Search Results (163)

Infrared small target detection is crucial for military surveillance and autonomous driving. However, complex scenes and weak signal characteristics make the identification of such targets particularly difficult. This study proposes YOLO-SSFA, an enhanced You Only Look Once version 11 (YOLOv11) model with three modules: Scale-Sequence Feature Fusion (SSFF), LiteShiftHead detection head, and Noise Suppression Network (NSN). SSFF improves multi-scale feature representation through adaptive fusion; LiteShiftHead boosts efficiency via sparse convolution and dynamic integration; and NSN enhances localization accuracy by focusing on key regions. Experiments on the HIT-UAV and FLIR datasets show mAP50 scores of 94.9% and 85%, respectively. These findings showcase YOLO-SSFA’s strong potential for real-time deployment in challenging infrared environments. Full article

Multispectral object detection faces challenges in effectively integrating complementary information from different modalities in complex environmental conditions. This paper proposes SDRFPT-Net (Spectral Dual-stream Recursive Fusion Perception Target Network), a novel architecture that integrates three key innovative modules: (1) the Spectral Hierarchical Perception Architecture (SHPA), which adopts a dual-stream separated structure with independently parameterized feature extraction paths for visible and infrared modalities; (2) the Spectral Recursive Fusion Module (SRFM), which combines hybrid attention mechanisms with recursive progressive fusion strategies to achieve deep feature interaction through parameter-sharing multi-round recursive processing; and (3) the Spectral Target Perception Enhancement Module (STPEM), which adaptively enhances target region representation and suppresses background interference. Extensive experiments on the VEDAI, FLIR-aligned, and LLVIP datasets demonstrate that SDRFPT-Net significantly outperforms state-of-the-art methods, with improvements of 2.5% in mAP50 and 5.4% in mAP50:95 on VEDAI, 11.5% in mAP50 on FLIR-aligned, and 9.5% in mAP50:95 on LLVIP. Ablation studies further validate the effectiveness of each proposed module. The proposed method provides an efficient and robust solution for multispectral object detection in remote sensing image interpretation, making it particularly suitable for all-weather monitoring applications from aerial and satellite platforms, as well as in intelligent surveillance and autonomous driving domains. Full article

Multispectral detection leverages visible and infrared imaging to improve detection performance in complex environments. However, conventional convolution-based fusion methods predominantly rely on local feature interactions, limiting their capacity to fully exploit cross-modal information and making them more susceptible to interference from complex backgrounds. To overcome these challenges, the YOLO-MEDet multispectral target detection model is proposed. Firstly, the YOLOv5 architecture is redesigned into a two-stream backbone network, incorporating a midway fusion strategy to integrate multimodal features from the C3 to C5 layers, thereby enhancing detection accuracy and robustness. Secondly, the Attention-Enhanced Feature Fusion Framework (AEFF) is introduced to optimize both cross-modal and intra-modal feature representations by employing an attention mechanism, effectively boosting model performance. Finally, the C3-PSA (C3 Pyramid Compressed Attention) module is integrated to reinforce multiscale spatial feature extraction and refine feature representation, ultimately improving detection accuracy while reducing false alarms and missed detections in complex scenarios. Extensive experiments on the FLIR, KAIST, and M3FD datasets, along with additional validation using SimuNPS simulations, confirm the superiority of YOLO-MEDet. The results indicate that the proposed model outperforms existing approaches across multiple evaluation metrics, providing an innovative solution for multispectral target detection. Full article

