“Very nifty.”
Demo of a self-improving object tracker.
Full comment
My friend forwarded me the video demo link for this: this video Very nifty. I'm looking forward to reading the machine learning code involved in this.

893K views · Jan 1, 2011 · 4:12 · 1 HN recommender · 3 mentions · discussed 2011–2023
A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks. The technology was later developed commercially.
Why Hacker News points people here: HN found it a nifty demo and cites it as a primitive but effective learning tracker that predates modern deep-learning trackers.
“Very nifty.”HN comment, 2011
“Very nifty.”
Demo of a self-improving object tracker.
My friend forwarded me the video demo link for this: this video Very nifty. I'm looking forward to reading the machine learning code involved in this.
Example that object tracking has existed for a decade.
Incorrect. Recognition applications have been able to track objects across disparate frames of video even when obscures from camera view, for at least a decade now [1]. 1. this video
“This time with some very primitive ML: OpenTLD”
Earlier primitive ML tracker, good enough for commercialization.
OK, 11 years ago then. This time with some very primitive ML: OpenTLD this video Was good enough for commercialization link . I think their tech is powering this link