Improved background modeling for real-time spatio-temporal non-parametric moving object detection strategies

摘要

Answering to the growing demand of machine vision applications for the latest generation of electronic devices endowed with camera platforms, several moving object detection strategies have been proposed in recent years. Among them, spatio-temporal based non-parametric methods have recently drawn the attention of many researchers. These methods, by combining a background model and a foreground model, achieve high-quality detections in sequences recorded with non-completely static cameras and in scenarios containing complex backgrounds. However, since they have very high memory and computational associated costs, they apply some simplifications in the background modeling process, therefore decreasing the quality of the modeling. Here, we propose a novel background modeling that is applicable to any spatio-temporal non-parametric moving object detection strategy. Through an efficient and robust method to dynamically estimate the bandwidth of the kernels used in the modeling, both the usability and the quality of previous approaches are improved. Furthermore, by adding a novel mechanism to selectively update the background model, the number of misdetections is significantly reduced, achieving an additional quality improvement. Empirical studies on a wide variety of video sequences demonstrate that the proposed background modeling significantly improves the quality of previous strategies while maintaining the computational requirements of the detection process.