Infrared background suppression method based on low-pass adaptive morphological filtering

Dim infrared targets often have low recognition accuracy in complex environments, because of its small size and low brightness. Therefore, this paper presents an infrared background suppression method based on low-pass adaptive morphological filtering. In this method, the infrared background noise is connected into multiple regions by low-pass filtering, the adaptive morphological mask is generated by local mean variance ratio and region growth, and then most of the background is suppressed by top-hat operation. The test results show that this method can suppress the background of infrared images and enhance the target signal.

I. Introduction

Target detection technology based on infrared band has always been a hot topic in the field of target tracking because of its small influence by external illumination and its ability to work in various weather conditions. However, the target in infrared image is greatly affected by clutter and complex background, so the detection accuracy of dim targets is often poor. Therefore, in order to improve the accuracy of dim target recognition, background suppression is needed to enhance the contrast between target and ambient noise.