Search Results (726)

In response to problems such as large target scale variations, strong background noise, and blurred features leading by low contrast in infrared target detection in near space environments, this paper proposes an efficient detection model, YOLO-MARS, which is based on YOLOv8. The model introduces a Space-to-Depth (SPD) convolution module into the backbone section, which retains the detailed features of smaller targets by downsampling operations without information loss, alleviating the loss of the target feature caused by traditional downsampling. The Grouped Multi-Head Self-Attention (GMHSA) module is added after the backbone’s SPPF module to improve cross-scale global modeling capabilities for target area feature responses while suppressing complex thermal noise background interference. In addition, a Light Adaptive Spatial Feature Fusion (LASFF) detector head is designed to mitigate the scale sensitivity issue of infrared targets (especially smaller targets) in the feature pyramid. It uses a shared weighting mechanism to achieve adaptive fusion of multi-scale features, reducing computational complexity while improving target localization and classification accuracy. To address the extreme scarcity of near space data, we integrated 284 near space images with the HIT-UAV dataset through physical equivalence analysis (atmospheric transmittance, contrast, and signal-to-noise ratio) to construct the NS-HIT dataset. The experimental results show that ${mAP}_{@0.5}$ increases by 5.4% and the number of parameters only increase 10% using YOLO-MARS compared to YOLOv8. YOLO-MARS improves the accuracy of detection significantly while considering the requirements of model complexity, which provides an efficient and reliable solution for applications in near space infrared target detection. Full article

Blood glucose monitoring is crucial for the daily management of diabetic patients. In this study, we developed a differential absorbance and photoplethysmography (PPG)-based non-invasive blood glucose measurement system (NIBGMS) using visible–near-infrared (Vis-NIR) light. Three light-emitting diodes (LEDs) (625 nm, 850 nm, and 940 nm) and three photodetectors (PDs) with different source–detector separation distances were used to detect the differential absorbance of tissues at different depths and PPG signals of the index finger. A spatiotemporal multimodal fused long short-term memory (STMF-LSTM) model was developed to improve the prediction accuracy of blood glucose levels by multimodal fusion of optical spatial information (differential absorbance and PPG signals) and glucose temporal information. The validity of the NIBGMS was preliminarily verified using multilayer perceptron (MLP), support vector regression (SVR), random forest regression (RFR), and extreme gradient boosting (XG Boost) models on datasets collected from 15 non-diabetic subjects and 3 type-2 diabetic subjects, with a total of 805 samples. Additionally, a continuous dataset consisting 272 samples from four non-diabetic subjects was used to validate the developed STMF-LSTM model. The results demonstrate that the STMF-LSTM model indicated improved prediction performance with a root mean square error (RMSE) of 0.811 mmol/L and a percentage of 100% for Parkes error grid analysis (EGA) Zone A and B in 8-fold cross validation. Therefore, the developed NIBGMS and STMF-LSTM model show potential in practical non-invasive blood glucose monitoring. Full article

Spectroscopic observations of Earth-like exoplanets and ultra-faint galaxies–top scientific priorities for the coming decades–involve measuring broadband signals at rates of only a few photons per square meter per hour. This imposes exceptional requirements on the detector performance, necessitating dark currents below 1 e⁻/pixel/kilo second, read noise under 1 e⁻/pixel/frame, and the ability to handle large-format arrays–capabilities that are not yet met by most existing infrared detectors. In addition, spaceborne LiDAR systems require photodetectors with exceptional sensitivity, compact size, low power consumption, and multi-channel capability to facilitate long-range range finding, topographic mapping, and active spectroscopy without increasing the instrument burden. MCT Avalanche photodiodes arrays offer high internal gain, pixelation, and photon-counting performance across SW to MW wavelengths needed for multi-beam and multi-wavelength measurements, marking them as a critical enabling technology for next-generation planetary and Earth science LiDAR missions. This work reports the latest progress in developing Hg_1−xCd_xTe linear-mode e-APDs at premier industrial research institutions, including relevant experimental data, simulations and major project planning. Related studies are summarized to demonstrate the practical and iterative approach for device fabrication, which have a transformative impact on the evolution of this discipline. Full article

