Local Gradient Field Feature Contrast Measure for Infrared Small Target Detection
Bin Xiong, Xinhan Huang, Min Wang
Abstract
To overcome the drawbacks of conventional methods to detect infrared (IR) small targets, including high false alarm probability and low detection rate, a novel approach to detect IR small targets based on local gradient field feature contrast measure (LGFFCM) is presented in this letter. First, the distinctive characters of the target, background, and clutter in the infrared gradient vector field (IGVF) are investigated. Next, a local contrast measure based on IGVF features was proposed. Then, an adaptive threshold method to obtain coarse detection results is proposed. Finally, a flux across the plane curve in the IGVF, which can eliminate clutter and enhance target, is defined. The experimental results indicate that the proposed approach shows superiority to other advanced approaches and can effectively and stably reduce false alarm probability and enhance detection rate.