- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Background-Foreground Interaction for Moving Object Detection in Dynamic Scenes
摘要： Both background subtraction and foreground extraction are the typical methods used to detect moving objects in video sequences. In order to flexibly represent the long-term state and the short-term changes in a scene, a new weighted Kernel Density Estimation (KDE) is proposed to build the long-term background (LTB) and short-term foreground (STF) models, respectively. A novel mechanism is proposed to support the interaction between the LTB and STF models. The interaction includes the weight transmission and the fusion between the LTB and STF models. In the weight transmission process between the LTB and STF models, the sample weight of one model (either the background model or the foreground model) in the current time step is updated under the guidance of the decision of the other model in the previous time step. In the background-foreground fusion stage, a unified Bayesian framework is proposed to detect objects and the detection result in any time step is given by the logarithm of the posterior ratio between the background and foreground models. This interactive approach proposed in this paper improves the robustness of moving object detection, preventing deadlocks and degeneration in the models. The experimental results demonstrate that our proposed approach outperforms previous ones.
关键词： Weighted kernel density estimation,Background-foreground interaction,Moving object detection,Dynamic scene
更新于2025-09-23 15:23:52
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Hybrid Parametric - Nonparametric Target Detector for Hyperspectral Images
摘要： In this work a novel target detector is proposed that is nonparametric in terms of conditional probability density function (pdf) estimation and parametric with respect to the target strength of the additive model it relies upon. The variable bandwidth kernel density estimator is employed to estimate the conditional pdfs, whereas the target strength is estimated via the Maximum Likelihood approach. Experimental results over real hyperspectral data show that the detector succeeds in detecting target objects embedded in a complex background and in providing reasonable estimates for the target strengths.
关键词： nonparametric approach,kernel density estimation,additive model,target detection,Hyperspectral imaging
更新于2025-09-23 15:23:52
-
Estimation of Uncertainty in the Lateral Vibration Attenuation of a Beam with Piezo-Elastic Supports by Neural Networks
摘要： Quantification of uncertainty in technical systems is often based on surrogate models of corresponding simulation models. Usually, the underlying simulation model does not describe the reality perfectly, and consequently the surrogate model will be imperfect. In this article we propose an improved surrogate model of the vibration attenuation of a beam with shunted piezoelectric transducers. Therefore, experimentally observed and simulated variations in the vibration attenuation are combined in the model estimation process, by using multi–layer feedforward neural networks. Based on this improved surrogate model, we construct a density estimate of the maximal amplitude in the vibration attenuation. The density estimate is used to analyze the uncertainty in the vibration attenuation, resulting from manufacturing variations.
关键词： Density estimation,neural network,uncertainty quantification,imperfect model,surrogate model
更新于2025-09-23 15:22:29
-
A general approach to evaluate the ensemble cross-correlation response for PIV using Kernel density estimation
摘要： Cross-correlation in particle image velocimetry is well known to behave as a non-linear operator, depending heavily on the distribution of tracer images and image quality. While analytical descriptors of the correlation response have so far been dealt with for simplistic flow cases, in this work a methodology is presented based on Kernel density estimation to retrieve the inherent correlation response to any deterministic flow field. The new approach bypasses the need for Monte-Carlo simulations and its inherent sensitivity to parameter settings make it a more efficient alternative to analyse filtering of the underlying velocity field due to image cross-correlation. The derivation of the underlying equations is presented and a numerical assessment corroborates the suitability of the approach to mimic ensemble correlation.
关键词： Ensemble correlation,Particle image velocimetry,Flow field filtering,Kernel density estimation,Cross-correlation
更新于2025-09-23 15:21:01
-
Minimisation of variations in locating an acupuncture point using a laser-device
摘要： Background: Identifying accurate acupoint is an essential component in clinical practice. A laser device can provide us with a visual guide for locating acupoints by dividing the space equally between two landmarks on the body. In this study, we compared the accuracy between the naked-eye and a laser device to locate an acupoint. Methods: Twenty-two participants were asked to mark acupoint PC5 on a male volunteer’s arm using two different methods: without a laser device (naked-eye) and with a laser device. The distributions of the acupoints were estimated by the kernel density estimation methods. Results: The overall distribution of acupoints was less when the laser device method was used, compared to the naked-eye method. We found signi?cant differences in the longitudinal axis between the two methods, but no signi?cant differences in the horizontal axis. Conclusions: Our ?ndings suggest that direct measurement of the acupoint location using a laser device can reduce variations in locating points. Laser-assisted tools will help practitioners locate the acupoints more accurately and should be considered as standard practice, especially in acupuncture research and education.
