Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: feature detector

Sortuj według:

Ogranicz wyniki do:

Overview of an improved and speedy features detection method for digital imagery

Hafsia Touka, Nouri Khaled, Belhaj Asma, Tlijani Hatem

Przegląd Elektrotechniczny

2023

R. 99, nr 12

181--184

In this paper, we were interested in the analysis of the visual field in the captured images, and information on the correct movement of the vision system in its environment to facilitate the analysis and detection of objects. Various feature extraction techniques for objects are discussed in this paper with the intention of doing a comparative study about edge and POIs detection methods to try to develop a novel algorithm that merges point and edge detection.

W niniejszej pracy interesowała nas analiza pola widzenia w przechwyconych obrazach oraz informacje na temat prawidłowego poruszania się układu wizyjnego w jego otoczeniu, aby ułatwić analizę i wykrywanie obiektów. W tym artykule omówiono różne techniki ekstrakcji cech obiektów z zamiarem przeprowadzenia badania porównawczego metod wykrywania krawędzi i punktów POI w celu opracowania nowego algorytmu, który łączy wykrywanie punktów i krawędzi.

Simultaneous localization and mapping for tracked wheel robots combining monocular and stereo vision

Jesus F., Ventura R.

Journal of Automation Mobile Robotics and Intelligent Systems

2013

Vol. 7, No. 1

21--27

This paper addresses an online 6D SLAM method for a tracked wheel robot in an unknown and unstructured environment. While the robot pose is represented by its position and orientation over a 3D space, the environment is mapped with natural landmarks in the same space, autonomously collected using visual data from feature detectors. The observation model employs opportunistically features detected from either monocular and stereo vision. These features are represented using an inverse depth parametrization. The motion model uses odometry readings from motor encoders and orientation changes measured with an IMU. A dimensional-bounded EKF (DBEKF) is introduced here, that keeps the dimension of the state bounded. A new landmark classifier using a Temporal Difference Learning methodology is used to identify undesired landmarks from the state. By forcing an upper bound to the number of landmarks in the EKF state, the computational complexity is reduced to up to a constant while not compromising its integrity. All experimental work was done using real data from RAPOSA-NG, a tracked wheel robot developed for Search and Rescue missions.