Title:

Techniki informacyjne teoria i zastosowania * Wybrane problemy * Metody detekcji cech obrazów w analizie wielokadrowej

Subtitle:

Książka = Book ; KS/8/2011/T13P04

Creator:

Koniarski, Konr

Publisher:

Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences

Place of publishing:

Warszawa

Date issued/created:

2011

Description:

[2], 68-82 pages ; 21 cm ; Bibliography p. 81-82

Type of object:

Book/Chapter

Abstract:

The paper presents review of selected methods for detection of image features. Three common used methods are compared for stereo viewing correspondence problem. The first is Harris corner detection method, next is gradient base method from SIFT (Scale Invariant Feature Transformation) detector and the last is FAST (Features from Accelerated Segment Test) method. Selected points are evaluated with regard to use epipolar geometry for view matching. RANSAC algorithm is used for computing of Fundamental Matrix and Epipolar geometry constraints. Special attention is paid to stability of point selection and performance. Based on the obtained numerical results FAST method is recommended as the most appropriate for augmented reality solutions.

Relation:

Książka = Book

Resource type:

Text

Detailed Resource Type:

Book

Source:

KS-2011-08-T13P04

Language:

pol

Language of abstract:

pol

Rights:

Creative Commons Attribution BY 4.0 license

Terms of use:

Copyright-protected material. [CC BY 4.0] May be used within the scope specified in Creative Commons Attribution BY 4.0 license, full text available at: ; -

Digitizing institution:

Systems Research Institute of the Polish Academy of Sciences

Original in:

Library of Systems Research Institute PAS

Projects co-financed by:

Operational Program Digital Poland, 2014-2020, Measure 2.3: Digital accessibility and usefulness of public sector information; funds from the European Regional Development Fund and national co-financing from the state budget.

Access:

Open