This pilot study evaluated the effectiveness of ice boots in cooling the metacarpal and coronary regions of a horse after training over 8 days (n = 8). Background: While cryotherapy is effective in managing exertional heat illness, stress fractures, and laminitis in horses, conventional methods are often costly and impractical. This pilot study assessed the efficacy of ice boots as an accessible alternative for cooling the metacarpal and coronary regions post-training. Methods: A four-year-old Warmblood mare was trained on a treadmill over 8 days. An ice boot was applied to the right thoracic limb for 20 min post-exercise. Thermographic images were captured at six time points from pre-training to 30 min post-cooling. Mean temperatures in four regions were analyzed using the FLIR Tools software v6.4.18039.1003. Results: Post-training, metacarpal temperatures increased by 10.97 ± 0.46 °C (p = 0.000). Ice boot application reduced metacarpal temperature by 20.27 ± 0.22 °C (p = 0.001) and coronary band temperature by 5.28 ± 0.30 °C (p = 0.001), with altered thermal patterns visible on the imaging. Treated regions returned to baseline within 30 min, while the control limb took 50 min. Conclusions: Ice boots provide rapid, effective cooling and distinctive thermal pattern changes, offering a practical cryotherapy alternative for equine limb care post-training. These initial findings lay the groundwork for larger studies involving more horses under varied conditions, which will be necessary to confirm the results and establish clear guidelines for the clinical use of ice boots in equine practice. Full article

The dominant low-light object detectors face the following spectral trilemma: (1) the loss of high-frequency structural details during denoising, (2) the amplification of low-frequency illumination distortion, and (3) cross-band interference in multi-scale features. To resolve these intertwined challenges, we present UMFNet—a frequency-guided detection framework that unifies adaptive frequency distillation with inter-band attention coordination. Our technical breakthroughs manifest through three key innovations: (1) a frequency-adaptive fusion (FAF) module employing learnable wavelet kernels (16–64 decomposition basis) with dynamic SNR-gated thresholding, achieving an 89.7% photon utilization rate in ≤1 lux conditions—2.4× higher than fixed-basis approaches; (2) a spatial-channel coordinated attention (SCCA) mechanism with dual-domain nonlinear gating that reduces high-frequency hallucination by 37% through parametric phase alignment (verified via gradient direction alignment coefficient ${\rho }_G$ = 0.93); (3) a spectral perception loss combining the frequency-weighted structural similarity index measure (SSIM) with gradient-aware focal modulation, enforcing physics-constrained feature recovery. Extensive validation demonstrates UMFNet’s leadership: 73.1% mAP@50 on EXDark (+6.4% over YOLOv8 baseline), 58.7% on DarkFace (+3.1% over GLARE), and 40.2% on thermal FLIR ADAS (+9.7% improvement). This work pioneers a new paradigm for precision-critical vision systems in photon-starved environments. Full article

Multimodal pedestrian detection has garnered significant attention due to its potential applications in complex scenarios. The complementarity characteristics between infrared and visible modalities can enhance detection performance. However, the design of cross-modal fusion mechanisms and the in-depth exploration of inter-modal complementarity still pose challenges. To address this, we propose TCCDNet, a novel network integrating cross-modal complementarity. Specifically, the efficient multi-scale attention C2f (EMAC) is designed for the backbone, which combines the C2f structure with an efficient multi-scale attention mechanism to achieve feature weighting and fusion, thereby enhancing the model’s feature extraction capacity. Subsequently, the cross-modal complementarity (CMC) module is proposed, which enhances feature discriminability and object localization accuracy through a synergistic mechanism combining channel attention and spatial attention. Additionally, a deep semantic fusion module (DSFM) based on a cross-attention mechanism is incorporated to achieve deep semantic feature fusion. The experimental results demonstrate that TCCDNet achieves a MR⁻² of 7.87% on the KAIST dataset, representing a 3.83% reduction compared to YOLOv8. For the other two multimodal pedestrian detection datasets, TCCDNet attains mAP₅₀ scores of 83.8% for FLIR ADAS and 97.3% for LLVIP, outperforming the baseline by 3.6% and 1.9% respectively. These results fully validate the effectiveness and advancement of the proposed method. Full article

