MDIGCNet: Multidirectional Information-Guided Contextual Network for Infrared Small Target Detection
Infrared small target detection (ISTD) technology has extensive applications in the military field. Due to the quality of imaging equipment and environmental interference, infrared small target images lack texture and structural information. Deep learning-based algorithms have achieved superior accu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10770559/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Infrared small target detection (ISTD) technology has extensive applications in the military field. Due to the quality of imaging equipment and environmental interference, infrared small target images lack texture and structural information. Deep learning-based algorithms have achieved superior accuracy in this field compared to traditional algorithms; however, these methods are often not designed with domain knowledge integration. In this article, we propose a multidirectional information-guided contextual network (MDIGCNet) for ISTD. The primary structure of this network adopts the U-Net architecture. To address the issue of lacking texture and structural information in the target images, we employ an integrated differential convolution (IDConv) module to extract richer image features during both the encoding and decoding stages. Skip connections in the network utilize a multidirectional gradient information extraction block (MGIEB) to obtain gradient features of infrared small targets. Our domain-inspired multidirectional Gaussian differential convolution (MGDC) module is employed to extract features of Gaussian-distributed small targets, enhancing the distinction between targets and backgrounds. Additionally, we designed a local-global feature fusion (LGFF) module incorporating an attention mechanism to merge shallow and deep features, thereby improving the efficiency of feature utilization within the model. Furthermore, since both IDConv and MGDC are parallel multiconvolutional kernel structures, reparameterization techniques are used to avoid excessive parameters and computational load. Experimental results on public datasets NUDT-SIRST, IRSTD-1k, and SIRST-Aug demonstrate that our algorithm outperforms other state-of-the-art methods in detection performance. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |