Tracking object paths across sparse array
in [Matlab]
|
Prev: Aligning Point Clouds
Next: AM
From: Matt J on 29 Jun 2010 13:44 "Dan " <remove.this.gouldani111(a)gmail.com> wrote in message <i0db1s$830$1(a)fred.mathworks.com>... > The array I am trying to seperate the individual plane paths from is a sparse matrix with a number other than zero whereever a plane has been, the x and y axis being the x and y coordinates. So if two planes ever passed over the same spot, it registers only once. =============== That's what you are *trying* to do, but as ImageAnalyst pointed out, you are losing information unnecessarily by combining the frames into one. The correct approach is to process the 500 frames separately, rather than after they are combined.
From: Dan on 29 Jun 2010 14:00 ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <cde9ef78-1e7d-47d7-b73c-053923d14b9c(a)s9g2000yqd.googlegroups.com>... > On Jun 29, 12:08 pm, "Matt J " <mattjacREM...(a)THISieee.spam> wrote: > > Come to think of it, you might not need a mathematical model as long as the planes never cross paths at the same (if they do, it would hopefully be at different altitudes, cf. us). > > > > In that case, simply track the positions from frame to frame. I.e., in each of your 500 frames, find the (x,y) positions of the planes using find(). > > > > Then, for each (x,y) position, find the closest one in the subsequent frame using bsxfun(). That will allow you to match planes between adjacent frames. > > --------------------------------------------------------------------------------------------------------- > Dan: > I agree with Matt J. The only way to remove ambiguity (almost > completely) is to track each plane one at a time as it progresses > through the frames. It would help if you could post pictures. I'm > envisioning each frame being black with 10 white dots, each dot > representing a plane. So just find the centroids of the dots, and in > the next frame, see which centroids and trajectories makes sense when > compared to the dots of the prior frames. The only possible ambiguity > would come if, as Steven said, you have complete overlap for a certain > trajectory (so there are only 9 dots in some pictures instead of 10). > But you do need to keep track of the trajectory angle because just > tracking centroids may not be enough if two of the dots get very close > to each other (not even overlapping, just close). > -ImageAnalyst Yes, I have 500 black frames with 10 white dots each. I had not thought of a way to track them frame by frame. How would I find the trajectory angle?
From: Matt J on 29 Jun 2010 14:22 ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <cde9ef78-1e7d-47d7-b73c-053923d14b9c(a)s9g2000yqd.googlegroups.com>... > But you do need to keep track of the trajectory angle because just > tracking centroids may not be enough if two of the dots get very close > to each other (not even overlapping, just close). ========== I don't mean to harp on this excessively, but how close can 2 planes get to each other during flight? Surely, the minimum separation distance ought to be much greater than the dot representing the plane. Of course, I have flown on planes where you could see another plane flying along roughly the same path at a lower altitidue, but again with a significant separation distance. If that's an applicable scenario here, do we have no altitude information to play with? If so, then again, this could all be done using bwconncomp.
From: Dan on 29 Jun 2010 14:46 "Matt J " <mattjacREMOVE(a)THISieee.spam> wrote in message <i0ddke$q5j$1(a)fred.mathworks.com>... > ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <cde9ef78-1e7d-47d7-b73c-053923d14b9c(a)s9g2000yqd.googlegroups.com>... > > > But you do need to keep track of the trajectory angle because just > > tracking centroids may not be enough if two of the dots get very close > > to each other (not even overlapping, just close). > ========== > > I don't mean to harp on this excessively, but how close can 2 planes get to each other during flight? Surely, the minimum separation distance ought to be much greater than the dot representing the plane. > > Of course, I have flown on planes where you could see another plane flying along roughly the same path at a lower altitidue, but again with a significant separation distance. > > If that's an applicable scenario here, do we have no altitude information to play with? If so, then again, this could all be done using bwconncomp. Unfortunately, I do not have any altitude information, and the planes to overlap
From: Matt J on 29 Jun 2010 15:07
"Dan " <remove.this.gouldani111(a)gmail.com> wrote in message <i0df1i$20$1(a)fred.mathworks.com>... > > Unfortunately, I do not have any altitude information, and the planes to overlap ================== You mean the paths can overlap both spatially (x,y) and temporarily, and differ by unknown altitudes only? In that case, I don't think trajectory angle can help you. Potentially 2 flight paths can merge, overlap continuously for 1000s of miles, then separate. In that scenario, you could never distinguish the 2 given the limits in information you've described. |