Robot mapping algorithm based on Kalman filtering and symbolic tags

Vokhmintcev, A. V.; Botova, T.; Sochenkov, Ilya; Sochenkova, Anastasiia; Makovetskii, Artyom

doi:10.1117/12.2273562

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Полученное в результате решения вариационной задачи минимизации функционала отображение можно интерпретировать как конформную параметризацию исходной поверхности сцены на римановом многообразии. Для предсказания поверхности нами был предложен модифицированной вариант расширенной калмановской фильтрации (Extended Kalman Filter, EKF), который позволяет получить точные и непрерывно обновляемые оценки положения камеры на основе временного ряда неточных измерений её местоположения [15]. Положение камеры на этапе k обозначается x v (k) -вектор состояния.…”

Section: схема построения трёхмерной модели сценыunclassified

“…Было установлено, что точность реконструкции зависит от количества особых точек в кадре нелинейным образом -в виде функции с одним ярко выраженным пиком для всех типов дескрипторов. В работах [14,15] показано, что предлагаемый метод регистрации трёхмерных объектов является наилучшим с точки зрения ошибок пропуска и ложных тревог для широкого спектра искажений белым шумом от 50 Дц до 10 Дцб. Основные недостатки классического метода ICP связаны с ограничением области сходимости и большой вычислительной сложностью.…”

Section: схема построения трёхмерной модели сценыunclassified

See 1 more Smart Citation

Reconstruction of three-dimensional maps based on closed-form solutions of the variational problem of multisensor data registration

Vokhmintcev¹,

Melnikov²,

Mironov³

et al. 2019

Доклады Академии наук

View full text Add to dashboard Cite

A closed-form solution is proposed for the problem of minimizing a functional consisting of two terms measuring mean-square distances for visually associated characteristic points on an image and meansquare distances for point clouds in terms of a point-to-plane metric. An accurate method for reconstructing three-dimensional dynamic environment is presented, and the properties of closed-form solutions are described. The proposed approach improves the accuracy and convergence of reconstruction methods for complex and large-scale scenes.

show abstract

Section: схема построения трёхмерной модели сценыunclassified

Reconstruction of three-dimensional maps based on closed-form solutions of the variational problem of multisensor data registration

Vokhmintcev¹,

Melnikov²,

Mironov³

et al. 2019

Доклады Академии наук

View full text Add to dashboard Cite

show abstract

“…A mathematical model of the scene will be saved in the form of a graph the vertices of which correspond to certain moments of time [21]. A new combined adaptive method was developed in the present work for the generating a three-dimensional combined dense map of an accessible environment and determining the position of the robot in a relative coordinate system based on the history of camera positions, on symbolic (semantic) tags, on the robot's movements and on the matching of obtained threedimensional depth maps which account for the accuracy of their superimposition, as well as geometric relationships between various images of one scene [22].…”

Section: Robot Mapping Algorithmmentioning

confidence: 99%

The New Combined Closed-Solution for 3D Reconstruction of Environment Based on Iterative Closest Point Algorithm

Vokhmintcev¹,

Melnikov²,

Pachganov³

et al. 2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

This The scientific problem at solving which the present project is directed consists in the development of accurate methods for reconstruction of a three-dimensional map of the accessible of environment with requied accuracy of reconstruction. The problem of consistent aligning of 3D point data is known registration task. The most popular registration algorithm is the Iterative Closest Point algorithm. Three basic problems are characteristic for the ICP algorithm: first, the convergence of the algorithm depends strongly on the choice of the initial approximation; second, the algorithm does not take into account the local shape of the surface around each point; and, third, the search for the nearest points is of high computational complexity. In this paper a new close solutions to 3D total variation regularization will be obtained and effective algorithms for restoring 3D data will be designed. The proposed approach improves the accuracy and convergence of reconstruction methods for complex and large-scale scenes. The performance and computational complexity of the proposed RGB-D Mapping algorithm in real indoor environments is discussed.

show abstract

Reconstruction of Three-Dimensional Maps Based on Closed-Form Solutions of the Variational Problem of Multisensor Data Registration

et al. 2019

View full text Add to dashboard Cite

Robot mapping algorithm based on Kalman filtering and symbolic tags

Cited by 3 publications

References 7 publications

Reconstruction of three-dimensional maps based on closed-form solutions of the variational problem of multisensor data registration

Reconstruction of three-dimensional maps based on closed-form solutions of the variational problem of multisensor data registration

The New Combined Closed-Solution for 3D Reconstruction of Environment Based on Iterative Closest Point Algorithm

Reconstruction of Three-Dimensional Maps Based on Closed-Form Solutions of the Variational Problem of Multisensor Data Registration

Contact Info

Product

Resources

About