English

Neural Spatial-Temporal Tensor Representation for Infrared Small Target Detection

Computer Vision and Pattern Recognition 2024-12-24 v1

Abstract

Optimization-based approaches dominate infrared small target detection as they leverage infrared imagery's intrinsic low-rankness and sparsity. While effective for single-frame images, they struggle with dynamic changes in multi-frame scenarios as traditional spatial-temporal representations often fail to adapt. To address these challenges, we introduce a Neural-represented Spatial-Temporal Tensor (NeurSTT) model. This framework employs nonlinear networks to enhance spatial-temporal feature correlations in background approximation, thereby supporting target detection in an unsupervised manner. Specifically, we employ neural layers to approximate sequential backgrounds within a low-rank informed deep scheme. A neural three-dimensional total variation is developed to refine background smoothness while reducing static target-like clusters in sequences. Traditional sparsity constraints are incorporated into the loss functions to preserve potential targets. By replacing complex solvers with a deep updating strategy, NeurSTT simplifies the optimization process in a domain-awareness way. Visual and numerical results across various datasets demonstrate that our method outperforms detection challenges. Notably, it has 16.6×\times fewer parameters and averaged 19.19\% higher in IoUIoU compared to the suboptimal method on 256×256256 \times 256 sequences.

Keywords

Cite

@article{arxiv.2412.17302,
  title  = {Neural Spatial-Temporal Tensor Representation for Infrared Small Target Detection},
  author = {Fengyi Wu and Simin Liu and Haoan Wang and Bingjie Tao and Junhai Luo and Zhenming Peng},
  journal= {arXiv preprint arXiv:2412.17302},
  year   = {2024}
}
R2 v1 2026-06-28T20:46:03.273Z