.png){kind=icon}
.png){kind=icon}
Return
Feature-Guided Discriminative Ring Local Contrast Measure for Infrared Small Target Detection
.png){kind=icon}
PRE
AI
D
胡
J
D
DOI：10.1109/lgrs.2026.3710496.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The infrared small targets detection (IRSTD) is easily affected by structural edges and textured backgrounds, which degrades performance. The existing deep learning (DL)- and low-rank sparse representation (LRSR)-based methods suffer from high computational complexity, while local contrast measure (LCM)-based methods are limited in structure suppression and feature fusion. To address these issues, this letter proposes a feature-guided discriminative ring local contrast measure (FGDRLCM) for IRSTD. Specifically, an information-discriminative ring local contrast measure (ID-RLCM) is first designed to enhance small targets while suppressing structural interference. Then, a multidirectional group structure tensor model (MDG-STM) is introduced to improve the separability between targets and structural components, providing effective structure suppression cues. Finally, guided filtering is employed for adaptive feature fusion, followed by a global-statistics-based adaptive thresholding strategy to obtain detection results. Experimental results demonstrate that the proposed method achieves effective detection performance under complex backgrounds with low computational complexity, showing strong potential for practical applications. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/biangbiangliang/FGDRLCM</uri>
Keywords:
Guided filtering
infrared small target
ring local contrast measure
structure tensor
Journal
I
IF:
4.4
Papers:
486
Citations:
0
Organization
Cited Papers