Detecting Dim Small Target in Infrared Images via Subpixel Sampling Cuneate Network

Infrared dim small target (IDST) detection is regarded as a critical technology for the interpretation of space-based remote sensing images. In recent years, driven by deep learning technology and the surge of data, remarkable effects have been achieved for dim small target detection in infrared images. Nevertheless, the intrinsic feature scarcity and low signal-to-clutter ratio (SCR) characteristics pose tremendous challenges to deep learning-based detection methods. In this letter, we present a novel subpixel sampling cuneate network (SPSCNet) to detect dim small targets in infrared images. The overall model architecture is based on an end-to-end cuneate network with multiple groups of parallel high-to-low resolution subnetworks. Specifically, we design a multiscale feature reweighted fusion (MSFRF) module to effectively fuse multiscale feature maps which contain both low-level detail features and high-level semantics information. In addition, considering that the pooling operation may lose dim small targets with low SCR, we also exploit a subpixel sampling scheme to greatly retain the features of small targets. Moreover, to better test and verify the performance of the proposed method, we also develop an IDST dataset to conduct more comparative experiments. Extensive experiments on the single-frame infrared small target (SIRST) and IDST datasets illustrate that the proposed SPSCNet yields state-of-the-art performance in comparison with other detection algorithms.