I’m off to RSS 2009 in Seattle next week to present a new paper on FAB-MAP, our appearance-based navigation system. For the last year I’ve been hard at work on pushing the scale of the system. Our initial approach from 2007 could handle trajectories about 1km long. This year, we’re presenting a new system that we demonstrate doing real-time place recognition over a 1,000km trajectory. In terms of accuracy, the 1,000km result seems to be on the edge of what we can do, however at around the 100km scale performance is really rather good. Some video results below.
One of the hardest things to get right was simply gathering the 1,000km dataset. The physical world is unforgiving! Everything breaks. I’ll have a few posts about the trials of building the data collection system over the next few days.
As you gathered so much data & that too was not an easy task so i appreciate you for the following since you have proved a very great work for the others!I appreciate you for that!
WOW! From 1 km to 1000 km in just 2 years!!! good job
I ve read few things about navigation related systems.its nice to hear that you are able to do it on 1000km trajectory.as well you are also maintaining the database over that much range good great job…
I hope you get through the next step in an quick manner.