OpenTLD is an open source library for real-time 2D tracking of a single object in video. This repository is no longer under development. For latest version see: http://www.tldvision.com/tld2.html
GNU General Public License v3.0
2.09k
stars
1.27k
forks
source link
How to modify OpenTLD to support object recognition? #27
From what I have gathered, OpenTLD is a tracker and detector, it tracks what you tell it to and detects the object frame by frame. I feel that this can be applied to the broader scope of object recognition, where the software learns many object and can name the objects it sees in a frame. I'm aware of openTLD's one object tracking limitations, but there shouldn't be a limitation to find all the recognizable objects correct? It should be able to go through the database of saved objects and look for those objects in a frame.
Any thoughts on this? Can this be done easily? Better yet, has anyone made modifications for this already?
From what I have gathered, OpenTLD is a tracker and detector, it tracks what you tell it to and detects the object frame by frame. I feel that this can be applied to the broader scope of object recognition, where the software learns many object and can name the objects it sees in a frame. I'm aware of openTLD's one object tracking limitations, but there shouldn't be a limitation to find all the recognizable objects correct? It should be able to go through the database of saved objects and look for those objects in a frame.
Any thoughts on this? Can this be done easily? Better yet, has anyone made modifications for this already?
thanks