Unscented Transform: A Powerful Tool for Measurement Uncertainty Evaluation

Angrisani, L.; D’Apuzzo, Massimo; Moriello, Rosario Schiano Lo

doi:10.1109/tim.2006.873811

Cited by 33 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this reduces the accuracy of estimation result. A better choice is the usage of Kalman Filter based on the Unscented Transform (UT) [55]. Such filters propagate mean and covariance based on sigma points, like Unscented Kalman Filtef (UKF) [56] or Sigma Point Kalman Filter (SPKF) [57].…”

Section: The Iterated Sigma Point Kalman Filter Refinementmentioning

confidence: 99%

Robust Features and Accurate Inliers Detection Framework: Application to Stereo Ego-motion Estimation

2016

KSII TIIS

View full text Add to dashboard Cite

In this paper, an innovative robust feature detection and matching strategy for visual odometry based on stereo image sequence is proposed. First, a sparse multiscale 2D local invariant feature detection and description algorithm AKAZE is adopted to extract the interest points. A robust feature matching strategy is introduced to match AKAZE descriptors. In order to remove the outliers which are mismatched features or on dynamic objects, an improved random sample consensus outlier rejection scheme is presented. Thus the proposed method can be applied to dynamic environment. Then, geometric constraints are incorporated into the motion estimation without time-consuming 3-dimensional scene reconstruction. Last, an iterated sigma point Kalman Filter is adopted to refine the motion results. The presented ego-motion scheme is applied to benchmark datasets and compared with state-of-the-art approaches with data captured on campus in a considerably cluttered environment, where the superiorities are proved.

show abstract

Section: The Iterated Sigma Point Kalman Filter Refinementmentioning

confidence: 99%

Robust Features and Accurate Inliers Detection Framework: Application to Stereo Ego-motion Estimation

2016

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…DS techniques are based on rules that can be directly manipulated, while RS requires indirect modification of the sample generator. For instance, utilizing nonuniform sample weights in DS (see section 3.3.5) an arbitrary mixed moment of any finite number of parameters can easily be represented by solving a linear system of equations [1]. To represent every additional moment, the ensemble must be expanded with at least one sample.…”

Section: Propagation Of Covariance In the Unscented Kalman Filtermentioning

confidence: 99%

“…Here, the operator ξ evaluates the statistic(s) or moment(s) of interest; e.g., (ξ(V )) ij = (V ij ) k will return all (n) kth marginal moments of the excitation matrixV . Assigning rather than solving for the sample pointŝ V (:, k) and instead letting the weights W k be variables, the complicated strongly nonlinear system of equations (2.1) is translated to a strictly linear system [1] given by (3.22), which is straightforward to solve. That will also make it possible to have full control of the rangeM to avoid prohibited samples.…”

Section: Combined Ensembles (Cmb)mentioning

confidence: 99%

Deterministic Sampling for Propagating Model Covariance

Hessling¹

2013

SIAM/ASA J. Uncertainty Quantification

View full text Add to dashboard Cite

Abstract. Deterministic sampling can be used for nonlinear propagation of the statistics of signal processing models. Unlike Monte Carlo methods, random generators are not utilized in any stage. The samples are instead calculated deterministically. Our novel approach generalizes the deterministic sampling technique for propagating covariance in the unscented Kalman filter by introducing generic excitation matrices describing small discrete canonical ensembles. The approximation lies in how well the available statistical information is encoded in the discrete ensemble, not how each sample is propagated. The application and performance of deterministic sampling are illustrated for a typical step response analysis of an electrical device modeled with an uncertain digital filter. [20,12,11], which is widely utilized in the signal processing community. There are very few other examples. In the most general context presented here, DS utilizes small and thus highly effective ensembles of samples of models devised for particular purposes. This work targets parameterized models h(q, t) = g(q, t) x(t), which are identified from calibration measurements and thus have dependent parameters q. Such a model is usually nonlinear in parameters and describes the linear response of a system with impulse response g(q, t) to an excitation x(t). The convolution ( ) will here be evaluated with classical linear digital filters [6].Once the samples are found, the procedure of DS is identical to that of RS-the model is evaluated for all samples of the ensemble, followed by calculation of the desired statistics. For instance, assume h(q) depends on one parameter q with mean q and variance δ 2 q , where · denotes statistical expectation. The mean h and the variance δ 2 h of the model can

show abstract

“…This paper solved the gas sensor cross-sensitivity problem, but did not propose a reasonable solution to the uncertainty measurement of the entire measurement dynamic system. The paper in [15]- [18] compiled an authoritative review of works published on measurement uncertainty since 2004 and described the measurement uncertainty evaluation scheme. However, there are few papers on the dynamic uncertainty of sensor arrays.…”

Section: Introductionmentioning

confidence: 99%

“…In the papers in [19]- [21], the uncertainty of the generalized Lambda distribution of expressions is described, but the proposed algorithm is not suitable for the estimation of measurement uncertainty of MOS gas sensor arrays. The paper in [18], [22], and [23] discussed the uncertainty assessment in indirect measurements, where the main concern is the measurement model. Its input is modeled as a dependent random variable, but this method has a large error in evaluating the dynamic uncertainty of the MOS gas sensor array and the calculation process is complicated.…”

Section: Introductionmentioning

confidence: 99%

Gas Sensor Array Dynamic Measurement Uncertainty Evaluation and Optimization Algorithm

Zhang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Metal oxide semiconductor (MOS) gas sensor array dynamic measurement uncertainty evaluation, which currently mainly uses static measurement approximation estimations, cannot accurately distinguish the measured value of the sudden change of the measured value caused by the dynamic mutation of the measured gas or the actual sensor array local fault caused by the sudden change of the measured value, thereby resulting in a dynamic measurement process of the MOS gas sensor array uncertainty evaluation results and the validation measurement value reliability being greatly reduced. This paper presents a dynamic adaptive Kalman filter andGray bootstrap comprehensive modified prediction model for the dynamic measurement uncertainty evaluation. The dynamic adaptive Kalman filter and Gray bootstrap method is used to estimate the good performance of the probability distribution function of the measured value, and the uncertainty evaluation of the dynamic measurement state of the MOS gas sensor array is realized. Using the correlation of the dynamic adaptive Kalman filter and Gray model multisensor output, a new MOS gas sensor array measurement value confirmation algorithm is proposed to distinguish the measured value mutation caused by the normal dynamic mutation of the measured gas and the fault of the real sensor array. Finally, the MOS gas sensor array measurement is set up, and the experiments show that the proposed MOS gas sensor array dynamic measurement uncertainty evaluation and an optimization algorithm is effective. INDEX TERMS Sensor array, dynamic measurement, uncertainty, dynamic adaptive Kalman filter.

show abstract

Unscented Transform: A Powerful Tool for Measurement Uncertainty Evaluation

Cited by 33 publications

References 9 publications

Robust Features and Accurate Inliers Detection Framework: Application to Stereo Ego-motion Estimation

Robust Features and Accurate Inliers Detection Framework: Application to Stereo Ego-motion Estimation

Deterministic Sampling for Propagating Model Covariance

Gas Sensor Array Dynamic Measurement Uncertainty Evaluation and Optimization Algorithm

Contact Info

Product

Resources

About