Panorama Construction from Multi-view Cameras in Outdoor Scenes

Margarita Favorskaya, Lakhmi JAIN

Research output: A Conference proceeding or a Chapter in BookChapter

3 Citations (Scopus)
2 Downloads (Pure)

Abstract

The applications of panoramic images are wide spread in computer vision including navigation systems, object tracking, virtual environment creation, among others. In this chapter, the problems of multi-view shooting and the models of geometrical distortions are investigated under the panorama construction in the outdoor scenes. Our contribution are the development of procedure for selection of “good” frames from video sequences provided by several cameras, more accurate estimation of projective parameters in top, middle, and bottom regions in the overlapping area during frames stitching, and also the lighting improvement of the result panoramic image by a point-based blending in a stitching area. Most proposed algorithms have high computer cost because of mega-pixel sizes of initial frames. The reduction of frames sizes, the use of CUDA technique, or the hardware implementation will improve these results. The experiments show good visibility results with high stitching accuracy, if the initial frames were selected well
Original languageEnglish
Title of host publicationComputer Vision in Control Systems-2
EditorsMargarita Favorskaya, Lakhmi Jain
Place of PublicationGermany
PublisherSpringer
Pages71-108
Number of pages38
Volume75
Edition1
ISBN (Print)9783319114293
DOIs
Publication statusPublished - 2015

Publication series

NameIntelligent Systems Reference Library
PublisherSpringer Science + Business Media
ISSN (Print)1868-4394

Fingerprint

Navigation systems
Visibility
Virtual reality
Computer vision
Lighting
Pixels
Cameras
Hardware
Costs
Experiments

Cite this

Favorskaya, M., & JAIN, L. (2015). Panorama Construction from Multi-view Cameras in Outdoor Scenes. In M. Favorskaya, & L. Jain (Eds.), Computer Vision in Control Systems-2 (1 ed., Vol. 75, pp. 71-108). (Intelligent Systems Reference Library). Germany: Springer. https://doi.org/10.1007/978-3-319-11430-9_4
Favorskaya, Margarita ; JAIN, Lakhmi. / Panorama Construction from Multi-view Cameras in Outdoor Scenes. Computer Vision in Control Systems-2. editor / Margarita Favorskaya ; Lakhmi Jain. Vol. 75 1. ed. Germany : Springer, 2015. pp. 71-108 (Intelligent Systems Reference Library).
@inbook{17efcc4e8b3e43d3a305d503ef84acef,
title = "Panorama Construction from Multi-view Cameras in Outdoor Scenes",
abstract = "The applications of panoramic images are wide spread in computer vision including navigation systems, object tracking, virtual environment creation, among others. In this chapter, the problems of multi-view shooting and the models of geometrical distortions are investigated under the panorama construction in the outdoor scenes. Our contribution are the development of procedure for selection of “good” frames from video sequences provided by several cameras, more accurate estimation of projective parameters in top, middle, and bottom regions in the overlapping area during frames stitching, and also the lighting improvement of the result panoramic image by a point-based blending in a stitching area. Most proposed algorithms have high computer cost because of mega-pixel sizes of initial frames. The reduction of frames sizes, the use of CUDA technique, or the hardware implementation will improve these results. The experiments show good visibility results with high stitching accuracy, if the initial frames were selected well",
keywords = "Panorama-construction, multi-view-cameras, outdoor-scenes, Panorama construction, Projective transformation, Image selection, Retinex algorithm, Robust detectors, Texture blending, Image stitching",
author = "Margarita Favorskaya and Lakhmi JAIN",
year = "2015",
doi = "10.1007/978-3-319-11430-9_4",
language = "English",
isbn = "9783319114293",
volume = "75",
series = "Intelligent Systems Reference Library",
publisher = "Springer",
pages = "71--108",
editor = "Margarita Favorskaya and Lakhmi Jain",
booktitle = "Computer Vision in Control Systems-2",
address = "Netherlands",
edition = "1",

}

Favorskaya, M & JAIN, L 2015, Panorama Construction from Multi-view Cameras in Outdoor Scenes. in M Favorskaya & L Jain (eds), Computer Vision in Control Systems-2. 1 edn, vol. 75, Intelligent Systems Reference Library, Springer, Germany, pp. 71-108. https://doi.org/10.1007/978-3-319-11430-9_4

Panorama Construction from Multi-view Cameras in Outdoor Scenes. / Favorskaya, Margarita; JAIN, Lakhmi.

Computer Vision in Control Systems-2. ed. / Margarita Favorskaya; Lakhmi Jain. Vol. 75 1. ed. Germany : Springer, 2015. p. 71-108 (Intelligent Systems Reference Library).

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - Panorama Construction from Multi-view Cameras in Outdoor Scenes

AU - Favorskaya, Margarita

AU - JAIN, Lakhmi

PY - 2015

Y1 - 2015

N2 - The applications of panoramic images are wide spread in computer vision including navigation systems, object tracking, virtual environment creation, among others. In this chapter, the problems of multi-view shooting and the models of geometrical distortions are investigated under the panorama construction in the outdoor scenes. Our contribution are the development of procedure for selection of “good” frames from video sequences provided by several cameras, more accurate estimation of projective parameters in top, middle, and bottom regions in the overlapping area during frames stitching, and also the lighting improvement of the result panoramic image by a point-based blending in a stitching area. Most proposed algorithms have high computer cost because of mega-pixel sizes of initial frames. The reduction of frames sizes, the use of CUDA technique, or the hardware implementation will improve these results. The experiments show good visibility results with high stitching accuracy, if the initial frames were selected well

AB - The applications of panoramic images are wide spread in computer vision including navigation systems, object tracking, virtual environment creation, among others. In this chapter, the problems of multi-view shooting and the models of geometrical distortions are investigated under the panorama construction in the outdoor scenes. Our contribution are the development of procedure for selection of “good” frames from video sequences provided by several cameras, more accurate estimation of projective parameters in top, middle, and bottom regions in the overlapping area during frames stitching, and also the lighting improvement of the result panoramic image by a point-based blending in a stitching area. Most proposed algorithms have high computer cost because of mega-pixel sizes of initial frames. The reduction of frames sizes, the use of CUDA technique, or the hardware implementation will improve these results. The experiments show good visibility results with high stitching accuracy, if the initial frames were selected well

KW - Panorama-construction

KW - multi-view-cameras

KW - outdoor-scenes

KW - Panorama construction

KW - Projective transformation

KW - Image selection

KW - Retinex algorithm

KW - Robust detectors

KW - Texture blending

KW - Image stitching

UR - http://www.scopus.com/inward/record.url?scp=84921377183&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/panorama-construction-multiview-cameras-outdoor-scenes

U2 - 10.1007/978-3-319-11430-9_4

DO - 10.1007/978-3-319-11430-9_4

M3 - Chapter

SN - 9783319114293

VL - 75

T3 - Intelligent Systems Reference Library

SP - 71

EP - 108

BT - Computer Vision in Control Systems-2

A2 - Favorskaya, Margarita

A2 - Jain, Lakhmi

PB - Springer

CY - Germany

ER -

Favorskaya M, JAIN L. Panorama Construction from Multi-view Cameras in Outdoor Scenes. In Favorskaya M, Jain L, editors, Computer Vision in Control Systems-2. 1 ed. Vol. 75. Germany: Springer. 2015. p. 71-108. (Intelligent Systems Reference Library). https://doi.org/10.1007/978-3-319-11430-9_4