Infrared and visible imagery fusion based on region saliency detection for 24-hour-surveillance systems

Abstract

With the growing demand for security, video surveillance is becoming increasingly important. And persistence is a key indicator for intelligent surveillance systems which means the ability to fit 24 hoursall-weather work. While the performances of traditional surveillance systems are limited since they can only gain either visible images during the day or intensity images in poor illumination conditions at night. To solve this problem, the integration of images from multiple sensors is becoming a new way. This paper utilize this measure to realize a whole day moving object detection system. First, infrared and visible images are integrated using Region saliency detection (RSD) method with different fusion strategies applied for salient and non-salient regions. In the next target detection stage, fused images are adopted instead of directly using images from various sensors for time efficiency. And background subtraction method is employed afterwards using Mixture of Gaussian (MOG). Experiments in several kinds of environments give promising results and show that this model is robust for whole-day surveillance.