Popular tutorials of using openCV to detect objects and showing recognised results are based on a black window with rapid command lines flushing up. As MFC has more powerful functions in interface design than pure interfaces provided by openCV, it is attractive to move openCV application from console to MFC. Here is an tutorial of introducing using openCV in MFC, check it out.
Using the function cvsnakeimage(), this was an idea i tried to recognise hand gestures. The thought was that as to set a threshold to filter the image firstly, based on the image then contours were able to be extracted (as blue curves shown in the picture on the left), then passing contours points to ‘cvsnakeimage’ function to calculate the green curves which were snake curves.
The hand detection and image descriptor is a tool developed for direct interaction with a device called PR2 which is a robot by a student in Stanford University. It enables hand gestures to control the movement of the robot, as the video below shows (if can see the video, please refer here Hand detection) Meanwhile, a library descriptors_2d is also presented. And, resources of learning more about the hand detection techniques and image descriptors are provided here (2d_decriptors.PDF) as well. Read More
A method of tracking hand manipulating objects is presented by Hamer et al. (2009), as shown in the picture above it seems quite robust for tracking.
To create your own OpenCV-based project in Visual Studio do the following:
Linking DLLs:
To permanantly include necessary dll files, add “C:\Program Files\OpenCV\bin” to PATH by visiting Advanced tab in System of Windows (the locate of directory might be different).
One can just copy necessary dll files into project directory with source files.
It might be required to restart Visual C++ when execution of instance failes after successful build.