Mosaicing and restoration from blurred image sequence taken with moving camera

Midori Onogi, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

A wide-area image can be synthesized from an image sequence taken with a moving camera by using image mosaicing techniques. However, motion blur caused by the motion of the camera may significantly degrade the quality of the synthesized image. In this paper, we propose a new method for generating a deblurred mosaic from an image sequence that is degraded by motion blur under the condition that we do not have any information about the intrinsic and extrinsic parameters of the moving camera during input acquisition. In this method, we assume the objects in the scene can be classified into two regions in order to handle depth. In this paper, the displacement vectors of the features, which are computed using the KLT feature tracker on the consecutive frames, are classified into two regions. Here, the classified vectors provide a Point Spread Function (PSF) of the blurred image, and a homography between two consecutive frames for segmentation and mosaicing. Experimental results show that the Signal to Noise Ratio of the generated images can be significantly improved by our proposed method.

Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsS. Singh, M. Singh, C. Apte, P. Perner
Pages598-607
Number of pages10
Volume3687
EditionPART II
Publication statusPublished - 2005
EventThird International Conference on Advances in Patten Recognition, ICAPR 2005 - Bath, United Kingdom
Duration: 2005 Aug 222005 Aug 25

Other

OtherThird International Conference on Advances in Patten Recognition, ICAPR 2005
CountryUnited Kingdom
CityBath
Period05/8/2205/8/25

Fingerprint

Restoration
Cameras
Optical transfer function
Signal to noise ratio

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Onogi, M., & Saito, H. (2005). Mosaicing and restoration from blurred image sequence taken with moving camera. In S. Singh, M. Singh, C. Apte, & P. Perner (Eds.), Lecture Notes in Computer Science (PART II ed., Vol. 3687, pp. 598-607)

Mosaicing and restoration from blurred image sequence taken with moving camera. / Onogi, Midori; Saito, Hideo.

Lecture Notes in Computer Science. ed. / S. Singh; M. Singh; C. Apte; P. Perner. Vol. 3687 PART II. ed. 2005. p. 598-607.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Onogi, M & Saito, H 2005, Mosaicing and restoration from blurred image sequence taken with moving camera. in S Singh, M Singh, C Apte & P Perner (eds), Lecture Notes in Computer Science. PART II edn, vol. 3687, pp. 598-607, Third International Conference on Advances in Patten Recognition, ICAPR 2005, Bath, United Kingdom, 05/8/22.
Onogi M, Saito H. Mosaicing and restoration from blurred image sequence taken with moving camera. In Singh S, Singh M, Apte C, Perner P, editors, Lecture Notes in Computer Science. PART II ed. Vol. 3687. 2005. p. 598-607
Onogi, Midori ; Saito, Hideo. / Mosaicing and restoration from blurred image sequence taken with moving camera. Lecture Notes in Computer Science. editor / S. Singh ; M. Singh ; C. Apte ; P. Perner. Vol. 3687 PART II. ed. 2005. pp. 598-607
@inproceedings{dbcbc75f656341b69a6fd5ba1e703de1,
title = "Mosaicing and restoration from blurred image sequence taken with moving camera",
abstract = "A wide-area image can be synthesized from an image sequence taken with a moving camera by using image mosaicing techniques. However, motion blur caused by the motion of the camera may significantly degrade the quality of the synthesized image. In this paper, we propose a new method for generating a deblurred mosaic from an image sequence that is degraded by motion blur under the condition that we do not have any information about the intrinsic and extrinsic parameters of the moving camera during input acquisition. In this method, we assume the objects in the scene can be classified into two regions in order to handle depth. In this paper, the displacement vectors of the features, which are computed using the KLT feature tracker on the consecutive frames, are classified into two regions. Here, the classified vectors provide a Point Spread Function (PSF) of the blurred image, and a homography between two consecutive frames for segmentation and mosaicing. Experimental results show that the Signal to Noise Ratio of the generated images can be significantly improved by our proposed method.",
author = "Midori Onogi and Hideo Saito",
year = "2005",
language = "English",
volume = "3687",
pages = "598--607",
editor = "S. Singh and M. Singh and C. Apte and P. Perner",
booktitle = "Lecture Notes in Computer Science",
edition = "PART II",

}

TY - GEN

T1 - Mosaicing and restoration from blurred image sequence taken with moving camera

AU - Onogi, Midori

AU - Saito, Hideo

PY - 2005

Y1 - 2005

N2 - A wide-area image can be synthesized from an image sequence taken with a moving camera by using image mosaicing techniques. However, motion blur caused by the motion of the camera may significantly degrade the quality of the synthesized image. In this paper, we propose a new method for generating a deblurred mosaic from an image sequence that is degraded by motion blur under the condition that we do not have any information about the intrinsic and extrinsic parameters of the moving camera during input acquisition. In this method, we assume the objects in the scene can be classified into two regions in order to handle depth. In this paper, the displacement vectors of the features, which are computed using the KLT feature tracker on the consecutive frames, are classified into two regions. Here, the classified vectors provide a Point Spread Function (PSF) of the blurred image, and a homography between two consecutive frames for segmentation and mosaicing. Experimental results show that the Signal to Noise Ratio of the generated images can be significantly improved by our proposed method.

AB - A wide-area image can be synthesized from an image sequence taken with a moving camera by using image mosaicing techniques. However, motion blur caused by the motion of the camera may significantly degrade the quality of the synthesized image. In this paper, we propose a new method for generating a deblurred mosaic from an image sequence that is degraded by motion blur under the condition that we do not have any information about the intrinsic and extrinsic parameters of the moving camera during input acquisition. In this method, we assume the objects in the scene can be classified into two regions in order to handle depth. In this paper, the displacement vectors of the features, which are computed using the KLT feature tracker on the consecutive frames, are classified into two regions. Here, the classified vectors provide a Point Spread Function (PSF) of the blurred image, and a homography between two consecutive frames for segmentation and mosaicing. Experimental results show that the Signal to Noise Ratio of the generated images can be significantly improved by our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=27244444427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27244444427&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3687

SP - 598

EP - 607

BT - Lecture Notes in Computer Science

A2 - Singh, S.

A2 - Singh, M.

A2 - Apte, C.

A2 - Perner, P.

ER -