A real-time method for object detection and tracking in outdoor enviro
nments where illumination can be very low and not constant is presente
d. A hierarchical (two levels) change detection method is employed to
detect moving objects in the scene. At the first level, a focus-of-att
ention stage is applied to individuate image areas containing moving o
bjects; at the second level, each selected image area is inspected at
higher accuracy to improve the detection probability and to obtain an
accurate binary reconstruction of the object shape. A background updat
ing procedure is used to adapt the background image to the changes in
the scene. Then, an extended Kalman filter is applied to track multipl
e objects entering the scene. Results are reported on real scenarios i
n the presence of shadows, occlusions, light reflections, and bad envi
ronmental conditions. (C) 1998 Society of Photo-Optical instrumentatio
n Engineers.