Small Target Detection Based on Improved Local Energy Factor

Infrared small targets occupy fewer pixel points and lack significant features such as shape and color, so it is difficult to detect small targets under complex background. To achieve accurate detection of small infrared targets, this paper proposes a small target detection method based on improved local energy factor (ILEF). Firstly, low-threshold zero processing and morphological operations are used to suppress most of the background, then ILEF is constructed based on the local structural differences between the target and the background, and ILEF is computed for each pixel to obtain a feature map, which enhances the real target while further suppressing the background and the noise, and finally an adaptive threshold is designed to extract the small target. The detection capability of infrared small target based on the ILEF method is verified by using multiple infrared images in complex backgrounds and comparing with multiple local feature extraction methods. The experimental results show that the detection rate and detection accuracy distribution reach 95.1% and 86.8%, which are better than the comparison algorithms.