Detection Of Camouflaged Targets Research Articles

Camouflaged target detection based on multimodal image input pixel-level fusion

Camouflaged target detection based on multimodal image input pixel-level fusion

RSVP-based BCI for inconspicuous targets: detection, localization, and modulation of attention

Objective.While brain-computer interface (BCI) based on rapid serial visual presentation (RSVP) is widely used in target detection, patterns of event-related potential (ERP), as well as the performance on detecting inconspicuous targets remain unknown. Moreover, participant-screening methods to excluded 'BCI-blind' users are still lacking.Approach.A RSVP paradigm was designed with targets of varied concealment, size, and location. ERPs (e.g. P300 and N2pc) and target detection accuracy were compared among these conditions. The relationship between participants' attention scores and target detection accuracy was also analyzed to test attention level as a criterion for participant screening.Main results.Statistical analysis showed that the conditions of target concealment and size significantly influenced ERP. In particular, ERP for inconspicuous targets, such as concealed and small targets, exhibited lower amplitudes and longer latencies. In consistent, the accuracy of detection in inconspicuous condition was significantly lower than that of conspicuous condition. In addition, a significant association was found between attention scores and target detection accuracy for camouflaged targets.Significance.The study was the first to address ERP features among multiple dimensions of concealment, size, and location. The conclusion provided insights into the relationship between ERP decoding and properties of targets. In addition, the association between attention scores and detection accuracy implied a promising method in screening well-behaved participants for camouflaged target detection.

Lightweight camouflaged object detection model based on multilevel feature fusion

The intrinsic similarity between camouflaged objects and background environment impedes the automatic detection/segmentation of camouflaged objects, and novel network architectures for deep learning are promising to overcome this challenge and improve detection accuracy. However, these existing network architectures for distinguishing between camouflaged objects and their backgrounds do not account for the constraint of detection speed, which results in high computational complexity and the inability to meet the requirements of rapid detection. Therefore, based on the human visual system, this study proposes a single-stage lightweight camouflage object detection network using multilevel feature fusion, integrating features of various feature layers and receptive field sizes. Using three benchmark datasets for normal camouflaged objects, the lightweight network (LINet) model demonstrated an accuracy superior to those of six existing mainstream camouflaged object detection methods. Its detection speed, 126.3 frames per second, is significantly higher than those of the existing mainstream methods, enabling rapid detection with a maximum increase of 187.62%. The accuracy of LINet is the minimum and maximum for Resnet101 and Resnet152, respectively. These findings pave the way for diverse applications of camouflaged target detection algorithms.

Deep learning-based spectral reconstruction in camouflaged target detection

Camouflaged target detection aims to detect targets that blend into their surroundings, but RGB has difficulty distinguishing between targets and backgrounds. While methods using multispectral image (MSI) can distinguish targets from background via spectral information, they are limited by imaging speed, resolution, and high cost for camouflaged target detection. Here, we propose a novel camouflaged target detection workflow based on reconstructed MSI from RGB image. Specifically, we propose a spectral reconstruction model, S2HFormer, which utilizes the deep neural network to fit the mapping of RGB image to MSI without additional information. And the reconstructed MSI based on S2HFormer achieves higher accuracy in both reconstruction and target detection, outperforming existing methods. Furthermore, we integrate a spectral band selection algorithm to optimize the number of bands used for improving detection efficiency. Experimental results show that the proposed method acquires MSI at 55 frames per second (FPS) and achieves an F-score of 0.925, achieving real-time (24 FPS) MSI acquisition. The evaluation indicates the effectiveness and efficiency of our method for camouflaged target detection.