HgCdSe has recently been proposed as a potential alternative material to HgCdTe for fabricating high-performance infrared detectors. This work presents a study on the growth of high-crystalline-quality HgCdSe materials on GaSb (211)B substrates via molecular beam epitaxy and demonstration of the first prototype HgCdSe-based mid-wave infrared detectors. By optimizing the MBE growth parameters, and especially the thermal cleaning process of the GaSb substrate surface prior to epitaxial growth, high-quality HgCdSe material was achieved with a record XRD full width at half maximum of ~65 arcsec. At a temperature of 77 K, the mid-wave infrared HgCdSe n-type material demonstrated a minority carrier lifetime of ~1.19 µs, background electron concentration of ~2.2 × 10¹⁷ cm⁻³, and electron mobility of ~1.6 × 10⁴ cm²/Vs. The fabricated mid-wave infrared HgCdSe photoconductor presented a cut-off wavelength of 4.2 µm, a peak responsivity of ~40 V/W, and a peak detectivity of ~1.2 × 10⁹ cmHz^1/2/W at 77 K. Due to the relatively high background electron concentration, the detector performance is lower than that of state-of-the-art low-doped HgCdTe counterparts. However, these preliminary results indicate the great potential of HgCdSe materials for achieving next-generation IR detectors on large-area substrates with features of lower cost and larger array format size. Full article

Multi-modal object detection that fuses RGB (Red-Green-Blue) and infrared (IR) data has emerged as an effective approach for addressing challenging visual conditions such as low illumination, occlusion, and adverse weather. However, most existing multi-modal detectors prioritize accuracy while neglecting computational efficiency, making them unsuitable for deployment on resource-constrained edge devices. To address this limitation, we propose PONet, a lightweight and efficient multi-modal vehicle detection network tailored for real-time edge inference. PONet incorporates Polarized Self-Attention to improve feature adaptability and representation with minimal computational overhead. In addition, a novel fusion module is introduced to effectively integrate RGB and IR modalities while preserving efficiency. Experimental results on the VEDAI dataset demonstrate that PONet achieves a competitive detection accuracy of 82.2% mAP@0.5 while sustaining a throughput of 34 FPS on the OrangePi AIpro 20T device. With only 3.76 M parameters and 10.2 GFLOPs (Giga Floating Point Operations), PONet offers a practical solution for edge-oriented remote sensing applications requiring a balance between detection precision and computational cost. Full article

Bird-dropping fouling and hotspot anomalies remain the most prevalent and detrimental defects in utility-scale photovoltaic (PV) plants; their co-occurrence on a single module markedly curbs energy yield and accelerates irreversible cell degradation. However, markedly disparate visual–thermal signatures of the two phenomena impede high-fidelity concurrent detection in existing robotic inspection systems, while stringent onboard compute budgets also preclude the adoption of bulky detectors. To resolve this accuracy–efficiency trade-off for dual-defect detection, we present YOLOv8-SG, a lightweight yet powerful framework engineered for mobile PV inspectors. First, a rigorously curated multi-modal dataset—RGB for stains and long-wave infrared for hotspots—is assembled to enforce robust cross-domain representation learning. Second, the HSV color space is leveraged to disentangle chromatic and luminance cues, thereby stabilizing appearance variations across sensors. Third, a single-head self-attention (SHSA) block is embedded in the backbone to harvest long-range dependencies at negligible parameter cost, while a global context (GC) module is grafted onto the detection head to amplify fine-grained semantic cues. Finally, an auxiliary bounding box refinement term is appended to the loss to hasten convergence and tighten localization. Extensive field experiments demonstrate that YOLOv8-SG attains 86.8% mAP@0.5, surpassing the vanilla YOLOv8 by 2.7 pp while trimming 12.6% of parameters (18.8 MB). Grad-CAM saliency maps corroborate that the model’s attention consistently coincides with defect regions, underscoring its interpretability. The proposed method, therefore, furnishes PV operators with a practical low-latency solution for concurrent bird-dropping and hotspot surveillance. Full article

