Detection of Small Target Using Schatten 1/2 Quasi-Norm Regularization with Reweighted Sparse Enhancement in Complex Infrared Scenes

Abstract

In uniform infrared scenes with single sparse high-contrast small targets, most existing small target detection algorithms perform well. However, when encountering multiple and/or structurally sparse targets in complex backgrounds, these methods potentially lead to high missing and false alarm rate. In this paper, a novel and robust infrared single-frame small target detection is proposed via an effective integration of Schatten 1/2 quasi-norm regularization and reweighted sparse enhancement (RS1/2NIPI). Initially, to achieve a tighter approximation to the original low-rank regularized assumption, a nonconvex low-rank regularizer termed as Schatten 1/2 quasi-norm (S1/2N) is utilized to replace the traditional convex-relaxed nuclear norm. Then, a reweighted l1 norm with adaptive penalty serving as sparse enhancement strategy is employed in our model for suppressing non-target residuals. Finally, the small target detection task is reformulated as a problem of nonconvex low-rank matrix recovery with sparse reweighting. The resulted model falls into the workable scope of inexact augment Lagrangian algorithm, in which the S1/2N minimization subproblem can be efficiently solved by the designed softening half-thresholding operator. Extensive experimental results on several real infrared scene datasets validate the superiority of the proposed method over the state-of-the-arts with respect to background interference suppression and target extraction.

Robust Infrared Small Target Detection via Jointly Sparse Constraint of l1/2-Metric and Dual-Graph Regularization

“…For instance, Dai et al [22] proposed a weighted IPI model (WIPI), which used the target likelihood coefficient based on steering kernel instead of the constant weight. In [23,24], the nonconvex and tighter rank surrogate acts as a substitute for the original nuclear norm to achieve better background suppression. Besides, in the enhancement type of the IPI model, Wang et al [45] used the total variation regularization (TVPCP) to depict the background feature, which aimed to obtain good target-background separation for some mild situations.…”

“…Difference to related existing subspace learning based methods: As a subspace learning method, our proposed model differs from the aforementioned ones in several aspects. (1) Our method incorporates prior information in both spatial and feature spaces of patch images simultaneously, whereas other methods [21][22][23][24] only take the priors within the patch space into account, ignoring the feature space.…”

“…(2) Our method employs the sparser regularizer instead of commonly used reweighting manner [22][23][24] to enhance the sparsity of small targets, so as to suppress target-like outlier better. (3) Our method uses LADMAP to give the model solution, while other methods apply the traditional ADMM [45,46], which will introduce too many multipliers, leading to increasing time consumption.…”

“…where M t and µ b are same as those in Equation (24). The higher the above three indicators, the better the background suppression performance of the detection method is.…”

Classification of Infrared Objects in Manifold Space Using Kullback-Leibler Divergence of Gaussian Distributions of Image Points

“…Many different approaches have been proposed for infrared object tracking such as saliency extraction [9], multiscale patch-based contrast measure and a temporal variance filter [14], feature learning and fusion, reliability weight estimation based on nonnegative matrix factorization [15], Poisson reconstruction and the Dempster-Shafer theory [16], three-dimensional scalar field [17], a double-layer region proposal network (RPN) [18], Siamese convolution network [19], a mixture of Gaussians with modified flux density [20], spatial-temporal total variation regularization and weighted tensor [21], two-stage U-skip context aggregation network [22], histogram similarity map based on the Epanechnikov kernel function [23], quaternion discrete cosine transform [24], non-convex optimization [25], Mexican-hat distribution of pixels [26], and Schatten regularization with reweighted sparse enhancement [27].…”