Background subtraction for night videos.
Ontology highlight
ABSTRACT:
SUBMITTER: Pan H
PROVIDER: S-EPMC8205302 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
Background subtraction for night videos.
Pan Hongpeng H Zhu Guofeng G Peng Chengbin C Xiao Qing Q
PeerJ. Computer science 20210610
Motion analysis is important in video surveillance systems and background subtraction is useful for moving object detection in such systems. However, most of the existing background subtraction methods do not work well for surveillance systems in the evening because objects are usually dark and reflected light is usually strong. To resolve these issues, we propose a framework that utilizes a Weber contrast descriptor, a texture feature extractor, and a light detection unit, to extract the featur ...[more]
Similar Datasets
Project description:BACKGROUND:One important preprocessing step in the analysis of microarray data is background subtraction. In high-density oligonucleotide arrays this is recognized as a crucial step for the global performance of the data analysis from raw intensities to expression values. RESULTS:We propose here an algorithm for background estimation based on a model in which the cost function is quadratic in a set of fitting parameters such that minimization can be performed through linear algebra. The model incorporates two effects: 1) Correlated intensities between neighboring features in the chip and 2) sequence-dependent affinities for non-specific hybridization fitted by an extended nearest-neighbor model. CONCLUSION:The algorithm has been tested on 360 GeneChips from publicly available data of recent expression experiments. The algorithm is fast and accurate. Strong correlations between the fitted values for different experiments as well as between the free-energy parameters and their counterparts in aqueous solution indicate that the model captures a significant part of the underlying physical chemistry.
| S-EPMC2785812 | biostudies-literature
Project description:Catheter Digital Subtraction Angiography (DSA) is markedly degraded by all voluntary, respiratory, or cardiac motion artifact that occurs during the exam acquisition. Prior efforts directed toward improving DSA images with machine learning have focused on extracting vessels from individual, isolated 2D angiographic frames. In this work, we introduce improved 2D + t deep learning models that leverage the rich temporal information in angiographic timeseries. A total of 516 cerebral angiograms were collected with 8784 individual series. We utilized feature-based computer vision algorithms to separate the database into "motionless" and "motion-degraded" subsets. Motion measured from the "motion degraded" category was then used to create a realistic, but synthetic, motion-augmented dataset suitable for training 2D U-Net, 3D U-Net, SegResNet, and UNETR models. Quantitative results on a hold-out test set demonstrate that the 3D U-Net outperforms competing 2D U-Net architectures, with substantially reduced motion artifacts when compared to DSA. In comparison to single-frame 2D U-Net, the 3D U-Net utilizing 16 input frames achieves a reduced RMSE (35.77 ± 15.02 vs 23.14 ± 9.56, p < 0.0001; mean ± std dev) and an improved Multi-Scale SSIM (0.86 ± 0.08 vs 0.93 ± 0.05, p < 0.0001). The 3D U-Net also performs favorably in comparison to alternative convolutional and transformer-based architectures (U-Net RMSE 23.20 ± 7.55 vs SegResNet 23.99 ± 7.81, p < 0.0001, and UNETR 25.42 ± 7.79, p < 0.0001, mean ± std dev). These results demonstrate that multi-frame temporal information can boost performance of motion-resistant Background Subtraction Deep Learning algorithms, and we have presented a neuroangiography domain-specific synthetic affine motion augmentation pipeline that can be utilized to generate suitable datasets for supervised training of 3D (2d + t) architectures.
| S-EPMC10980661 | biostudies-literature
Project description:The application of small-angle X-ray scattering (SAXS) for high-throughput characterization of biological macromolecules in solution is limited by radiation damage. By cryocooling samples, radiation damage and required sample volumes can be reduced by orders of magnitude. However, the challenges of reproducibly creating the identically sized vitrified samples necessary for conventional background subtraction limit the widespread adoption of this method. Fixed path length silicon sample holders for cryoSAXS have been microfabricated to address these challenges. They have low background scattering and X-ray absorption, require only 640 nl of sample, and allow reproducible sample cooling. Data collected in the sample holders from a nominal illuminated sample volume of 2.5 nl are reproducible down to q ≃ 0.02 Å-1, agree with previous cryoSAXS work and are of sufficient quality for reconstructions that match measured crystal structures. These sample holders thus allow faster, more routine cryoSAXS data collection. Additional development is required to reduce sample fracturing and improve data quality at low q.
