A Robust Infrared Small Target Detection Algorithm Based on Human Visual System

Abstract

Robust human visual system (HVS) properties can effectively improve the infrared (IR) small target detection capabilities, such as detection rate, false alarm rate, speed, etc. However, current algorithms based on HVS usually improve one or two of the aforementioned detection capabilities while sacrificing the others. In this letter, a robust IR small target detection algorithm based on HVS is proposed to pursue good performance in detection rate, false alarm rate, and speed simultaneously. First, an HVS size-adaptation process is used, and the IR image after preprocessing is divided into subblocks to improve detection speed. Then, based on HVS contrast mechanism, the improved local contrast measure, which can improve detection rate and reduce false alarm rate, is proposed to calculate the saliency map, and a threshold operation along with a rapid traversal mechanism based on HVS attention shift mechanism is used to get the target subblocks quickly. Experimental results show the proposed algorithm has good robustness and efficiency for real IR small target detection applications.Index Terms-Human visual system (HVS), improved local contrast measure (ILCM), infrared (IR) small target.

Infrared Small Target Detection via Non-Convex Rank Approximation Minimization Joint l2,1 Norm

“…The local contrast measure (LCM) [14] was first proposed to describe the dissimilarity between the current cell and its eight adjacent cells, which is calculated pixel by pixel and is very time consuming. For good performance in detection rate, false alarm rate and speed simultaneously, the improved LCM (ILCM) [15], the novel LCM (NLCM) [16], and the relative LCM (RLCM) [17] were provided to calculate the saliency map. The multiscale patch-based contrast measure (MPCM) [18] focuses on the multi-directional dissimilarity between the current patch and the surrounding patches.…”

“…Unfortunately, most backgrounds do not meet the ideal assumption, leading to a high false alarm ratio. Recently, approaches based on human visual system (HVS) [11] have been developed to improve the performance of infrared small target detection with the assumption that the target is the most salient object, most of which compute the saliency map in a manner of filtering [7,[12][13][14][15][16][17][18] or transforming [19,20]. Actually, in many real scenes, the most prominent object is not the desired target while the highlight edges and salient non-target components can destroy the whole detection.…”

A centre-scale sorting local contrast method for infrared small target detection

“…Kim et al [3] initially applied Laplacian of Gaussian (LoG) filtering to enhance contrast in infrared images. Building upon this work, Wang et al [4] proposed the difference of Gaussian (DoG) filter, and Han et al [5] further introduced the Gabor function. Additionally, Han et al proposed a Gabor function difference filter based on these techniques.…”

“…In order to incorporate local orientation information, Chen et al [6] proposed the Local Contrast Measure (LCM) method, which enhances images by considering the gray-scale ratio between each position and its local neighboring region. Based on this, Han et al [7] proposed an improved local contrast measure (ILCM), Qin et al [8] introduced a novel local contrast measure (NLCM), and Wei et al [9] developed a multiscale patch-based contrast measure (MPCM). Deng et al [10][11] weighted local contrast with information entropy.…”

Infrared Small Target Detection Based on Partial Sum of the Tensor Nuclear Norm

“…The prior information is the key to the success of single-frame-based methods, also in many other fields [9][10][11]. Up to now, the consistency of backgrounds [12][13][14][15], the saliency of targets [16][17][18][19], the sparsity of targets and the low rank of backgrounds [20][21][22][23][24] are the most used assumptions to detect infrared small targets in single image from different perspectives. The former two are local priors, whereas the latter two are nonlocal priors which are usually exploited simultaneously.…”