MilDetr: Detection Transformer for Military Camouflaged Target Detection

MilDetr: Detection Transformer for Military Camouflaged Target Detection

Camouflage target detection based on strong semantic information and feature fusion

Camouflage target detection based on strong semantic information and feature fusion

A camouflage target detection method based on local minimum difference constraints

A camouflage target detection method based on local minimum difference constraints

Digital Camouflage Pattern Design Based on the Biased Random Walk

Digital camouflage is a common countermeasure against military reconnaissance. In the face of high-tech imaging reconnaissance, battlefield detection means tend to be automated and refined. In order to adapt to the concealment requirements under various environmental backgrounds, combined with the camouflage performance of digital camouflage and its feedback mechanism in camouflage pattern design, this paper proposed a digital camouflage pattern design method based on biased random walk. Firstly, the original background is preprocessed, and the background texture’s direction, corner, step length, and pixel intensity difference are statistically analyzed, and the boundary probability between pixel nodes is estimated. Then, a biased random walk is used to outline the camouflage patches. The edge scatter is enriched according to the density of the patches, and the camouflage patches are filled according to the proportion of the main color of the background. Finally, a digital camouflage pattern is obtained. The quantitative analysis results show that the mean heart rate of the digital camouflage pattern based on multiscene design is at least 31.0% higher than that of the original background segmentation texture, and the standard deviation index of equivalent diameter is increased by 14.9% on average. In addition, the results of simulation camouflage image detection in multiple scenes show that the proposed method can effectively deal with camouflage target detection on the basis of fully retaining the original background texture information and has strong camouflage concealment effect in the scene.

Research on camouflage target detection method based on improved YOLOv5

Objective: In the task of camouflage target detection, there is a problem that the target is highly integrated with the complex environment background, which is difficult to identify and leads to false detection and missed detection. A target detection algorithm CM-YOLOv5s is proposed for camouflage characteristics. Method: The algorithm uses YOLOv5s as the basic framework. First, a coordinated attention mechanism is embedded in the backbone feature extraction network, which enhances the network’s ability to extract camouflaged target features, weakens the attention to the surrounding background, and effectively improves the algorithm’s anti-background. Interference ability; secondly, the Mixup data enhancement strategy is used to simulate overlapping occlusion scenarios, which further strengthens the network model’s learning ability for complex samples. Results: The training and verification were carried out on the self-made Military Camouflage Target Dataset (MCTD), and the precision, recall, and average mAP of the improved CM-YOLOv5s algorithm reached 95.9%, 87.1%, and 94.1, respectively. %, compared with the original YOLOv5s model, the average accuracy rate is improved by 3.8 percentage points. Conclusion: The improved algorithm has better detection effect, and realizes accurate identification and rapid positioning of military camouflage targets in complex environments.

Camouflaged Target Detection Based on Snapshot Multispectral Imaging

The spectral information contained in the hyperspectral images (HSI) distinguishes the intrinsic properties of a target from the background, which is widely used in remote sensing. However, the low imaging speed and high data redundancy caused by the high spectral resolution of imaging spectrometers limit their application in scenarios with the real-time requirement. In this work, we achieve the precise detection of camouflaged targets based on snapshot multispectral imaging technology and band selection methods in urban-related scenes. Specifically, the camouflaged target detection algorithm combines the constrained energy minimization (CEM) algorithm and the improved maximum between-class variance (OTSU) algorithm (t-OTSU), which is proposed to obtain the initial target detection results and adaptively segment the target region. Moreover, an object region extraction (ORE) algorithm is proposed to obtain a complete target contour that improves the target detection capability of multispectral images (MSI). The experimental results show that the proposed algorithm has the ability to detect different camouflaged targets by using only four bands. The detection accuracy is above 99%, and the false alarm rate is below 0.2%. The research achieves the effective detection of camouflaged targets and has the potential to provide a new means for real-time multispectral sensing in complex scenes.

Detection of conspicuous and cryptic food by common marmosets (Callithrix jacchus): An evaluation of the importance of color and shape cues

In primates, the advantage of trichromacy (i.e., color vision expressed by most humans) over dichromacy (i.e., color vision expressed by many colorblind humans) has been linked to the detection of yellowish/reddish targets against a background of mature green leaves. Nevertheless, mostly because of studies conducted in humans, we know that achromatic cues might also play an important role in object identification, particularly when camouflage is involved. For instance, dichromacy favors the detection of camouflaged targets by exploitation of shape cues. The present study sought to evaluate the relative importance of color and shape cues on the detection of food targets by female and male marmosets (Callithrix jacchus). Animals were observed with respect to their foraging behavior and the number of food targets captured. We confirmed that females are advantageous in detecting conspicuous food against a green background and revealed that females and males rely on shape cues to segregate cryptic food. Unexpectedly, males outperformed females in cryptic food foraging, while camouflage improved males’ (but not females’) performance. Here we show that dichromats could potentially benefit from a better segregation of green natural targets (e.g., immature fruits, green insects, and gum trees) when viewed against a green dappled background.

