Search Results (13)

Infrared cameras play an important role in various fields, such as research and development, and inspection and surveillance; the higher the performance of an infrared camera, the more important the specifications are. However, in the field of long-range surveillance, it is difficult to strictly grasp the performance of infrared cameras because they are affected by atmospheric conditions. The performance of DRI (Detection, Recognition, Identification), one of the specifications used in infrared cameras for surveillance, is merely a simulated value from each company. In this verification, we used a MWIR long focal infrared camera to verify whether there was any difference between the simulation values in a real environment and the actual usage conditions. Full article

Existing frameworks for classifying the fidelity for object detection tasks do not consider false positive likelihood and object uniqueness. Inspired by the Detection, Recognition, Identification (DRI) framework proposed by Johnson 1958, we propose a new modified framework that defines three categories as visible anomaly, identifiable anomaly, and unique identifiable anomaly (AIU) as determined by human interpretation of imagery or geophysical data. These categories are designed to better capture false positive rates and emphasize the importance of identifying unique versus non-unique targets compared to the DRI Index. We then analyze visual, thermal, and multispectral UAV imagery collected over a seeded minefield and apply the AIU Index for the landmine detection use-case. We find that RGB imagery provided the most value per pixel, achieving a 100% identifiable anomaly rate at 125 pixels on target, and the highest unique target classification compared to thermal and multispectral imaging for the detection and identification of surface landmines and UXO. We also investigate how the AIU Index can be applied to machine learning for the selection of training data and informing the required action to take after object detection bounding boxes are predicted. Overall, the anomaly, identifiable anomaly, and unique identifiable anomaly index prescribes essential context for false-positive-sensitive or resolution-poor object detection tasks with applications in modality comparison, machine learning, and remote sensing data acquisition. Full article

Kelp, often referred to as a “sea vegetable”, holds substantial economic significance. Currently, the drying process for kelp in China primarily relies on outdoor sun-drying methods. Detecting kelp in the field presents challenges arising from issues such as overlapping and obstruction. To address these challenges, this study introduces a lightweight model, K-YOLOv5, specifically designed for the precise detection of sun-dried kelp. YOLOv5-n serves as the base model, with several enhancements implemented in this study: the addition of a detection head incorporating an upsampling layer and a convolution module to improve the recognition of small objects; the integration of an enhanced I-CBAM attention mechanism, focusing on key features to enhance the detection accuracy; the replacement of the CBS module in the neck network with GSConv to reduce the computational burden and accelerate the inference speed; and the optimization of the IoU algorithm to improve the identification of overlapping kelp. Utilizing drone-captured images of sun-dried kelp, a dataset comprising 2190 images is curated. Validation on this self-constructed dataset indicates that the improved K-YOLOv5 model significantly enhances the detection accuracy, achieving 88% precision and 78.4% recall. These values represent 6.8% and 8.6% improvements over the original model, respectively, meeting the requirements for the real-time recognition of sun-dried kelp. Full article

This paper analyses the efficiency of thermal infrared (TIR) systems during night search operations under specific weather conditions, with a focus on determining the maximum operating altitude of the drone. The drone used in the research (DJI Matrice 210 V2) is equipped with a thermal camera, in a scenario involving maritime search and rescue (SAR) operation, i.e., person detection at sea with or without a survival suit. By capturing images from different altitudes and measuring key atmospheric and maritime parameters, essential data are obtained for defining optimal DRI parameters (detection, recognition, and identification) within the existing on-site meteorological conditions. This research contributes to more accurate life-saving procedures, underlining the importance of uncrewed aerial vehicle (UAV) technology for maritime SAR. It is expected that the presented model will improve operational readiness for SAR operations in areas with similar climatic profiles. The research results indicate the need to conduct similar research in different climatic conditions to improve the application of the TIR system in maritime SAR operations. Full article

