run_bg_esti — Estimate the background and return the foreground region.
run_bg_esti adapts the background image stored in the
BgEsti data set using a Kalman filter on each pixel and
returns a region of the foreground (detected moving objects).
For every pixel an estimation of its grayvalue is computed using the
values of the current data set and its stored background image and
the current image (
PresentImage). By comparison to the
threshold (fixed or adaptive, see
pixels are classified as either foreground or background.
The background estimation processes only single-channel images. Therefore the background has to be adapted separately for every channel.
The background estimation should be used on half- or even
quarter-sized images. For this, the input images (and the
initialization image!) has to be reduced using
zoom_image_factor. The advantage is a shorter run-time on one
hand and a low-band filtering on the other. The filtering eliminates
high frequency noise and results in a more reliable estimation. As a
result the threshold (see
create_bg_esti) can be
lowered. The foreground region returned by
then has to be enlarged again for further processing.
The passed image (
PresentImage) must have the same
type and size as the background image of the current data set
→object (byte / real)
Region of the detected foreground.
ID of the BgEsti data set.
* Read image for initialization: read_image(InitImage,'xing/init') * Initialize BgEsti dataset with * fixed gains and threshold adaption: create_bg_esti(InitImage,0.7,0.7,'fixed',0.002,0.02, \ 'on',7.0,10,3.25,15.0,BgEstiHandle) * Read the next image in sequence: read_image(Image0,'xing/xing000') * Estimate the background: run_bg_esti(Image0,ForegroundRegion1,BgEstiHandle) * Display the foreground region: dev_display (ForegroundRegion1) * Read the next image in sequence: read_image(Image1,'xing/xing001') * Estimate the background: run_bg_esti(Image1,ForegroundRegion2,BgEstiHandle) * Display the foreground region: dev_display (ForegroundRegion2) * etc.
run_bg_esti returns 2 (H_MSG_TRUE) if all parameters are