Narcotics trafficking is a fundamental part of organized crime, posing significant and evolving challenges for forensic investigations. Addressing these challenges requires rapid, precise, and scientifically validated analytical methods for reliable identification of illicit substances. Over the past five years, forensic drug testing has advanced considerably, improving detection of traditional drugs—such as tetrahydrocannabinol, cocaine, heroin, amphetamine-type stimulants, and lysergic acid diethylamide—as well as emerging new psychoactive substances (NPS), including synthetic cannabinoids (e.g., 5F-MDMB-PICA), cathinones (e.g., α-PVP), potent opioids (e.g., carfentanil), designer psychedelics (e.g., 25I-NBOMe), benzodiazepines (e.g., flualprazolam), and dissociatives (e.g., 3-HO-PCP). Current technologies include colorimetric assays, ambient ionization mass spectrometry, and chromatographic methods coupled with various detectors, all enhancing accuracy and precision. Vibrational spectroscopy techniques, like Raman and Fourier transform infrared spectroscopy, have become essential for non-destructive identification. Additionally, new sensors with disposable electrodes and miniaturized transducers allow ultrasensitive on-site detection of drugs and metabolites. Advanced chemometric algorithms extract maximum information from complex data, enabling faster and more reliable identifications. An important emerging trend is the adoption of green analytical methods—including direct analysis, solvent-free extraction, miniaturized instruments, and eco-friendly chromatographic processes—that reduce environmental impact without sacrificing performance. This review provides a comprehensive overview of innovations over the last five years in forensic drug analysis based on the ScienceDirect database and highlights technological trends shaping the future of forensic toxicology. Full article

In this paper, the first demonstration of a highly strained In_0.8Ga_0.2As/In_0.2Ga_0.8Sb type-II superlattice structure grown on InAs substrates by molecular beam epitaxy (MBE) for long-wavelength infrared detection was reported. Novel methodologies were developed to optimize the As and Sb flux growth conditions. The quality of the epitaxial layer was characterized using multiple analytical techniques, including differential interference contrast microscopy, atomic force microscopy, high-resolution X-ray diffraction, and high-resolution transmission electron microscopy. The high-quality superlattice structure, with a total thickness of 1.5 μm, exhibited exceptional surface morphology with a root-mean-square roughness of 0.141 nm over a 5 × 5 μm² area. Single-element devices with PIN architecture were fabricated and characterized. At 77 K, these devices demonstrated a 50% cutoff wavelength of approximately 12.1 μm. The long-wavelength infrared PIN devices exhibited promising performance metrics, including a dark current density of 7.96 × 10⁻² A/cm² at −50 mV bias and a high peak responsivity of 4.90 A/W under zero bias conditions, both measured at 77 K. Furthermore, the devices achieved a high peak quantum efficiency of 65% and a specific detectivity (D*) of 2.74 × 10¹⁰ cm·Hz^1/2/W at the peak responsivity wavelength of 10.7 µm. These results demonstrate the viability of this material system for long-wavelength infrared detection applications. Full article

The palm-vein recognition system has garnered attention as a biometric technology due to its resilience to external environmental factors, protection of personal privacy, and low risk of external exposure. However, with recent advancements in deep learning-based generative models for image synthesis, the quality and sophistication of fake images have improved, leading to an increased security threat from counterfeit images. In particular, palm-vein images acquired through near-infrared illumination exhibit low resolution and blurred characteristics, making it even more challenging to detect fake images. Furthermore, spoof detection specifically targeting palm-vein images has not been studied in detail. To address these challenges, this study proposes the Fourier-gated feature-fusion network (FGFNet) as a novel spoof detector for palm-vein recognition systems. The proposed network integrates masked fast Fourier transform, a map-based gated feature fusion block, and a fast Fourier convolution (FFC) attention block with global contrastive loss to effectively detect distortion patterns caused by generative models. These components enable the efficient extraction of critical information required to determine the authenticity of palm-vein images. In addition, fractal dimension estimation (FDE) was employed for two purposes in this study. In the spoof attack procedure, FDE was used to evaluate how closely the generated fake images approximate the structural complexity of real palm-vein images, confirming that the generative model produced highly realistic spoof samples. In the spoof detection procedure, the FDE results further demonstrated that the proposed FGFNet effectively distinguishes between real and fake images, validating its capability to capture subtle structural differences induced by generative manipulation. To evaluate the spoof detection performance of FGFNet, experiments were conducted using real palm-vein images from two publicly available palm-vein datasets—VERA Spoofing PalmVein (VERA dataset) and PLUSVein-contactless (PLUS dataset)—as well as fake palm-vein images generated based on these datasets using a cycle-consistent generative adversarial network. The results showed that, based on the average classification error rate, FGFNet achieved 0.3% and 0.3% on the VERA and PLUS datasets, respectively, demonstrating superior performance compared to existing state-of-the-art spoof detection methods. Full article

