Re: Video motion tracking and speed estimation
- From: "Anthony Fremont" <nobody@xxxxxxxxxxx>
- Date: Sun, 15 Mar 2009 14:10:56 -0500
Jan Panteltje wrote:
On a sunny day (Sun, 15 Mar 2009 13:31:41 -0500) it happened "Anthony
Fremont" <nobody@xxxxxxxxxxx> wrote in
<KKSdnZdqU7wT1CDUnZ2dnUVZ_uqdnZ2d@xxxxxxxxxxxxx>:
Jan Panteltje wrote:
On a sunny day (Sun, 15 Mar 2009 10:59:55 -0500) it happened
"Anthony Fremont" <nobody@xxxxxxxxxxx> wrote in
<aL-dnfRulbJguCDUnZ2dnUVZ_sTinZ2d@xxxxxxxxxxxxx>:
Jan Panteltje wrote:
On a sunny day (Sun, 15 Mar 2009 09:51:12 -0500) it happened
"Anthony Fremont" <nobody@xxxxxxxxxxx> wrote in
<Iv-dnZWSocN_iCDUnZ2dnUVZ_q7inZ2d@xxxxxxxxxxxxx>:
Hello all,
I posted a short video on ABSE showing something I've been
tinkering with over the last couple of weeks. I wanted to learn
a little about the capturing data from the video for Linux (V4L2)
interface, and one thing led to another. I'm using a cheap BT878
capture card and a really cheap camera.
Anyone have any tips on improving the results or know of a good
source of info on the internet? Google likes to return links to
patent claims on anything related to the subject.
I am sort of interested, but do you have any other site then a
newsgroup that is not available?
Here is a link to a folder on photobucket. Sorry about the adds,
but it's free.
http://s55.photobucket.com/albums/g143/afremont/capture/
There are 10 still images and a couple of videos. One of the
videos is a much earlier trial.
Very nice.
The speed measurement depends on the distance I suppose?
How do you get the distance?
Could perhaps be done with 2 cameras, the parallax would tell you
something about it.
It's really just an estimate. It's reasonably accurate, but still
just an estimate. The true way to tell how fast they are going is
to watch how long it takes to cover a known distance (like you
didn't already know that). It's true that I'm giving the further
cars a bit of a break on the speed measurement, but I'm far enough
back and the street is narrow enough that the distance variation is
very limited in range so I don't factor it in.
I basically measure how fast the vertical yellow segments progress
thru the frame. Each pixel moved per frame is approximately 1.8MPH.
Frames arrive 30 times per second; each is timestamped to the uS by
the capture card's device driver.
Neat.
How do you get the motion vector?
I have some motion detection here,
http://panteltje.com/panteltje/mcamip/
but I just subtract 2 subsequent frames,
and the amount of difference tells me is something changed.
Do you calculate a motion vector?
I use subtraction like you do, but I have a couple of different ways of
doing it. Each has its strengths and weaknesses. I find "blobs" of change
and draw a box around the largest "blob". The rate of change of the X
coordinate of the vertical line segments is the motion vector.
.
- References:
- Video motion tracking and speed estimation
- From: Anthony Fremont
- Re: Video motion tracking and speed estimation
- From: Jan Panteltje
- Re: Video motion tracking and speed estimation
- From: Anthony Fremont
- Re: Video motion tracking and speed estimation
- From: Jan Panteltje
- Re: Video motion tracking and speed estimation
- From: Anthony Fremont
- Re: Video motion tracking and speed estimation
- From: Jan Panteltje
- Video motion tracking and speed estimation
- Prev by Date: Re: OT: Soda water oceans to replace global warming?
- Next by Date: Re: Question For The Gurus - Fan Noise (whine)
- Previous by thread: Re: Video motion tracking and speed estimation
- Next by thread: Re: Video motion tracking and speed estimation
- Index(es):
Relevant Pages
|