| S-EPMC4453169 | biostudies-literature
Project description:BackgroundCa2+ plays an important role in many physiological processes and an accurate study of these signals is important. In modern fluorescence microscopy, a charge-coupled device (CCD) camera is widely deployed for calcium imaging. The ratiometric method is used for the fluorescence dye Fura-2 and Grynkiewitz's formula (Grynkiewicz et al., 1985) is commonly used to convert fluorescence to free Ca2+ concentration ([Ca2+]). But the need to subtract the background signal can lead to a big error in ratiometric calcium measurements. When the error due to background subtraction occurs, the fluorescence ratio of 340 nm divided by 380 nm lights may be twice as large as the actual value. Under conditions when the excitation intensity is not adjusted to ensure the same throughput of the objective lens for ultraviolet dye illumination, the indicator does not gradually bleach out for channels with a wavelength of 340 nm and 380 nm light, which lead to an additional error in determining the concentration of Ca2+.New methodHere we present a new approach for calculating [Ca2+] from the ratiometric fluorescence of Fura-2 dye imaged by a CCD camera. It is designed to optimize [Ca2+] measurements with photobleaching correction without background subtraction error. A mathematical method is also provided for removing the existing underestimated value of fluorescence at an excitation wavelength of 340 nm and compensating for the bleaching rate for both channels with wavelengths of 340 nm and 380 nm using a power function.ResultsIn cultured neurons, the calculations of the free Ca2+ concentration during Ca2+ transients estimated by the old and new methods, determine it to the same extent. This comparison was made under conditions without errors through background subtraction. If there is this error, the old method calculates [Ca2+] with a much higher, rather than the actual value.ConclusionsWe present a modified Grynkiewitz's formula for calculation [Ca2+] for ratiometric dye, such as Fura-2 imaged by a CCD camera, with photobleaching correction without background subtraction error.
| S-EPMC7322130 | biostudies-literature
Project description:Regular monitoring of wild animal populations through the collection of behavioral and demographic data is critical for the conservation of endangered species. Identifying individual Asian elephants (Elephas maximus), for example, can contribute to our understanding of their social dynamics and foraging behavior, as well as to human-elephant conflict mitigation strategies that account for the behavior of specific individuals involved in the conflict. Wild elephants can be distinguished using a variety of different morphological traits-e.g., variations in ear and tail morphology, body scars and tumors, and tusk presence, shape, and length-with previous studies identifying elephants via direct observation or photographs taken from vehicles. When elephants live in dense forests like in Thailand, remote sensing photography can be a productive approach to capturing anatomical and behavioral information about local elephant populations. While camera trapping has been used previously to identify elephants, here we present a detailed methodology for systematic, experimenter differentiation of individual elephants using data captured from remote sensing video camera traps. In this study, we used day and night video footage collected remotely in the Salakpra Wildlife Sanctuary in Thailand and identified 24 morphological characteristics that can be used to recognize individual elephants. A total of 34 camera traps were installed within the sanctuary as well as crop fields along its periphery, and 107 Asian elephants were identified: 72 adults, 11 sub-adults, 20 juveniles, and four infants. We predicted that camera traps would provide enough information such that classified morphological traits would aid in reliably identifying the adult individuals with a low probability of misidentification. The results indicated that there were low probabilities of misidentification between adult elephants in the population using camera traps, similar to probabilities obtained by other researchers using handheld cameras. This study suggests that the use of day and night video camera trapping can be an important tool for the long-term monitoring of wild Asian elephant behavior, especially in habitats where direct observations may be difficult.
