Skip to content

A C++ Qt GUI desktop program to calculate Harris, FAST, SIFT and SURF image features with OpenCV

License

Notifications You must be signed in to change notification settings

kayspark/ImageFeatureDetector

 
 

Repository files navigation

Image Feature Detector for Neuromorphic hardware

Compiling the project

To configure the project building and binary linking IFD makes use of CMake. This program is tested on Windows 10, Ubuntu 18.04 /18.10 and MacOS 10.13 to 10.14.3

Resolving dependencies

  • Installing nm500 SDK : NM500 is AI hardware which is based on neuromorphic technology. It can be used in many ways with many feature extracting algorithms. For installation, please refer readme at lib foler.

  • Installing Qt: on Linux and Debian-based distributions you don't need to compile Qt. The easiest and fastest way to install Qt is with apt-get (details on the link). on Mac homebrew will make install as breeze. on Windows, vcpkg seems the most easier way.

  • Installing OpenCV: On Mac and Windows, homebrew and vcpkg will be the best way to use OpenCV. On Linux, to some OpenCV copyrighted code, the modules containing SIFT and SURF detectors aren't available on Debian repositories like the rest of OpenCV modules. This means you will have to compile OpenCV libraries by yourself. By and large you will need to download the main OpenCV modules plus the OpenCV contrib ones (the code containing SIFT and SURF detectors), and when you are about to compile the main OpenCV modules set the OPENCV_EXTRA_MODULES_PATH CMake variable to <opencv_contrib>/modules. Better explained here.

  • Installing VLC : For rtsp stream, it requires libvlc. For linux, 3 packages will require. $ sudo apt install libvlc-dev libvlccore-dev vlc

For windows, just download and install latest vlc which contains SDK. It is packaged as 7zip file and SDK folders are included. Other zip, exe packages do not contains SDK folder. For Mac, there is no binary package yet. however, you can compile with instructions from https://wiki.videolan.org/OSXCompile/

Compilation

On Unix machines, once you have these two dependencies solved, from the command shell just run: $ cd $ mkdir build $ cd build $ cmake .. $ make

On windows, For Qt and OpenCV, vcpkg (https://github.com/Microsoft/vcpkg) is the most convenient way.

$ cd $ mkdir msbuild $ cd msbuild $ cmake .. -G"Visual Studio 15 2017 Win64" "-DCMAKE_TOOLCHAIN_FILE=C:/vcpkg/scripts/buildsystems/vcpkg.cmake" $ cmake --build . --config release

For any enquiries, contact wfms123 a t g m a i l

About

A C++ Qt GUI desktop program to calculate Harris, FAST, SIFT and SURF image features with OpenCV

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 89.8%
  • Python 5.3%
  • CMake 3.8%
  • Other 1.1%