Infrared Small Target Detection Based on Weak Feature Enhancement and Target Adaptive Proliferation

Abstract

The imbalance between positive and negative samples and the loss of small targets in complex backgrounds are catastrophic for infrared small target detection. To address these issues, we proposed an infrared small target detection method based on weak feature enhancement and target adaptive proliferation (IRSTD-WFETAP). First, we utilized a sparse sampling mechanism and hybrid filtering method to flexibly capture the complex shapes and edge information of small targets while reducing the loss and shift of scarce features. Then, we introduced a multiscale feature enhancement module that used vertical-horizontal bidirectional attention and multiscale feature encoding to establish stable feature interaction channels between the encoder and decoder, further enhancing key features of small targets. In addition, we introduced a target data self-adaptive proliferation strategy (DSAS) to address the imbalance of positive and negative samples, enhancing the generalization and expression capability of the detection datasets. Finally, we proposed a target-background joint loss to alleviate the imbalance issue and help the network converge smoothly. Extensive experiments on NUAA-SIRST, IRSTD-1k, and our custom-made dataset demonstrated the effectiveness of the proposed IRSTD-WFETAP method, achieving superior performance in nIoU, Pd, Fa, and F1-measure compared to the latest methods.

Keywords

• Deep learning
• thermal infrared image
• thermal infrared small target detection (IRSTD)
• weak feature enhancement