: Error Message
The files are all where they are supposed to be and I set all paths and additional dependencies as well as the include directory...
Any Idea what's wrong?
OK - I did it.
I disabled all other modules in cmake and now the includes for aruco work.
But I can't really explain myself why the other (unused) modules corrupt the aruco libraries?
I've been searching around the Lazarus IDE documentation for a bit, and thus far only found information related to cross compiling, so I was hoping someone could give me a straight answer on this. I'm currently working on a project that will require compilation for 32-bit Windows as well as 64-bit Windows. Additionally, I've already set up both versions of the Free Pascal Compiler. Does Lazarus have any built in functionality for configuring in both compilers, and then based on the build target, using the appropriate compiler? Ideally, this would be done at a global level, so that the configuration persists across projects, but if it can only be done at the project level, I don't mind doing it that way.
On further reading, I think I found my answer. I didn't realize it, but fpc has the same sort of front-end functionality as gcc. With that said, implementing the functionality described in my question is just a matter of installing the compiler as a cross compiler, rather than as an independent compiler. Since it doesn't look like you can use the x86_64 compiler to create a 32-bit version, you'll have to compile the 32-bit version, and then crosscompile the 64-bit version. In my case, I first compiled and installed the Win32 compiler using:
make all install INSTALL_PREFIX=C:\path\to\lazarus\1.0.8\fpc\2.6.3 OS_TARGET=win32 CPU_TARGET=i686 PP=ppc386.exe
Next, I compiled and crossinstalled the 64-bit compiler:
make crossall crossinstall INSTALL_PREFIX=C:\path\to\lazarus\1.0.8\fpc\2.6.3 OS_TARGET=win64 CPU_TARGET=x86_64
To confirm that it worked, you can find an executable called, ppcrossx64 in your C:\path\to\lazarus\1.0.8\fpc\2.6.3\bin\i386-win32 folder.
I am working on my final year project. I need to work with Kinect to detect hand movements. I have tried a few ways and got some results, however, none was enough to meet the needs of the project. I saw this video long ago, and just got to know that they open sourced it recently. So I gave it a try.
My problem now is how to set things up.
The above awesome project uses OpenNI with Kinect. I tried to follow OpenCV tutorials to build it from source code, to let OpenCV work with OpenNI.
Problems:
It says "For the OpenNI Framework you need to install both the development build and the PrimeSensor Module." but as I followed the links some of them were dead. Seems like OpenNI 2.0 doesn't use PrimeSensor any longer.
It also says that in Cmake folders, one is OpenCV/Src, the other is /build. But the OpenCV I downloaded doesn't have anything as Src folder.
Still I used the whole folder as Src, and built it to a build folder and checked WITH OPENNI. I used the Include and Lib folder in OpenNI2 I downloaded, but when I built the OpenCV solution (already generated from CMake) all builds failed.
Also, while generating with Cmake, even if my future OpenCV solution had been successfully built (which wasn't the case), Cmake would have kept telling me how PrimeSense was not available, which made me feel so insecure. :(
I am a bit confused about 32- and 64-bit. The above project I want to follow says it works on 64-bit. But I use MS C++ Express, all projects are 32-bit. So which PrimeSense drivers (given in OpenNI2) should I use?
Could anyone please tell me how to set all these things (OpenNI2.0, OpenCV 2.4.3, PrimeSense) together so I can work with Kinect?
A while back I wrote two tutorials on 1) how to set up OpenNI 1.5 with NITE 2) How to compile OpenCV with OpenNI support.
These can be found here and here
I know this is not what you asked for, but the process of compiling OpenCV with OpenNI 2.0 should be similar and might help you understand where you are going wrong.
I will try to write a newer tutorial, however since I currently do not have access to a sensor, I might not be able to test if it works out in the end.
EDIT:
I have written some code to access Kinect data streams in OpenCV Mat format using OpenNI 2.x. The code github repo can be found here. Detailed guidance on how to set everything up can be found here.
OpenNI 2.x is much advanced than the previous versions. You don't need to install primesense sensorkinect driver. You can use OpenNI 2.x along with the Microsoft Kinect SDK 1.x.
Install both 64 and 32-bit OpenNI 2.x if you have Windows 7 x64 otherwise only 32-bit. Configure it with Visual Studio 2010 or 12. You can follow this video:
http://www.youtube.com/watch?v=ACqPsV0R4to
Then configure OpenCV for visual Studio 2010 or 12. You can follow this link:
http://4someonehelp.blogspot.in/2013/04/install-opencv-245-using-visual-studio.html
Thanks
I have been having this issue with OpenCV 2.4.2 that it doesn't really get installed properly with Microsoft VS 2010 Express; It is always missing a dll file or two doesn't matter what I follow by Googling. Also, Visual Studio 2010 Express is only valid for a few days, so it is acceptable that VS will not behave well with OpenCV at that point. However, when I changed my IDE to CodeBlocks, it is even stranger because now I have missing dll files and also "Missing Entry Point" error because of a duplicate .dll file. I found this guide and followed what it told me to do:
http://conanhung.wordpress.com/2012/05/23/opencv-2-2c-codeblocks-and-mingw-got-it-working-on-windows/
But it still doesn't work!! What I am after is a complete and definitive solution to integrating OpenCV (preferrably 2.4.2 version) on a Windows 7 64-bit machine. I have been turning Stackoverflow inside out but no solution is working for me. The problems are
WHEN USING VISUAL STUDIO:
Missing dll file (e.g. libopencv_core242d.dll, etc.)
WHEN USING CODE BLOCKS:
First it complains that libstdc++-6.dll is missing. When I download it to my C:\MinGW\libexec\gcc\mingw32\4.7.0 folder, it stops complaining about this. But now it complains that there is any entry point problem and some other .dll file is missing!!!
If someone has managed to make it work by hook or crook, I will be more than happy to know what it is, IN DEPTH. I don't believe that such an important library can be so stupidly distributed so that developers have to struggle night and day to make this work.
FYI, I have tried even the OPenCV website and frankly their instructions are a bit useless. Also, all the necessary information e.g. adding PATH, adding includes and libraries, etc. Please someone point me to the right direction as it has been two days and I cannot get anywhere. It is literally stopping my job now :(
As an answer, but probably a very simple one, I did the following and got rid of the problem:
1) Uninstalled code::blocks completely from the PC and downloaded the IDE-only version (i.e. withouth MinGW compiler), then installed it.
2) Downloaded the latest stable version of MinGW, installed, and added C:\MinGW\bin to PATH
3) Followed rest of the instructions from [link] http://conanhung.wordpress.com/2012/05/23/opencv-2-2c-codeblocks-and-mingw-got-it-working-on-windows/
4) Just to be sure, copied the opencv .dll files from the build folder (i.e. the one that you have created "make" and "install" files using CMake) to the debug (i.e. the executables') folder.
This will fix the problems. In case, it doesn't it might be that you need to add some environment variables.