The space–air–ground integrated network (SAGIN) represents a pivotal component within the realm of next-generation mobile communication technologies, owing to its established reliability and adaptable coverage capabilities. Central to the advancement of SAGIN is propagation channel research due to its critical role in aiding network system design and resource deployment. Nevertheless, real-world propagation channel research faces challenges in data collection, deployment, and testing. Consequently, this paper designs a comprehensive simulation framework tailored to facilitate SAGIN propagation channel research. The framework integrates the open source QuaDRiGa platform and the self-developed satellite channel simulation platform to simulate communication channels across diverse scenarios, and also integrates data processing, intelligent identification, algorithm optimization modules in a modular way to process the simulated data. We also provide a case study of scenario identification, in which typical channel features are extracted based on channel impulse response (CIR) data, and recognition models based on different artificial intelligence algorithms are constructed and compared. Full article

Objective: Walnuts have rich nutritional value and are favored by the majority of consumers. As walnuts are shelled nuts, they are prone to suffer from defects such as mildew during storage. The fullness and mildew of the fruit impose effects on the quality of the walnuts. Therefore, it is of great economic significance to carry out a study on the rapid, non-destructive detection of walnut quality. Methods: Terahertz spectroscopy, with wavelengths between infrared and electromagnetic waves, has unique detection advantages. In this paper, the rapid and nondestructive detection of walnut mildew and fullness based on terahertz spectroscopy is carried out using the emerging terahertz transmission spectroscopy imaging technology. First, the normal walnuts and mildewed walnuts are identified and analyzed. At the same time, the image processing is carried out on the physical samples with different kernel sizes to calculate the fullness of the walnut kernels. The THz image of the walnuts is collected to extract the spectral information in different regions of interest. Four kinds of time domain signals in different regions of interest are extracted, and three qualitative discrimination models are established, including the support vector machine (SVM), random forest (RF), and k-nearest neighbor (KNN) algorithms. In addition, in order to realize the visual expression of walnut fullness, the terahertz images of the walnut are segmented with a binarization threshold, and the walnut fullness is calculated by the proportion of the shell and kernel pixels. Results: In the frequency domain signal, the amplitude intensity from high to low is the mildew sample, walnut kernel, and walnut shell, and the distinction between walnut kernel, shell samples, and mildew samples is high. The overall identification accuracy of the aforementioned three models is 90.83%, 97.38%, and 97.87%, respectively. Among them, KNN has the best qualitative discrimination effect. In a single category, the recognition accuracy of the model for the walnut kernel, walnut shell, mildew sample, and reference group (background) reaches 94%, 100%, 97.43%, and 100%, respectively. The terahertz transmission images of the five categories of walnut samples with different kernel sizes are processed to visualize the detection of kernel fullness inside walnuts, and the errors are less than 5% compared to the actual fullness of walnuts. Conclusion: This study illustrates that terahertz spectroscopy detection can achieve the detection of walnut mildew, and terahertz imaging technology can realize the visual expression and fullness calculation of walnut kernels. Terahertz spectroscopy and imaging provides a non-destructive detection method for walnut quality, which can provide a reference for the quality detection of other dried nuts with shells, thus having significant practical value. Full article

The classification of maritime boats and ship targets using optical satellite imagery is a challenging subject. This research introduces a unique and rich ship dataset named Very High-Resolution Ships (VHRShips) from Google Earth images, which includes diverse ship types, different ship sizes, several inshore locations, and different data acquisition conditions to improve the scalability of ship detection and mapping applications. In addition, we proposed a deep learning-based multi-stage approach for ship type classification from very high resolution satellite images to evaluate the performance of the VHRShips dataset. Our “Hierarchical Design (HieD)” approach is an end-to-end structure that allows the optimization of the Detection, Localization, Recognition, and Identification (DLRI) stages, independently. We focused on sixteen parent ship classes for the DLR stages, and specifically considered eight child classes of the navy parent class at the identification stage. We used the Xception network in the DRI stages and implemented YOLOv4 for the localization stage. Individual optimization of each stage resulted in F1 scores of 99.17%, 94.20%, 84.08%, and 82.13% for detection, recognition, localization, and identification, respectively. The end-to-end implementation of our proposed approach resulted in F1 scores of 99.17%, 93.43%, 74.00%, and 57.05% for the same order. In comparison, end-to-end YOLOv4 yielded F1-scores of 99.17%, 86.59%, 68.87%, and 56.28% for DLRI, respectively. We achieved higher performance with HieD than YOLOv4 for localization, recognition, and identification stages, indicating the usability of the VHRShips dataset in different detection and classification models. In addition, the proposed method and dataset can be used as a benchmark for further studies to apply deep learning on large-scale geodata to boost GeoAI applications in the maritime domain. Full article

