Computer Vision

Tracking Objects in YouTube Videos
In this project enhancements were made to OpenTLD: https://github.com/zk00006/OpenTLD
to make it View Point Invariant and have Class Invariant.
I wrote a paper on this project as part of my class work, you can find it here:
Aparajith Sairam – CS 231 A Project Report

I am posting some videos which demonstrate the improvements.

View Point Invariance

Soccer Ball Tracking Original

Soccer Ball Tracking Enhanced

Class Invariance

Tracking Chair 1

Tracking Chair 2 with same input data

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s