Training detection of camouflaged targets in natural scenes: Backgrounds and targets both matter

As target-background similarity increases, search performance declines, but this pattern can be attenuated with training. In the present study we (1) characterized training and transfer effects in visual search for camouflaged targets in naturalistic scenes, (2) evaluated whether transfer effects are preserved 3 months after training, (3) tested the suitability of the perceptual learning hypothesis (i.e., using learned scene statistics to aid camouflaged target detection) for explaining camouflage search improvements over training, and (4) provide guidance for camouflage detection training in practice. Participants were assigned to one of three training groups: adaptive camouflage (difficulty varied by performance), massed camouflage (difficulty increased over time), or an active control (no camouflage), and trained over 14 sessions. Additional sessions measured transfer (immediately post training) and retention of training benefits (10 days and 3 months post training). Both the adaptive and massed training groups showed improved camouflaged target detection up to 3 months following training, relative to the control. These benefits were observed only with backgrounds and targets that were similar to those experienced during training and are broadly consistent with the perceptual learning hypothesis. In practice, training interventions should utilize stimuli similar to the operational environment in which detection is expected to occur.

Airborne hyperspectral detection of underwater camouflaged targets and the effect of target shape and seafloor on image quality

The goal of the present work is to increase the detectivity of hyperspectral imaging systems, deployed on airborne marine search and rescue platforms (SAR), also the increase of the probability for camouflaged target detection and recognition through optimization of image quality. Hence, water column spectral characteristics will be simulated, bringing into consideration the effect of both air layer and plankton layer. This experimental simulation is based on hyperspectral imaging of camouflaged dummy targets of different shapes in a special aquarium designed for this purpose, where an argon laser source was used as multi-spectral line target illuminator and three different bottom backgrounds were tested.

Modeling apparent camouflage-pattern color using segment-weighted spectra

ABSTRACTCamouflage patterns for military applications, typically upon base materials such as dyed fabrics, consist of highly detailed camouflage patternings that are characterized by combined refectance spectra. The complexity of these camouflage patterns establishes a need for modeling camouflage-pattern reflectance for pattern evaluation as a function of distance. A metric for pattern evaluation is the apparent-camouflage-pattern reflectance spectrum, which is the total reflectance due to all contributions from component segments, within a wavelength range of interest, for light reflected from sufficiently large fabric samples (≥1m2), as a function of standoff distance. This follows in that camouflage patterns tend to lose contributions to the total reflectance from component segments, having less coverage, with increasing standoff distance. Eventually, with increasing distance, reflectance of pattern segments having more coverage combine to produce the “apparent spectrum” of the camouflage pattern at far field. The physical characteristics of camouflage-pattern reflectance spectra are based on far-field and diffuse scattering properties of electromagnetic waves. Accordingly, a modeling approach can be developed to simulate camouflage-pattern spectra using diffuse-reflectance theory, which is based on decomposition of camouflage-pattern reflectance with respect to component segments of camouflage patterns. This paper presents a modeling approach and prototype simulations of camouflage-pattern reflectance within the visible range of wavelengths, which are relevant for evaluating camouflage fabrics with respect to realistic field conditions. A significant aspect of this modeling approach is that it can be extended for simulation of a wide range of factors influencing detection of camouflaged targets.

Detection and Identification of Camouflaged Targets using Hyperspectral and LiDAR data