In open and dynamic environments, object detection is affected by rain, fog, snow, and complex lighting conditions, leading to decreased accuracy and posing a threat to driving safety. Infrared images can provide clear images at nighttime or in adverse weather conditions. Combined with the mature development of existing cross-modality object detection technologies, both of them offer support for addressing object detection issues in adverse weather scenarios. This paper establishes a novel dataset named Adverse Weather and Illumination Dataset (AWID) to simulate intricate real-world scenarios and proposes a cross-modal object detection algorithm for adverse weather scenarios in autonomous driving, named CME-YOLO, which is based on RGB and infrared images. It integrates the Cross-Perception Transformer Fusion algorithm, CPTFusion, and the Adaptive upsampling technique, AdSample, to enhance the extraction of detailed information and supplement effective information. CPTFusion fuses features from different modalities through multi-scale feature extraction and optimal fusion strategy computation. AdSample adaptively improves the utilization of key features and the quality of the resulting feature tensor. Experiments on two public datasets and AWID show that CME-YOLO performs optimally, with an mAP50 value on the FLIR dataset 6.8% higher than the state-of-the-art MPFT algorithm, verifying its excellent performance in autonomous driving object detection tasks. Full article

The objective of the study was to ascertain the potential of infrared thermal imaging (IRT) to detect the development of clinical mastitis at an early stage. The study was carried out on a one-site small pig farm with 80 breeding sows (crossbreed Landrace × Yorkshire) that had a history of high incidence of MMA. The udder-skin temperatures of the breeding sows were measured using a high-quality IRT camera (FLIR T650sc), in accordance with the IRT measurement protocol (including calibration and corrections), with a measurement uncertainty of $\pm 0.5$$°\mathrm{C}$. This study improves upon previous research by refining the measurement protocol and selecting more appropriate statistical methods to better analyze time-dependent data. To minimise the impact of measurement uncertainty, we propose the use of time-dependent trends (simple moving averages) caused by farrowing and lactation in place of the original IRT time series data. The findings indicate that a significant disparity between the maximum and minimum daily udder-skin temperature values, along with a pronounced maximal median of daily udder-skin IRT temperature values in sows during the early post-farrowing period, is associated with an elevated prevalence of multiglandular mastitis. Consequently, the utilisation of IRT imaging of the udder skin has the potential to facilitate the detection or prediction of multiglandular mastitis in sows. However, identifying uniglandular mastitis in individual mammary glands is more complex and may rely on time-dependent statistical trends derived from IRT imaging. Full article

Background/Objectives: The pathophysiological mechanisms of temperature asymmetry differ between patients with warm and cold subtypes of Complex Regional Pain Syndrome (CRPS). Consequently, the response to lumbar sympathetic blocks (LSBs) and the resulting temperature improvement may vary between these two subtypes. We aimed to evaluate whether there was a significant difference in temperature elevation following sympathetic blocks in warm versus cold subtypes of CRPS. Methods: We calculated the temperature difference by analyzing forward-looking infrared (FLIR) thermal camera images of the affected extremity at pre-block and 5-min post-block time points. The primary outcome measure was that the mean temperature increase following LSB would be higher in the cold CRPS group than in the warm CRPS group. The secondary outcome measure was that the mean temperature elevation following the sympathetic block in the cold CRPS subtype would be at least 50% higher than in the warm CRPS subtype. Results: The study assessed warm and cold CRPS subtypes by analyzing temperature profiles from 90 lumbar sympathetic blocks performed on 34 patients. The temperature change in the affected extremity following LSB varied widely, with the highest increase observed in one patient at 10.99 °C. The cold CRPS patients demonstrated a higher mean temperature increase at the 5 min time point following LSB, averaging 3.37 °C in initial cases and 2.67 °C across all cases. In comparison, warm CRPS patients had lower mean increases of 0.58 °C in initial cases and 1.23 °C across all cases. Notably, the mean temperature rise in the cold CRPS group exceeded that of the warm CRPS group by more than 50%, meeting the secondary outcome goal. Conclusions: Our results indicated that patients with the cold subtype of CRPS tend to experience greater temperature improvements compared to those with the warm subtype after undergoing a sympathetic block. Therefore, our findings suggest that the criteria for determining the success of a sympathetic block should be revised to account for the cold and warm subtypes of CRPS. Full article

