OpenCV-py-TrackerPerformance

Student Project for using Python Tracker with performance metrics projected alongside the target tracker

Dependencies:

OpenCV : Instruction for installation for the Fedora can be found on docs.opencv.org/trunk/dd/dd5/tutorial_py_setup_in_fedora.html Language: Python 3.5

For Fedora, it is much easier to install OpenCV using the dnf package manager than going out and compiling from source. It is more likely than not that there'll be a missing package.

Necessary Packages available via DNF:

opencv.x86_64

pygtk2-devel

python2-numpy

python3-numpy

webkitgtk

gtk2

glibc

python2-dlib

python3-dlib

dlib

Necessary Packages available PIP:

sudo pip2 install imutils

sudo pip3 install imutils

Optional Packages available via DNF:

cmake build-essential pkg-config libgtk2.0-dev libtbb-dev python-dev python-numpy python-scipy libjasper-dev libjpeg-dev libpng-dev libtiff-dev libavcodec-dev libavutil-dev libavformat-dev libswscale-dev libdc1394-22-dev libv4l-dev

Project Objectives:

Get OpenCV working for facial recognition in video - done

Get OpenCV working for facial recognition in streaming video - done

Performance Tracking for facial recognition in video - not done

Pefrormance Tracking for facial recognition in streaming video - not done

Future Objectives:

Upgrade to Fedora 26 to get Facial Landmarks script working for Python3

License

This project is done under the MIT License.