QuickTopic free message boards logo
Skip to Messages

TOPIC:

Tracking objects across cameras

14
hanyujoys
09-24-2009
11:10 PM ET (US)
Support of the Lou Zhu, Lou Zhu worked hard
Signature---------------------------------------------------------------- ---------------------------------------------------
Nothing is impossible for a willing heart.
ugg classic cardy
13
Deleted by topic administrator 09-25-2009 02:14 AM
12
Matt
10-26-2006
05:07 PM ET (US)
Somewhat related to my previous question: how does this method actually stack up with calibrated/supervised/overlapping-view methods? The amount of ad-hoc setup this method allows is certainly nice, but how much are we giving up?
11
Tom
10-26-2006
04:25 PM ET (US)
Yet another application that gets by with a crappy (color histogram) object recognition system that could probably benefit from having layers of classifiers with histograms on top. I'm pretty curious why they found that RGB was the nicest color space for their histograms. That surprises me somewhat, is there some nice intuition as to why that would be the case? (sensor sensitivity maybe?)

In response to the big brother: most survailence cams to the best of my knowledge are still black and white so we might be safe for another couple of years.
Edited 10-26-2006 04:26 PM
10
Iman
10-26-2006
04:22 PM ET (US)
I wonder if their system would work better if instead of using ordinary surveillance cameras, they used one of the new "dual sensor" cameras that combines visible imaging and thermal imaging into the same unit. Then they could not only track objects using color information, but would have a temperature signature too. I think this could improve their system's tracking ability for tracking objects that emit heat (like people). Plus it would work at night. I don't know how well thermal imaging works outdoors or in a brightly lit office environment though. Anybody know anything about this?
9
Carolina GalleguillosPerson was signed in when posted
10-26-2006
04:07 PM ET (US)
to Paul: There exist CSIFT:A SIFT Descriptor with Color Invariant Characteristics - For some reason is not that popular..maybe because adding color made the computation a lot heavier and the robustness gained is not that much compared with the traditional SIFT.

About the paper: I wonder how this would change if the backgrounds the corridors have constant traffic of people and maybe a bit more cluttered background?. Color histograms and CCCM seems to look pretty well using the links on this uniform corridors.
Edited 10-26-2006 04:15 PM
8
Paul
10-26-2006
03:52 PM ET (US)
It seems like they got a lot of mileage out of using a very simple appearance model for objects (color histograms). One of the reasons they use these histograms is that they are invariant to position. I wonder if a SIFT like feature might provide more discriminative power between objects and also some degree of pose independence. On the otherhand given the problem setting such a feature might be overkill.
7
Marius
10-26-2006
03:26 PM ET (US)
It is interesting that this type of paper comes out from the UK. London probably has more surveillance cameras per capita than any other big city. They monitor the underground, streets, and tax cars automatically entering the city centre.

Big brother is watching...
6
Matt
10-26-2006
03:20 PM ET (US)
Can someone explain how they defined 'accuracy'? A jump from 55% to 81% is certainly large, but I'm not really sure what they're measuring or if 81% is even close to being useful.
5
Adam
10-26-2006
02:50 PM ET (US)
re Anton: The Results section describes that their iterations are defined by # of objects tracked. I think their iterations denote when they split the blocks, but they do the recombination and link pruning throughout...because each iteration takes hours.
I'm curious how they organized their data structures - there's a lot of complexity in their technique and it needs to be running real-time.
4
Nadav
10-26-2006
01:38 PM ET (US)
very cool that the system learns as the amount of data increases.
3
Deborah
10-26-2006
01:24 PM ET (US)
What happens when there is more than one person in the scene. Will each individual be tracked separately? Thank you!
2
Anton
10-26-2006
01:12 PM ET (US)
Could you go over recombination? In Section 5 they state that "eventually, adjacent neighboring blocks can be recombined to form larger blocks if found to have similar distributions" How often does recombination take place? Figure 3 shows it after the 4th iteration, which makes me believe it isn't a part of each iteration, but I'm not sure if that's just an example. Also, how are the iterations defined?
1
Boris
10-26-2006
01:44 AM ET (US)
Could you give a quick crash course on Kalman filters?

Thanks!

Print | RSS Views: 2605 (Unique: 1204 ) / Subscribers: 0 | What's this?