The fast differentiation and classification of herb samples are complicated processes due to the presence of many various chemical compounds. Traditionally, separation techniques have been employed for the identification and quantification of compounds present in different plant matrices, but they are tedious, time-consuming and destructive. Thus, a non-targeted approach would be specifically advantageous for this purpose. In the present study, spectroscopy in the visible and near-infrared range and pattern recognition techniques, including the principal component analysis (PCA), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA), super k-nearest neighbor (SKNN) and support vector machine (SVM) techniques, were applied to develop classification models that enabled the discrimination of various commercial dried herbs, including mint, linden, nettle, sage and chamomile. The classification error rates in the validation data were below 10% for all the classification methods, except for SKNN. The results obtained confirm that spectroscopy and pattern recognition methods constitute a good non-destructive tool for the rapid identification of herb species that can be used in routine quality control by the pharmaceutical industry, as well as herbal suppliers, to avoid mislabeling. Full article

The recognition and management of life-threatening hemorrhage in the polytrauma patient poses several challenges to prehospital rescue personnel and hospital providers. First, identification of acute blood loss and the magnitude of lost volume after torso injury may not be readily apparent in the field. Because of the expression of highly effective physiological mechanisms that compensate for a sudden decrease in circulatory volume, a polytrauma patient with a significant blood loss may appear normal during examination by first responders. Consequently, for every polytrauma victim with a significant mechanism of injury we assume substantial blood loss has occurred and life-threatening hemorrhage is progressing until we can prove the contrary. Second, a decision to begin damage control resuscitation (DCR), a costly, highly complex, and potentially dangerous intervention must often be reached with little time and without sufficient clinical information about the intended recipient. Whether to begin DCR in the prehospital phase remains controversial. Furthermore, DCR executed imperfectly has the potential to worsen serious derangements including acidosis, coagulopathy, and profound homeostatic imbalances that DCR is designed to correct. Additionally, transfusion of large amounts of homologous blood during DCR potentially disrupts immune and inflammatory systems, which may induce severe systemic autoinflammatory disease in the aftermath of DCR. Third, controversy remains over the composition of components that are transfused during DCR. For practical reasons, unmatched liquid plasma or freeze-dried plasma is transfused now more commonly than ABO-matched fresh frozen plasma. Low-titer type O whole blood may prove safer than red cell components, although maintaining an inventory of whole blood for possible massive transfusion during DCR creates significant challenges for blood banks. Lastly, as the primary principle of management of life-threatening hemorrhage is surgical or angiographic control of bleeding, DCR must not eclipse these definitive interventions. Full article

Today’s long-range infrared cameras (LRIRC) are used in many systems for the protection of critical infrastructure or national borders. The basic technical parameters of such systems are noise equivalent temperature difference (NETD); minimum resolvable temperature difference (MRTD); and the range of detection, recognition and identification of selected objects (DRI). This paper presents a methodology of the theoretical determination of these parameters on the basis of technical data of LRIRCs. The first part of the paper presents the methods used for the determination of the detection, recognition and identification ranges based on the well-known Johnson criteria. The theoretical backgrounds for both approaches are given, and the laboratory test stand is described together with a brief description of the methodology adopted for the measurements of the selected necessary characteristics of a tested observation system. The measurements were performed in the Accredited Testing Laboratory of the Institute of Optoelectronics of the Military University of Technology (AL IOE MUT), whose activity is based on the ISO/IEC 17025 standard. The measurement results are presented, and the calculated ranges for a selected set of IR cameras are given, obtained on the basis of the Johnson criteria. In the final part of the article, the obtained measurement results are presented together with an analysis of the measurement uncertainty for 10 LRIRCs. The obtained measurement results were compared to the technical parameters presented by the manufacturers. Full article

