Kim Michael Fairchild (fair++at++iss.nus.sg)
Wed, 20 Sep 1995 14:20:14 +0800
>>
>> Hi,
>>
>> We are about the same thing in a quite simple way - just take an image
>> of the background WITHOUT the talking head and store it in memory. Then
>> in each frame we compare the backgroung with the current frame and the
>> head is where we find a significant difference. This is simple to implement
>> and works not-too-badly. It requires a static backgroung, i.e. if a
>> colegue is working behind you in the camera field of view it won't work.
>>
>> Hope this helps,
>> Igor
>>
Sorry, I think I didn't state the problem clearly in the first
message.
This is the same approach that we tried. Our problem seems to be that
1) the indy camera is terrible, the iris is so small we have to light
the person to get it to work.
2) the Indy seems to "pulse", the values aren't stable and so we get
problems like the dark hair of people fading in and out of the
background.
Do you do any cleanup algorithm to look for isolated pixels?
What machine do you use, Indy or PC? Love to share code.
thanks, Kim.
This archive was generated by hypermail 2.0b2 on Mon Aug 10 1998 - 17:51:53 PDT