MAPFF: Multiangle Pyramid Feature Fusion Network for Infrared Dim Small Target Detection

Infrared dim small target (IDST) detection holds significant importance in early target warning and ground monitoring. However, IDST detection remains a long-standing challenge due to the low signal-to-noise ratio and low contrast. Feature fusion is an effective approach for feature enrichment and i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-16
Main Authors: Yang, Hai, Liu, Jing, Wang, Zhe, Fu, Zhiling, Tan, Qinyan, Niu, Saisai
Format: Article
Language:English
Subjects:
Attention mechanism
False alarms
Feature extraction
feature fusion
Fuses
Image segmentation
infrared small target
Kernel
Modules
Monolayers
Multilayers
Object detection
Semantics
Signal to noise ratio
Target detection
Task analysis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Infrared dim small target (IDST) detection holds significant importance in early target warning and ground monitoring. However, IDST detection remains a long-standing challenge due to the low signal-to-noise ratio and low contrast. Feature fusion is an effective approach for feature enrichment and improving poor performance in IDST detection. Existing feature fusion methods tend to overlook the importance of focusing on both multilayer and single-layer features, which prevents target features from being fully exploited, resulting in suboptimal outcomes for IDST detection. In this article, we present a multiangle pyramid feature fusion (MAPFF) network, which selects fusion objects from multiple perspectives and then fuses them. Namely, multilayer features and single-layer features-two perspectives of the fusion object-are selected and fused separately. The MAPFF network consists of two primary modules: a cross-layer complementary feature (CLCF) module and an atrous spatial pyramid pooling with attention (AttnASPP) module. To effectively fuse semantic and geometric detail information, the CLCF module adaptively combines different layer features as complementary features, while the original layer features serve as the main features. Concurrently, through channel shuffle, the complementary and main features achieve substantial information exchange. The AttnASPP module employs parallel atrous convolutions with multiple dilation rates to obtain multiscale information and incorporates an attention mechanism to emphasize effective features. Experimental results on the SIATD, SIRST, and IRSTD_1k datasets demonstrate that our method can precisely identify IDSTs, significantly reduce the false alarm rate, and outperform other methods.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3388261