Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting
A way to reduce the uncertainty at the output of a Kalman filter embedded into a tracker connected to an automotive RADAR sensor consists of the adaptive selection of parameters during the tracking process. Different informed strategies for automatically tuning the tracker’s parameters and to jointl...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/1/361 |
id |
doaj-1d453d990cbb44c7b0db586b9d7d4007 |
---|---|
record_format |
Article |
spelling |
doaj-1d453d990cbb44c7b0db586b9d7d40072021-01-02T00:01:18ZengMDPI AGApplied Sciences2076-34172021-01-011136136110.3390/app11010361Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial FittingGeorgiana Magu0Radu Lucaciu1Alexandru Isar2Communications Department, Politehnica University, 060042 București, RomaniaCommunications Department, Politehnica University, 060042 București, RomaniaCommunications Department, Politehnica University, 060042 București, RomaniaA way to reduce the uncertainty at the output of a Kalman filter embedded into a tracker connected to an automotive RADAR sensor consists of the adaptive selection of parameters during the tracking process. Different informed strategies for automatically tuning the tracker’s parameters and to jointly learn the parameters and state/output sequence using: expectation maximization; optimization approaches, including the simplex algorithm; coordinate descent; genetic algorithms; nonlinear programming using finite differencing to estimate the gradient; Bayesian optimization and reinforcement learning; automatically tuning hyper-parameters in the least squares, were already proposed. We develop here a different semi-blind post-processing approach, which is faster and more robust. Starting from the conjecture that the trajectory is polynomial in Cartesian coordinates, our method supposes to fit the data obtained at the output of the tracker to a polynomial. We highlight, by simulations, the improvement of the estimated trajectory’s accuracy using the polynomial fitting for single and multiple targets. We propose a new polynomial fitting method based on wavelets in two steps: denoising and polynomial part extraction, which compares favorably with the classical polynomial fitting method. The effect of the proposed post-processing methods is visible, the accuracy of targets’ trajectories estimations being hardly increased.https://www.mdpi.com/2076-3417/11/1/361polynomial fittingtrajectoryKalman filterwaveletsmultiple targets |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Georgiana Magu Radu Lucaciu Alexandru Isar |
spellingShingle |
Georgiana Magu Radu Lucaciu Alexandru Isar Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting Applied Sciences polynomial fitting trajectory Kalman filter wavelets multiple targets |
author_facet |
Georgiana Magu Radu Lucaciu Alexandru Isar |
author_sort |
Georgiana Magu |
title |
Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting |
title_short |
Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting |
title_full |
Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting |
title_fullStr |
Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting |
title_full_unstemmed |
Improving the Targets’ Trajectories Estimated by an Automotive RADAR Sensor Using Polynomial Fitting |
title_sort |
improving the targets’ trajectories estimated by an automotive radar sensor using polynomial fitting |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-01-01 |
description |
A way to reduce the uncertainty at the output of a Kalman filter embedded into a tracker connected to an automotive RADAR sensor consists of the adaptive selection of parameters during the tracking process. Different informed strategies for automatically tuning the tracker’s parameters and to jointly learn the parameters and state/output sequence using: expectation maximization; optimization approaches, including the simplex algorithm; coordinate descent; genetic algorithms; nonlinear programming using finite differencing to estimate the gradient; Bayesian optimization and reinforcement learning; automatically tuning hyper-parameters in the least squares, were already proposed. We develop here a different semi-blind post-processing approach, which is faster and more robust. Starting from the conjecture that the trajectory is polynomial in Cartesian coordinates, our method supposes to fit the data obtained at the output of the tracker to a polynomial. We highlight, by simulations, the improvement of the estimated trajectory’s accuracy using the polynomial fitting for single and multiple targets. We propose a new polynomial fitting method based on wavelets in two steps: denoising and polynomial part extraction, which compares favorably with the classical polynomial fitting method. The effect of the proposed post-processing methods is visible, the accuracy of targets’ trajectories estimations being hardly increased. |
topic |
polynomial fitting trajectory Kalman filter wavelets multiple targets |
url |
https://www.mdpi.com/2076-3417/11/1/361 |
work_keys_str_mv |
AT georgianamagu improvingthetargetstrajectoriesestimatedbyanautomotiveradarsensorusingpolynomialfitting AT radulucaciu improvingthetargetstrajectoriesestimatedbyanautomotiveradarsensorusingpolynomialfitting AT alexandruisar improvingthetargetstrajectoriesestimatedbyanautomotiveradarsensorusingpolynomialfitting |
_version_ |
1724364188228255744 |