Layered detection


lThe scene can change after initial training.  These changes should update the background model.
lAdditional model ¡®cache¡¯ - The values re-appearing for a certain amount of time enter the background model as non-permanent, short-term backgrounds.

Example1: Unloading boxes from car

In this example, a man is unloading two boxes after parking his car.  The pixels are labeled by different colors based on time-layers.  We will be able to detect and know the person (who) stopped the car at the parking lot (where) and unloaded two boxes (what) at a certain time (when).

Original image Layered modeling/detection Current detection

Example2: Placing box and purse.

In this example, a woman placed a box on the desk and then it has been absorbed into the background model as non-permanent.  Then a purse is put in front of the box. It is detected against both the box and the desk.

Click here if you cannot see the video

Back to main page