Following article - https://medium.com/towards-data-science/building-a-real-time-object-recognition-app-with-tensorflow-and-opencv-b7a2b4ebdc32

His corresponding Github account - https://github.com/datitran/object_detector_app

corresponding google research blog - https://research.googleblog.com/2017/06/supercharge-your-computer-vision-models.html

Need to have opencv 3 or above for it to work. Hence first installing opencv from here - https://www.learnopencv.com/install-opencv3-on-ubuntu/

Faced one issue while build of opencv2 ,

error - fatal error: QtOpenGL: No such file or directory

resolution here - https://stackoverflow.com/questions/31538560/qtopengl-no-such-file-or-directory-opencv-python

( 2nd answer worked for me ) - sudo apt-get install libqt5opengl5 libqt5opengl5-dev

Once the installation was done, i was able to run code as below,

python object_detection_app.py

the app was able to detect person,phone that i checked against.

Now, lets get into coding, <TODO>