Infrared Small Target Detection Based on the Improved Density Peak Global Search and Human Visual Local Contrast Mechanism

Abstract

Effective detection of small targets plays a pivotal role in infrared (IR) search and track applications for modern military defense or attack. However, IR small targets are very difficult to detect because of their weak brightness, small size, and lack of shape, structure, texture, and other information elements. In order to simultaneously satisfy the robustness and timeliness of target detection, inspired by density peak clustering and the human visual system, an idea combining an improved density peak global search and local contrast calculation is proposed. First, the positions of candidate targets are determined in the preprocessed image using the improved density peak global search method (IDPGSM). Second, the saliency map is obtained using the double-weights enhanced local contrast method (DWELCM) for the candidate target neighborhood. Finally, adaptive threshold segmentation is used to detect IR small targets. Through comprehensive analysis of five evaluation indicators, the experimental results on seven real sequences and three hundred IR images of different scenes that the proposed method has better detection performance compared with six baseline methods. It can quickly and accurately determine the small target position in the case of severe background clutter and noise interference. Index Terms-Double-weights enhanced local contrast method (DWELCM), improved density peaks global search (IDPGSM), infrared (IR) small target, three-layer window. I. INTRODUCTIONA N INFRARED (IR) detection system is a passive detection device that works in the IR spectrum of the atmospheric window band. It is an important part of advanced electronic warfare and integrated fire-control systems. In a complex and strong electromagnetic interference environment, an IR detection system has many advantages, such as strong anti-interference ability, good concealment, ability to work during the day and night, and high measurement accuracy. Therefore, it is widely used in weapon systems for IR early warning, reconnaissance, and precision guidance in airborne, shipborne, vehicle, and spaceborne applications [1]. In a complex battlefield environment, an IR detection system is often required to quickly locate and Manuscript

A Detection Method With Antiinterference for Infrared Maritime Small Target

“…Most of the previous IR small target detection researches do not emphasize the detection scenarios. They can be used in the sky, farm and other scenarios [12][13][14][15][16]. Of course, they can also be used in maritime targets detection.…”

Generative Adversarial Differential Analysis for Infrared Small Target Detection

“…The method is better for uniform background suppression but is not as effective for complex backgrounds. Human visual system, such as local contrast measure (LCM) [11] and multiscale patch-based contrast measure (MPCM) [12], halo structure prior-based LCM (HSPLCM) [13], and the idea combining an improved density peak global search and local contrast calculation [14], mainly exploits the intrinsic properties of infrared small targets. The local texture of the image changes when the small target appears instead of the global texture, so the local features are used to complete the detection task.…”

CSAN-UNet: Channel Spatial Attention Nested UNet for Infrared Small Target Detection

“…In the realm of single-frame infrared small target detection, traditional methods have been the cornerstone, employing model-driven approaches grounded in assumptions about the target's physical and imaging characteristics. These methods fall into three primary categories: filter-based methods [6][7][8], which aim to enhance the visibility of targets by predicting and subtracting the background; local information-based methods [9][10][11][12][13][14][15], which detect targets based on the premise that the gray value and intensity of objects and their surroundings undergo sudden changes; and data structure-based methods [16][17][18][19][20][21], which approach the detection task as a problem of sparse low-rank tensor decomposition, identifying targets through the analysis of structural data. However, these traditional methods exhibit significant limitations, notably their reliance on handcrafted features designed based on prior knowledge of target appearances, and the need for extensive parameter tuning to adapt to the expected characteristics of the targets.…”