| |
In lugnet.robotics.rcx.legos, Bapt Denaeyer wrote:
> I've test a new filter for the camera .... In my first study I applied a
> filter only in one image .... Now I take the "time" parameter ! I make a
> difference between two image and here is the result
>
> When nothing move : http://nanobapt.homelinux.com/img/VC/nothingmove.jpg
> When I move my head : http://nanobapt.homelinux.com/img/VC/movehead2.jpg
> Original picture : http://nanobapt.homelinux.com/img/VC/original.jpg
>
> We can imagine that the software detect when sothing move and then
> transmit the position to another soft ....
This is a pretty cool technique! I really like the middle picture
(movehead2.jpg) just as a work of art.
> There are some trouble when the camera make his auto brightness. All the
> image change
You could overcome this by subtracting out the minimum pixel change from all
pixels. So if the entire picture gets brighter or darker, you adjust the
"delta" image to contain black pixels once again.
You might need to do some statistical footwork to determine a suitable
real-world offset to apply, but you should be able to detect when the entire
image gets brighter or darker all at once. You could even take the average
change of all RGB pixel values and subtract that out from the final image as a
first attempt.
- Chris.
|
|
Message has 1 Reply:
Message is in Reply To:
 | | Vision command + linux
|
| I've test a new filter for the camera .... In my first study I applied a filter only in one image .... Now I take the "time" parameter ! I make a difference between two image and here is the result When nothing move : (URL) I move my head : (URL) (...) (21 years ago, 11-Dec-03, to lugnet.robotics.rcx.legos, lugnet.robotics)
|
4 Messages in This Thread:
  
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