Object tracking in thermal video is challenging due to noise, blur, and low contrast. We present TVEMamba, a Mamba-based enhancement framework with near-linear complexity that improves tracking in these conditions. Our approach uses a State Space 2D (SS2D) module integrated with Convolutional Neural Networks (CNNs) to filter, sharpen, and highlight important details. Key components include (i) a denoising module to reduce background noise and enhance image clarity, (ii) an optical flow attention module to handle complex motion and reduce blur, and (iii) entropy-based labeling to create a fully labeled thermal dataset for training and evaluation. TVEMamba outperforms existing methods (DCRGC, RLBHE, IE-CGAN, BBCNN) across multiple datasets (BIRDSAI, FLIR, CAMEL, Autonomous Vehicles, Solar Panels) and achieves higher scores on standard quality metrics (EME, BDIM, DMTE, MDIMTE, LGTA). Extensive tests, including ablation studies and convergence analysis, confirm its robustness. Real-world examples, such as tracking humans, animals, and moving objects for self-driving vehicles and remote sensing, demonstrate the practical value of TVEMamba. Full article

To date, there is little publicly available scientific data on unidentified aerial phenomena (UAP) whose properties and kinematics purportedly reside outside the performance envelope of known phenomena. To address this deficiency, the Galileo Project is designing, building, and commissioning a multi-modal, multi-spectral ground-based observatory to continuously monitor the sky and collect data for UAP studies via a rigorous long-term aerial census of all aerial phenomena, including natural and human-made. One of the key instruments is an all-sky infrared camera array using eight uncooled long-wave-infrared FLIR Boson 640 cameras. In addition to performing intrinsic and thermal calibrations, we implement a novel extrinsic calibration method using airplane positions from Automatic Dependent Surveillance–Broadcast (ADS-B) data that we collect synchronously on site. Using a You Only Look Once (YOLO) machine learning model for object detection and the Simple Online and Realtime Tracking (SORT) algorithm for trajectory reconstruction, we establish a first baseline for the performance of the system over five months of field operation. Using an automatically generated real-world dataset derived from ADS-B data, a dataset of synthetic 3D trajectories, and a hand-labeled real-world dataset, we find an acceptance rate (fraction of in-range airplanes passing through the effective field of view of at least one camera that are recorded) of 41% for ADS-B-equipped aircraft, and a mean frame-by-frame aircraft detection efficiency (fraction of recorded airplanes in individual frames which are successfully detected) of 36%. The detection efficiency is heavily dependent on weather conditions, range, and aircraft size. Approximately 500,000 trajectories of various aerial objects are reconstructed from this five-month commissioning period. These trajectories are analyzed with a toy outlier search focused on the large sinuosity of apparent 2D reconstructed object trajectories. About 16% of the trajectories are flagged as outliers and manually examined in the IR images. From these ∼80,000 outliers and 144 trajectories remain ambiguous, which are likely mundane objects but cannot be further elucidated at this stage of development without information about distance and kinematics or other sensor modalities. We demonstrate the application of a likelihood-based statistical test to evaluate the significance of this toy outlier analysis. Our observed count of ambiguous outliers combined with systematic uncertainties yields an upper limit of 18,271 outliers for the five-month interval at a 95% confidence level. This test is applicable to all of our future outlier searches. Full article

Background: several authors have documented variations in local temperature in both horses and dogs presenting acute intervertebral disc extrusion (IVDE) along the entire spinal column. However, none have demonstrated distinct temperature differences between healthy animals and those with IVDE. A retrospective study was conducted to assess the efficacy of thermography at evaluating local temperature and thermal patterns in healthy dogs as well in those with IVDE across the T11–L3 area. Methods: the study included 20 healthy dogs and 32 dogs with IVDE. For both groups of dogs, the thoracolumbar region was trimmed and, subsequently, scanned using the Flir E50 thermography device. The Flir Tool software was used to analyze three designated areas (Bx1, Bx2, Bx3) within the thoracolumbar region by comparing the average temperature of the minimum, maximum, and mean temperature recordings between the two groups. Results: the thermal pattern and the local temperature of the thoracolumbar area present differences between healthy dogs and those with IVDE. Conclusions: we recommend thermographic scanning of the thoracolumbar area to find differences in local temperature between healthy dogs and those with intervertebral disc extrusion. Further investigations are required to differentiate between disc extrusion that exhibits lateralization to the right or left. Full article