| S-EPMC10064994 | biostudies-literature
Project description:Background and purposeAccurate pretreatment diagnosis and assessment of spinal vascular malformations using spinal CTA are crucial for patient prognosis, but the postprocessing reconstruction may not be able to fully depict the lesions due to the complexity inherent in spinal anatomy. Our purpose was to explore the application value of the spinal subtraction and bone background fusion CTA (SSBBF-CTA) technique in precisely depicting and localizing spinal vascular malformation lesions.Materials and methodsIn this retrospective study, patients (between November 2017 and November 2022) with symptoms similar to those of spinal vascular malformations were divided into diseased (group A) and nondiseased (group B) groups. All patients underwent spinal CTA using Siemens dual-source CT. Multiplanar reconstruction; routine bone subtraction, and SSBBF-CTA images were obtained using the snygo.via and ADW4.6 postprocessing reconstruction workstations. Multiple observers researched the following 3 aspects: 1) preliminary screening capability using original images with multiplanar reconstruction CTA, 2) the accuracy and stability of the SSBBF-CTA postprocessing technique, and 3) diagnostic evaluation of spinal vascular malformations using the 3 types of postprocessing images. Diagnostic performance was analyzed using receiver operating characteristic analysis, while reader or image differences were analyzed using the Wilcoxon signed-rank test or the Kruskal-Wallis rank sum test.ResultsForty-nine patients (groups A and B: 22 and 27 patients; mean ages, 44.0 [SD, 14.3] years and 44.6 [SD,15.2] years; 13 and 16 men) were evaluated. Junior physicians showed lower diagnostic accuracy and sensitivity using multiplanar reconstruction CTA (85.7% and 77.3%) than senior physicians (93.9% and 90.9%, 98% and 95.5%). Short-term trained juniors achieved SSBBF-CTA image accuracy similar to that of experienced physicians (P > .05). In terms of the visualization and localization of spinal vascular malformation lesions (nidus/fistula, feeding artery, and drainage vein), both multiplanar reconstruction and SSBBF-CTA outperformed routine bone subtraction CTA (P = .000). Compared with multiplanar reconstruction, SSBBF-CTA allowed less experienced physicians to achieve superior diagnostic capabilities (comparable with those of experienced radiologists) more rapidly (P < .05).ConclusionsThe SSBBF-CTA technique exhibited excellent reproducibility and enabled accurate pretreatment diagnosis and assessment of spinal vascular malformations with high diagnostic efficiency, particularly for junior radiologists.
| S-EPMC11286120 | biostudies-literature
Project description:BackgroundTranscatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatment. Thus, we aimed to develop and validate an artificial intelligence system for real-time automatic prediction of TACE response in HCC patients based on digital subtraction angiography (DSA) videos via a deep learning approach.MethodsThis retrospective cohort study included a total of 605 patients with intermediate-stage HCC who received TACE as their initial therapy. A fully automated framework (i.e., DSA-Net) contained a U-net model for automatic tumor segmentation (Model 1) and a ResNet model for the prediction of treatment response to the first TACE (Model 2). The two models were trained in 360 patients, internally validated in 124 patients, and externally validated in 121 patients. Dice coefficient and receiver operating characteristic curves were used to evaluate the performance of Models 1 and 2, respectively.ResultsModel 1 yielded a Dice coefficient of 0.75 (95% confidence interval [CI]: 0.73-0.78) and 0.73 (95% CI: 0.71-0.75) for the internal validation and external validation cohorts, respectively. Integrating the DSA videos, segmentation results, and clinical variables (mainly demographics and liver function parameters), Model 2 predicted treatment response to first TACE with an accuracy of 78.2% (95%CI: 74.2-82.3), sensitivity of 77.6% (95%CI: 70.7-84.0), and specificity of 78.7% (95%CI: 72.9-84.1) for the internal validation cohort, and accuracy of 75.1% (95% CI: 73.1-81.7), sensitivity of 50.5% (95%CI: 40.0-61.5), and specificity of 83.5% (95%CI: 79.2-87.7) for the external validation cohort. Kaplan-Meier curves showed a significant difference in progression-free survival between the responders and non-responders divided by Model 2 (p = 0.002).ConclusionsOur multi-task deep learning framework provided a real-time effective approach for decoding DSA videos and can offer clinical-decision support for TACE treatment in intermediate-stage HCC patients in real-world settings.
