Infrared small target enhancement and detection based on modified top-hat transformations

Abstract

To simply and efficiently enhance and detect infrared small target, a new algorithm through target enhancement by using modified top-hat transformations is proposed. Firstly, the modified top-hat transformations following the property of small target region are discussed, which could efficiently extract the possible target and dark regions. Secondly, the potential target regions are enhanced by using a target enhancement operation which is formed through enlarging the contrast between bright and dark regions using the modified top-hat transformations. Finally, an iterative thresholding method is used to automatically detect the target region. Various infrared images embedded with small targets are used to verify the efficiency of the algorithm, and experimental results show that our algorithm is very efficient.