A Local Contrast Method Combined With Adaptive Background Estimation for Infrared Small Target Detection

Abstract

Local contrast has been proven as an efficient method for infrared (IR) small target detection, but existing local contrast algorithms just directly choosing the neighboring area of a current position as the reference when calculating the local contrast of the current position, which may bring an inaccurate result. Meanwhile, existing algorithms are either ratio form or difference form, they cannot effectively enhance true target and suppress all the types of complex backgrounds simultaneously. In this letter, a new local contrast scheme that introduces the adaptive background estimation is proposed to provide a more accurate reference, and the multidirectional 2-D least mean square (MDTDLMS) algorithm that is more suitable for small target detection is presented. Then, a new ratio-difference joint local contrast measure (RDLCM) is proposed between raw IR image and the MDTDLMS result to enhance true small target and suppress all the types of complex backgrounds simultaneously. Experimental results show that the proposed MDTDLMS-RDLCM algorithm can achieve a good detection performance for different types of backgrounds and targets.