Reweighted Infrared Patch-Tensor Model With Both Nonlocal and Local Priors for Single-Frame Small Target Detection

By Yimian Dai, Yiquan Wu. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017

547 citations recorded by the source corpus.

Many state-of-the-art methods have been proposed for infrared small target detection. They work well on the images with homogeneous backgrounds and high-contrast targets. However, when facing highly heterogeneous backgrounds, they would not perform very well, mainly due to: 1) the existence of strong edges and other interfering components, 2) not utilizing the priors fully. Inspired by this, we propose a novel method to exploit both local and nonlocal priors simultaneously. First, we employ a new infrared patch-tensor (IPT) model to represent the image and preserve its spatial correlations. Exploiting the target sparse prior and background nonlocal self-correlation prior, the target-background separation is modeled as a robust low-rank tensor recovery problem. Moreover, with the help of the structure tensor and reweighted idea, we design an entrywise local-structure-adaptive and sparsity enhancing weight to replace the globally constant weighting parameter. The decomposition could be achieved via the elementwise reweighted higher order robust principal component analysis with an additional convergence condition according to the practical situation of target detection. Extensive experiments demonstrate that our model outperforms the other state-of-the-arts, in particular for the images with very dim targets and heavy clutters.

Subfields: Aerospace Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/78d39057605e98c56ead7a273a5414f9abc9846e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Electrical and Electronic Engineering

Citations in the corpus

ISNet: Shape Matters for Infrared Small Target Detection (2022, methodology): “…lo-cal contrast measure (WSLCM) [12], filtering based meth-ods [2, 9], as well as low-rank based methods, such as reweighted infrared patch-tensor (RIPT) [5], partial sum of the tensor nuclear norm [39], Infrared patch-image (IPI) [10], and non-convex rank approximation minimization [38].”
UIU-Net: U-Net in U-Net for Infrared Small Object Detection (2022, methodology): “infrared patch-tensor (RIPT) [14] model, transformed domain filter-based methods nonnegativity-constrained variational”
Infrared Small Target Detection via Non-Convex Rank Approximation Minimization Joint l2, 1 Norm (2018, methodology): “Since the constraints are more powerful than the IPI-based methods, the proposed algorithm converged faster.”
Infrared Small Target Detection Based on Partial Sum of the Tensor Nuclear Norm (2019, methodology): “7 10 ε = RIPT [42] Patch size: 30 × 30, sliding step: 10, / min( , ) L m n λ= , 1 L = , 1 h = , 7 10 ε = Ours Patch size: 40 × 40, sliding step: 40, 1 2 3 0.6/ max( , ) n n n λ = ∗ , 7 10 ε − = In this subsection, for a comprehensive comparison with the aforementioned state-of-the-art approaches,…”
Asymmetric Contextual Modulation for Infrared Small Target Detection (2020, methodology): “It shows that RIPT trades off the detection ability with the target integrity.”
Infrared Dim and Small Target Detection via Multiple Subspace Learning and Spatial-Temporal Patch-Tensor Model (2021, methodology): “From the perspective of data structure, a reweighted infrared patch-tensor (RIPT) method [32] expands the matrix domain to tensor domain.”
Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images (2019, methodology): “A common pipeline is to apply image ﬁltering [12, 29, 3], contrast and saliency detection [4, 9, 11] or low-rank recovery [13, 8, 7] to suppress the background and enhance the objects to obtain a conﬁdence map.”
Attentional Local Contrast Networks for Infrared Small Target Detection (2020, methodology): “, smooth [9] or nonlocal correlated [10] or both [11].”
Dense Nested Attention Network for Infrared Small Target Detection (2021, methodology): “Typical methods include filtering-based methods [6], [9], local contrast measure based methods [10], [11], [12], [13], [14], [15], and low rank based methods [7], [8] [16], [17], [18], [19].”