In computer vision, the performance of detectors trained under optimal lighting conditions is significantly impaired when applied to infrared domains due to the scarcity of labeled infrared target domain data and the inherent degradation in infrared image quality. Progress in cross-domain pedestrian re-identification is hindered by the lack of labeled infrared image data. To address the degradation of pedestrian recognition in infrared environments, we propose a framework for zero-shot infrared domain adaptation. This integrated approach is designed to mitigate the challenges of pedestrian recognition in infrared domains while enabling zero-shot domain adaptation. Specifically, an advanced reflectance representation learning module and an exchange–re-decomposition–coherence process are employed to learn illumination invariance and to enhance the model’s effectiveness, respectively. Additionally, the CLIP (Contrastive Language–Image Pretraining) image encoder and DINO (Distillation with No Labels) are fused for feature extraction, improving model performance under infrared conditions and enhancing its generalization capability. To further improve model performance, we introduce the Non-Local Attention (NLA) module, the Instance-based Weighted Part Attention (IWPA) module, and the Multi-head Self-Attention module. The NLA module captures global feature dependencies, particularly long-range feature relationships, effectively mitigating issues such as blurred or missing image information in feature degradation scenarios. The IWPA module focuses on localized regions to enhance model accuracy in complex backgrounds and unevenly lit scenes. Meanwhile, the Multi-head Self-Attention module captures long-range dependencies between cross-modal features, further strengthening environmental understanding and scene modeling. The key innovation of this work lies in the skillful combination and application of existing technologies to new domains, overcoming the challenges posed by vision in infrared environments. Experimental results on the SYSU-MM01 dataset show that, under the single-shot setting, Rank-1 Accuracy (Rank-1) andmean Average Precision (mAP) values of 37.97% and 37.25%, respectively, were achieved, while in the multi-shot setting, values of 34.96% and 34.14% were attained. Full article

Laser ranging technology holds a key position in the military, aerospace, and industrial fields due to its high precision and non-contact measurement characteristics. As a core component, the performance of the photon detector directly determines the ranging accuracy and range. This paper systematically reviews the technological development of photonic detectors for laser ranging, with a focus on analyzing the working principles and performance differences of traditional photodiodes [PN (P-N junction photodiode), PIN (P-intrinsic-N photodiode), and APD (avalanche photodiode)] (such as the high-frequency response characteristics of PIN and the internal gain mechanism of APD), as well as their applications in short- and medium-range scenarios. Additionally, this paper discusses the unique advantages of special structures such as transmitting junction-type and Schottky-type detectors in applications like ultraviolet light detection. This article focuses on photon counting technology, reviewing the technological evolution of photomultiplier tubes (PMTs), single-photon avalanche diodes (SPADs), and superconducting nanowire single-photon detectors (SNSPDs). PMT achieves single-photon detection based on the external photoelectric effect but is limited by volume and anti-interference capability. SPAD achieves sub-decimeter accuracy in 100 km lidars through Geiger mode avalanche doubling, but it faces challenges in dark counting and temperature control. SNSPD, relying on the characteristics of superconducting materials, achieves a detection efficiency of 95% and a dark count rate of less than 1 cps in the 1550 nm band. It has been successfully applied in cutting-edge fields such as 3000 km satellite ranging (with an accuracy of 8 mm) and has broken through the near-infrared bottleneck. This study compares the differences among various detectors in core indicators such as ranging error and spectral response, and looks forward to the future technical paths aimed at improving the resolution of photon numbers and expanding the full-spectrum detection capabilities. It points out that the new generation of detectors represented by SNSPD, through material and process innovations, is promoting laser ranging to leap towards longer distances, higher precision, and wider spectral bands. It has significant application potential in fields such as space debris monitoring. Full article