关键词： Measurement,Kernel density estimation,Location,Acupoint
更新于2025-09-16 10:30:52
-
Study of Short-Term Photovoltaic Power Forecast Based on Error Calibration under Typical Climate Categories
摘要： With the increasing permeability of photovoltaic (PV) power production, the uncertainties and randomness of PV power have played a critical role in the operation and dispatch of the power grid and ampli?ed the abandon rate of PV power. Consequently, the accuracy of PV power forecast urgently needs to be improved. Based on the amplitude and ?uctuation characteristics of the PV power forecast error, a short-term PV output forecast method that considers the error calibration is proposed. Firstly, typical climate categories are de?ned to classify the historical PV power data. On the one hand, due to the non-negligible diversity of error amplitudes in different categories, the probability density distributions of relative error (RE) are generated for each category. Distribution ?tting is performed to simulate probability density function (PDF) curves, and the RE samples are drawn from the ?tted curves to obtain the sampling values of the RE. On the other hand, based on the ?uctuation characteristic of RE, the recent RE data are utilized to analyze the error ?uctuation conditions of the forecast points so as to obtain the compensation values of the RE. The compensation values are adopted to sequence the sampling values by choosing the sampling values closest to the compensation ones to be the ?tted values of the RE. On this basis, the ?tted values of the RE are employed to correct the forecast values of PV power and improve the forecast accuracy.
关键词： Latin hypercube sampling,error calibration,photovoltaic power forecast,nonparametric kernel density estimation,typical climate categories
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Hyperspectral Target Detection Using Semi- and Non- Parametric Methods
摘要： In this paper we propose novel semi- and non- parametric detectors to be used with the additive target signal model within the general detection framework of the likelihood ratio test. In the semi-parametric detector, the Gaussian mixture model is employed to estimate a lower dimensional approximation of the background probability density function (PDF), whereas a multivariate kernel density estimator is employed to estimate the PDF in the multidimensional space within the non-parametric approach. Target detection experiments are carried out using the hyperspectral airborne “Viareggio 2013 trial” data set. The detectors are shown to provide promising results for the detection of the targets of interest deployed in the scene and outperform the well-known Adaptive Matched Filter detector.
关键词： target detection,non-parametric density estimation,Hyperspectral,semi-parametric density estimation
更新于2025-09-10 09:29:36
-
Nonparametric H Density Estimation Based on Regularized Nonlinear Inversion of the Lyman Alpha Emission in Planetary Atmospheres
摘要： Inversion of space-borne remote sensing measurements of the resonantly scattered solar Lyman alpha (121.6-nm) emission in planetary atmospheres is the most promising means of quantifying the H density in a vast volume of space near terrestrial planets. Owing to the highly nonlinear nature of the inverse problem and the lack of sufficient data constraints over the large volume of space where H atoms are present, previous inversion methods relied on physics-based parametric formulations of the H density distributions to guarantee solution uniqueness. Those physical formulations, such as the Chamberlain model, were developed with simple assumptions of the atmospheric conditions. The use of such formulations as constraints significantly limits the range of possible solutions, which might lead to large errors in the case when those assumptions are invalid. In this study, we demonstrate for the first time the feasibility of estimating the H density through regularized nonlinear inversion of the Ly-?? emission in an optically thick atmosphere, without using parametric formulations. Specifically, Occam’s inversion algorithm is used to demonstrate that the H density can be estimated in a large volume of space near the planet, with accuracy in different atmospheric regions depending on the observation scheme. Two distinctly different schemes are examined, including a low-Earth orbit and a geostationary orbit. Modeling results show that the low-Earth orbit is better for H density estimation in the thermosphere, while the high-altitude orbit is better for estimation in the exosphere. Our results could provide useful information for designing the observation schemes of future missions.
关键词： H density estimation,regularized nonlinear inversion,Occam’s inversion algorithm,planetary atmospheres,Lyman alpha emission
更新于2025-09-09 09:28:46