Gentianae Radix et Rhizome (Longdan in Chinese, GRR) in Chinese Pharmacopoeia is derived from the dried roots and rhizomes of Gentiana scabra and G. rigescens, that have long been used for heat-clearing and damp-drying in the medicinal history of China. However, the characterization of the chemical components of two species and the screening of chemical markers still remain unsolved. In current research, the identification and characterization of chemical components of two species was performed using ultra-high-performance liquid chromatography (UHPLC) coupled with linear ion trap-Orbitrap (LTQ-Orbitrap) mass spectrometry. Subsequently, the chemical markers of two species were screened based on metabolomics and multivariate statistical analysis. In total, 87 chemical constituents were characterized in G. scabra (65 chemical constituents) and G. rigescens (51 chemical constituents), with 29 common chemical constituents being discovered. Thereafter, 11 differential characteristic components which could differentiate the two species were designated with orthogonal partial least squares discriminant analysis (OPLS-DA) and random forest (RF) iterative modeling. Finally, seven characteristic components identified as (+)-syringaresinol, lutonarin, trifloroside, 4-O-β-d-glu-trifloroside, 4″-O-β-d-glucopyranosy1-6′-O-(4-O-β-d-glucaffeoyl)-linearroside, macrophylloside a and scabraside were selected as the chemical markers for the recognition of two Gentiana species. It was implied that the results could distinguish the GRR derived from different botanical sources, and also be beneficial in the rational clinical use of GRR. Full article

The study concentrates on researching possibilities of using computer image analysis and neural modeling in order to assess selected quality discriminants of spray-dried chokeberry powder. The aim of the paper is the quality identification of chokeberry powders on account of their highest dying power, the highest bioactivity, as well as technologically satisfying looseness of the powder. The article presents neural models with vision techniques backed up by devices such as digital cameras, as well as an electron microscope. The reduction in size of input variables with PCA has an influence on improving the processes of learning data sets, thus increasing the effectiveness of identifying chokeberry fruit powders included in digital pictures, which is shown in the results of the conducted research. The effectiveness of image recognition is presented by classifying abilities, as well as low Root Mean Square Error (RMSE), for which the best results are achieved with a typology of network type Multi-Layer Perceptron (MLP). The selected networks type MLP are characterized by the highest degree of classification at 0.99 and RMSE at 0.11 at most at the same time. Full article

Oregano (Origanum vulgare L.) is a flowering plant that belongs to the mint family (Lamiaceae). It is used as a culinary herb and is often commercialized as a fine powder or a mixture of small fragments of dried leaves, which makes morphological recognition difficult. Like other commercial preparations of drugs and spices, the contamination of oregano mixtures with vegetable matter of lower quality, or the use of generic misleading names, are frequent and stress the need to develop a molecular traceability system to easily, quickly, and cheaply unveil these scams. The DNA-based analytical approach known as cpDNA barcoding is particularly suited for fraud identification in crop plant species (fresh products and food derivatives), and it represents a promising traceability tool as an alternative or complement to traditional detection methods. In the present study, we used a combined approach based on both qualitative and quantitative cpDNA barcoding with end-point and real-time polymerase chain reaction (PCR) analyses to assess the type and degree of contamination in commercial batches of common oregano. In a preliminary qualitative screening, we amplified, cloned, and sequenced a number of universal trnH-psbA- and trnL-barcoded regions, to identify the main contaminants in the samples under investigation. On the basis of these findings, we then developed and validated a species-specific and sequence-targeted method of testing for the quantitative assessment of contaminants, using trnL gene intron assays. Surprisingly, the results obtained in our case study indicated an almost total absence of O. vulgare in the commercial batches analyzed, but a high presence of group I contaminants (Satureja pilosa Velen.), and a moderate presence of group II contaminants (Cistus lanidifer L./Cistus albidus). Full article