Skip to main content
main-content
Top

Hint

Swipe to navigate through the articles of this issue

01-07-2019 | APPLIED PROBLEMS | Issue 3/2019

Pattern Recognition and Image Analysis 3/2019

Detection and Removal of Foreground Objects in Spherical Images for the Synthesis of Photorealistic Intermediate Images

Journal:
Pattern Recognition and Image Analysis > Issue 3/2019
Authors:
V. A. Gorbachev, I. V. Osokin
Important notes
https://static-content.springer.com/image/art%3A10.1134%2FS1054661819030064/MediaObjects/11493_2019_6014_Fig24_HTML.gif
Vadim Aleksandrovich Gorbachev. Born 1988. Graduated from the Moscow Institute of Physics and Technology in 2011 in specialty “System Analysis, Control’ and Information Processing.” Received candidate’s degree in 2014. Currently is head of sector at the State Research Institute of Aviation Systems. Scientific interests: computer vision, machine learning, pattern recognition, and image analysis. Author of 15 scientific papers.
https://static-content.springer.com/image/art%3A10.1134%2FS1054661819030064/MediaObjects/11493_2019_6014_Fig25_HTML.gif
Il’ya Vital’evich Osokin. Born 1996. Graduated from the Moscow Institute of Physics and Technology in 2018 in specialty “System Analysis, Control, and Information Processing.” Currently is an engineer at the State Research Institute of Aviation Systems. Scientific interests: computer vision, image synthesis, and image processing.
Translated by I. Nikitin

Abstract

A method is proposed for the removal of foreground objects from spherical images as applied to the synthesis of intermediate images. The synthesis procedure is based on a 3D model of the captured scene. As a rule, the objects that appear in the frame but are not fixed in the model are deformed during the synthesis of an intermediate frame, thus making the result unrealistic. The method proposed allows one to remove such objects from the foreground. The method is based on the comparison of two images of the scene taken from close viewpoints and on the redundancy of available information. The method was tested on panoramas and models available in the Google Street View service.

Please log in to get access to this content

To get access to this content you need the following product:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 30 Tage kostenlos.

Literature
About this article

Other articles of this Issue 3/2019

Pattern Recognition and Image Analysis 3/2019 Go to the issue

REPRESENTATION, PROCESSING, ANALYSIS, AND UNDERSTANDING OF IMAGES

Robust Visual Tracking Based on Relaxed Target Representation

REPRESENTATION, PROCESSING, ANALYSIS, AND UNDERSTANDING OF IMAGES

Panoramic Image Mosaics via Distributed Systems Using Color Moments and Local Wavelet-Features

MATHEMATICAL METHOD IN PATTERN RECOGNITION

Lightweight Nearest Convex Hull Classifier

Premium Partner

    Image Credits