| S-EPMC9101835 | biostudies-literature
Project description:Historically, antibody reactivity to pathogens and vaccine antigens has been evaluated using serological measurements of antigen-specific antibodies. However, it is difficult to evaluate all antibodies that contribute to various functions in a single assay, such as the measurement of the neutralizing antibody titer. Bulk antibody repertoire analysis using next-generation sequencing is a comprehensive method for analyzing the overall antibody response; however, it is unreliable for estimating antigen-specific antibodies due to individual variation. To address this issue, we propose a method to subtract the background signal from the repertoire of data of interest. In this study, we analyzed changes in antibody diversity and inferred the heavy-chain complementarity-determining region 3 (CDRH3) sequences of antibody clones that were selected upon influenza virus infection in a mouse model using bulk repertoire analysis. A decrease in the diversity of the antibody repertoire was observed upon viral infection, along with an increase in neutralizing antibody titers. Using kernel density estimation of sequences in a high-dimensional sequence space with background signal subtraction, we identified several clusters of CDRH3 sequences induced upon influenza virus infection. Most of these repertoires were detected more frequently in infected mice than in uninfected control mice, suggesting that infection-specific antibody sequences can be extracted using this method. Such an accurate extraction of antigen- or infection-specific repertoire information will be a useful tool for vaccine evaluation in the future.ImportanceAs specific interactions between antigens and cell-surface antibodies trigger the proliferation of B-cell clones, the frequency of each antibody sequence in the samples reflects the size of each clonal population. Nevertheless, it is extremely difficult to extract antigen-specific antibody sequences from the comprehensive bulk antibody sequences obtained from blood samples due to repertoire bias influenced by exposure to dietary antigens and other infectious agents. This issue can be addressed by subtracting the background noise from the post-immunization or post-infection repertoire data. In the present study, we propose a method to quantify repertoire data from comprehensive repertoire data. This method allowed subtraction of the background repertoire, resulting in more accurate extraction of expanded antibody repertoires upon influenza virus infection. This accurate extraction of antigen- or infection-specific repertoire information is a useful tool for vaccine evaluation.
| S-EPMC10949447 | biostudies-literature
Project description:Water dynamics as reflected by the spectral diffusion of the water hydroxyl stretch were measured in w(0) = 2 (1.7 nm diameter) Aerosol-OT (AOT)/water reverse micelles in carbon tetrachloride and in isooctane solvents using ultrafast 2D IR vibrational echo spectroscopy. Orientational relaxation and population relaxation are observed for w(0) = 2, 4, and 7.5 in both solvents using IR pump-probe measurements. It is found that the pump-probe observables are sensitive to w(0), but not to the solvent. However, initial analysis of the vibrational echo data from the water nanopool in the reverse micelles in the isooctane solvent seems to yield different dynamics than the CCl(4) system in spite of the fact that the spectra, vibrational lifetimes, and orientational relaxation are the same in the two systems. It is found that there are beat patterns in the interferograms with isooctane as the solvent. The beats are observed from a signal generated by the AOT/isooctane system even when there is no water in the system. A beat subtraction data processing procedure does a reasonable job of removing the distortions in the isooctane data, showing that the reverse micelle dynamics are the same within experimental error regardless of whether isooctane or carbon tetrachloride is used as the organic phase. Two time scales are observed in the vibrational echo data, ~1 and ~10 ps. The slower component contains a significant amount of the total inhomogeneous broadening. Physical arguments indicate that there is a much slower component of spectral diffusion that is too slow to observe within the experimental window, which is limited by the OD stretch vibrational lifetime.
| S-EPMC3055695 | biostudies-other
Project description:Background:Essential tremor (ET) can be profoundly disabling in severe cases; however, such cases may not often be encountered by general practitioners, primary care physicians, or general neurologists, leading to misdiagnosis. Phenomenology shown:Severe kinetic, postural, and intention tremors in patients with ET. Educational value:To provide visual examples of severe, long-standing ET for general practitioners, primary care clinicians, and general neurologists.
| S-EPMC6691604 | biostudies-other