Shrinkage, a heat-induced process, reorganizes collagen fibers, thereby reducing wound surface area. This technique, commonly applied in surgeries like periareolar mastopexy and skin grafting, is well-established. Despite its widespread use, modern imaging has recently enabled detailed observation of shrinkage’s effects on tissue temperature and oxygenation. The aim of this study is to investigate the effects of shrinkage on histological level, temperature, and tissue oxygenation. Skin flaps were collected, marked, and subjected to shrinkage in vitro, with wound dimensions recorded before and after shrinkage. Biopsy samples were analyzed histologically. In our clinical set up, Snapshot NIR^® and FLIR thermography were used to assess tissue oxygenation and temperature changes before and after shrinkage. Shrinkage significantly reduced wound area by almost 47% ± 8.5%, with a 16.5% ± 6.0% reduction in length and a 36.5% ± 7.7% reduction in width. Tissue temperature rose by an average of 38.3 °C post-shrinkage, reaching approximately 65 °C. A slight decrease in oxygen saturation was observed following shrinkage. Histological analyses reveal collagen fiber denaturation and structural reorganization. Thermal shrinkage is an effective method for reducing wound size and tension, demonstrating potential for facilitating larger full-thickness skin grafts. Although minor decreases in oxygenation were observed, shrinkage may enhance wound healing by reducing tension at wound edges. Further studies are needed to quantify its impact on functional and cosmetic outcomes. Full article

This study aimed to investigate the incidence of subclinical mastitis (SCM), the implicated pathogens, and their impact on milk quality in dairy sheep in Greece. Furthermore, we preliminarily evaluated infrared thermography and the application of AI tools for the early, non-invasive diagnosis of relevant cases. In total, 660 milk samples and over 2000 infrared thermography images were obtained from 330 phenotypically healthy ewes. Microbiological investigations, a somatic cell count (SCC), and milk chemical analyses were performed. Infrared images were analyzed using the FLIR Research Studio software (version 3.0.1). The You Only Look Once version 8 (YOLOv8) algorithm was employed for the automatic detection of the udder’s region of interest. A total of 157 mammary glands with SCM were identified in 122/330 ewes (37.0%). The most prevalent pathogen was staphylococci (136/160, 86.6%). Considerable resistance was detected to tetracycline (29.7%), ampicillin (28.6%), and sulfamethoxazole–trimethoprim (23.6%). SCM correlated with high total mesophilic count (TMC) values and decreased milk fat, lactose, and protein content. A statistically significant variation (p < 0.001) was identified in the unilateral SCM cases by evaluating the mean temperatures of the udder region between the teats in the thermal images. Finally, the YOLOv8 algorithm was employed for the automatic detection of the udder’s region of interest (ROI), achieving 84% accuracy in defining the ROI in this preliminary evaluation. This demonstrates the potential of infrared thermography combined with AI tools for the diagnosis of ovine SCM. Nonetheless, more extensive sampling is essential to optimize this diagnostic approach. Full article

As universities strive to create sustainable and comfortable learning environments, understanding the factors that influence student well-being is crucial for promoting good health and well-being (SDG 3) and fostering sustainable communities (SDG 11). This study, conducted at a female campus in the UAE, investigates the impact of various external factors on students’ psychological perceptions. Specifically, it examines how abaya color, landscape settings, and time of day affect body fatigue, eye fatigue, and thermal discomfort, providing valuable insights for campus planning and design. Using GrADS and an FLIR thermal camera, this research analyzed temperature, humidity, and surface temperatures. The Kruskal–Wallis test and Don Bonferroni pairwise comparisons were employed to assess the impact of conditions on psychological perceptions. The results indicate that abaya color insignificantly affected perceptions in summer, but light brown was preferred in spring. Landscape sites influenced eye fatigue and skin dryness in summer, favoring shaded areas. The time of day affected body heat, skin dryness, and thermal discomfort, with greater discomfort in summer afternoons. These findings offer valuable insights for campus planning, particularly in hot summer months, promoting students’ psychological well-being (SDG 3) and sustainable campus communities (SDG 11). Full article