With the dynamic development of imaging technologies and increasing demands in various industrial fields, neural networks are playing a crucial role in advanced design, monitoring, and analysis techniques. This review article presents the latest research advancements in neural network-based imaging, thermal, infrared, and X-ray technologies from 2005 to 2024. It focuses on two main research categories: ‘Technology’ and ‘Application’. The ‘Technology’ category includes neural network-enhanced image sensors, thermal imaging, infrared detectors, and X-ray technologies, while the ‘Application’ category is divided into image processing, robotics and design, object recognition, medical imaging, and security systems. In image processing, significant progress has been made in classification, segmentation, digital image storage, and information classification using neural networks. Robotics and design have seen advancements in mobile robots, navigation, and machine design through neural network integration. Object recognition technologies include neural network-based object detection, face recognition, and pattern recognition. Medical imaging has benefited from innovations in diagnosis, imaging techniques, and disease detection using neural networks. Security systems have improved in terms of monitoring and efficiency through neural network applications. This review aims to provide a comprehensive understanding of the current state and future directions of neural network-based imaging, thermal, infrared, and X-ray technologies. Full article

Detecting oriented electrical equipment plays a fundamental role in enabling intelligent defect diagnosis in power systems. However, existing oriented object detection methods each have their own limitations, making it challenging to achieve robust and accurate detection under varying conditions. This work proposes a model ensemble approach that leverages the complementary strengths of two representative detectors—Oriented R-CNN and S²A-Net—to enhance detection performance. Recognizing that discrepancies in confidence score distributions may negatively impact ensemble results, this work first designs a calibration method to align the confidence levels of predictions from each model. Following calibration, a soft non-maximum suppression (Soft-NMS) strategy is employed to fuse the outputs, effectively refining the final detections by jointly considering spatial overlap and the calibrated confidence scores. The proposed method is evaluated on an infrared image dataset for electric power equipment detection. Experimental results demonstrate that our approach not only improves the performance of each individual model by 1.95 mean Average Precision (mAP) but also outperforms other state-of-the-art methods. Full article

A superconducting transition-edge sensor (TES) as a microcalorimeter detects incoming photons by measuring heat converted from photon energy. With high resolving power and low noise levels, a TES is sensitive to single photons and able to count photons within a wide spectral band from X-ray to near-infrared. We have developed a TES detector aiming at soft X-ray spectroscopy applications. In this work, the performance of this detector is characterized. It is shown that the energy resolution of this detector is about 1.8 eV for 1.5 keV photons. The good resolution is also kept in visible range, enabling photon-number resolving for 405 nm photons. Full article

Infrared image sensors are crucial across various industries. However, with technological advancements, the growing scale of infrared image sensors has made the impact of transient dose rate effects increasingly significant. It is necessary to conduct relevant radiation effect studies to provide the theoretical and data basis for future radiation-hardened design. This study explores the response of large-area N-wells in the readout circuit of infrared detectors to transient dose rate effects. The TCAD simulation results indicate that the expansive N-well area in the merged-design pixel units generates significant current pulses when exposed to gamma-ray irradiation. Specifically, at dose rates of 3 × 10¹¹ rad/s, 5 × 10¹¹ rad/s, 7 × 10¹¹ rad/s, and 9 × 10¹¹ rad/s, the pulse currents measured are 39 nA, 64 nA, 89 nA, and 119 nA, respectively. Due to the spatial constraints of the 55 nm merged design, the close proximity of the GND to the N-well creates a high potential barrier near the N-well, obstructing the path between the GND and the substrate, which results in the pulse current exhibiting a stepped-like characteristic. Full article