Vision-Based Vehicle Surveillance and Parking Lot Management Using Multiple Cameras

This paper proposes a vision-based vehicle surveillance system for parking lot management in outdoor environments. Due to the limited field of view of camera, this system uses multiple cameras for monitoring a wide parking area. Then, an affine transformation is used for merging the scenes obtained from these multiple cameras. Two major components are included, i.e., vehicle counting and parking lot management. For the first one, this paper integrates three features, i.e., color, position, and motion together for well tracking vehicles across different cameras. Thus, even though vehicles are occluded together, they still can be well tracked and identified across different cameras and under different lighting changes. For the second one, we propose a model-based approach to model the color changes of parking ground for determining whether a parking space is vacant. Due to the perspective effects, the visibility of a parking space is often affected by the vehicle parking on its neighborhood. To tackle this problem, two geometrical models (ellipses and grids) are proposed for well representing a parking space. Then, with different weights, a hybrid scheme is then constructed for well determining whether a parking space is vacant. The experimental results reveal that our system works well and accurately under different lighting and occlusion conditions.