Tag Archives: openCV

Status Update: Calibrating for Depth

Currently I am experimenting with stereo vision usb webcams, where an essential step is good calibration. It felt a bit strange to see the image feature detection working on live data:

Screenshot - 09.11.2014

I’ll try to form the gained experiences into a small step by step guide and probably a github repository soon. Currently I am aiming towards depth data gained by webcams only, especially to compare the results to previous setups, and to see if visual odometry can be an option in low cost environments.

Howto: OpenCV 2.4.9 on Raspberry Pi from source

OpenCV is a powerful tool for building computer vision based applications. For one of my projects, I needed it to be compiled on my Raspberry.

Installing it from repositories was not an option because of its too old version.
If this wouldn’t bother you, consider using: sudo apt-get install libopencv-dev

Here is how I installed it on my Rasbian Wheezy from source:

prerequisites:

after that:

downloading the zipfile into a folder located in $HOME

Make took about 6-7 hours on my Raspberry Pi, so be sure you have a stable connection or consider using a tool like ‘screen’.

Please also see:

For  openni2_camera it’s not necessary to go further like other posts suggested.