<p class="p1">Camouflaging is the process of merging the target with the background with the aim to reduce/delay its detection. It can be done using different materials/methods such as camouflaging nets, paints. Defence applications often require quick detection of camouflaged targets in a dynamic battlefield scenario. Though HSI data may facilitate detection of camouflaged targets but detection gets complicated due to issues (spectral variability, dimensionality). This paper presents a framework for detection of camouflaged target that allows military analysts to coordinate and utilise the expert knowledge for resolving camouflaged targets using remotely sensed data. Desired camouflaged target (set of three chairs as a target under a camouflaging net) has been resolved in three steps: First, hyperspectral data processing helps to detect the locations of potential camouflaged targets. It narrows down the location of the potential camouflaged targets by detecting camouflaging net using Independent component analysis and spectral matching algorithms. Second, detection and identification have been performed using LiDAR point cloud classification and morphological analysis. HSI processing helps to discard the redundant majority of LiDAR point clouds and support detailed analysis of only the minute portion of the point cloud data the system deems relevant. This facilitates extraction of salient features of the potential camouflaged target. Lastly, the decisions obtained have been fused to infer the identity of the desired targets. The experimental results indicate that the proposed approach may be used to successfully resolve camouflaged target assuming some <em>a priori </em>knowledge about the morphology of targets likely to be present.<span class="Apple-converted-space"> </span></p>

Research on Camouflage Target Detection via Computational Analysis with Spectral Imaging

Camouflage target detection is one of most important techniques in a great number of applications such as remote sensing, security monitoring and industrial production. In this paper, high-resolution spectral imaging together with computational analysis on spectral data cube is adopted to solve camouflage target recognition problem. Spectral data cubes of certain experimental scene are collected by a self-developed visual-band imaging spectrometer, and spectral information divergence (SID) is adopted as difference descriptor to discriminate abnormal target. SIDs of the whole spectral region and several specific ranges are all measured to quantitatively evaluate the effort of band selection on camouflage detection. This is proven to be a low-cost and effective tool for camouflage target detection and can be further developed beyond visual band spectral imaging technique.

Calculation model of scattering depolarization for camouflaged target detection system

As a new physical model to identify the camouflaged targets in the complex environments, the main effect of the polarization measurement system is the scattering depolarization information of different measured parts. This paper had observed the multiple scattering theory of electromagnetic wave, and analyzed the mechanism of the relation between the depolarization and scattering path. The correctness and accuracy of the theoretical model had been verified by the Fresnel formula. In order to prove the practicability of this model, the experiments on two kinds of camouflage materials had been conducted at seven different angles. Research shows that, as a link between material physical characteristics and optical signal information, the model could accurately and effectively identify the moving camouflaged objects. Therefore, this method has a great application value, and the paper has very important significance on the development of tracking technology.

红外偏振成像系统高速处理模块设计

The high speed imaging processing module based on MWIR cooled 320256 detector, SDRAM memory and other function module circuit was designed for time-sharing type polarization imaging system. Processing module mainly included the driver board connected to detector, processing board with FPGA as its core, system power supply board. The algorithm of blind pixels compensation, nonuniformity correction, plateau histogram equalization and linear mapping were implemented, calibration parameters can be calculated online. Image processing module can realize the synchronization switch, integral time adjusted continuously, frame rate up to 200 fps, and output 320256 pixels high quality infrared image, meeting the requirement of the polarization imaging system to detect moving objects. Infrared polarization imaging experiments on plastic cups with groove were carried out, effective Stokes parameter images were extracted from the polarization images, and the significant polarization properties were observed. The processing module can be applied to the detection of space target, mine detection, maritime search and camouflage target detection.

Camouflage Detection Using MWIR Hyperspectral Images

Mid Wave Infra Red (MWIR) region of the electromagnetic spectrum is a key region that is exploited for long range infrared reconnaissance and surveillance applications. Detecting enemy targets and being undetectable is the prime requirement of the modern warfare. In the present study MWIR hyperspectral imaging has been exploited for detection of camouflaged targets in the scene. Detection methodology has been developed using unsupervised target detection algorithms (Reed Xiaoli, K-Means and ISODATA). Methodology has been successfully tested in extracting camouflaged targets from the background. Performance results have been compared. The proposed methodology may in future be applied in detection and identification of gases and minerals in the field.

Developing a similarity index for static camouflaged target detection

Measurement of camouflage performance is of fundamental importance for military stealth applications. The goal of camouflage assessment algorithms is to automatically assess the effectiveness of camouflage in agreement with human detection responses. We propose a new method for computational evaluation of camouflage effectiveness. We evaluate the performance of the new method and other existing algorithms in a comparative setting which utilised an extensive human visual experiment. The results show that the new method is correlated with the human target searching results with higher correlations than the existing algorithms.