A new approach for automatic selection and transfer of corresponding image points in digital video image sequences

J. R. Tsay, I. C. Lee

Research output: Contribution to journalConference article

Abstract

We present a new approach for automatic selection and transfer of corresponding image points in digital video (DV) image sequences. This approach utilizes and extends some well-known techniques and theories (e.g. the optical flow theory) as well as a designed simple error-detection mechanism to achieve a much better efficiency than the well-known Lucas-Kanade optical flow estimation (LK) method. Our test results use the SONY DCR-PC115 DV image sequences and show that the trackable range of 3-4 pixels in the LK method can apparently be enlarged to 30 pixels in this new approach. The proposed error-detection mechanism simply utilizes the average gradient, normalized cross-correlation, and a simple image registration aided by least squares adjustment. Test results show that it can efficiently detect and delete wrong tracked points, and thus improve the quality of point transfer, and provide accurate coordinates of a large number of corresponding image points in DV image sequences. This work aims at high precision automatic image triangulation for the automatic real-time mobile mapping vehicle system (MMVS). Some future works need to be done.

Original languageEnglish
Pages (from-to)725-729
Number of pages5
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume35
Publication statusPublished - 2004 Jan 1
Event20th ISPRS Congress Technical Commission V - Istanbul, Turkey
Duration: 2004 Jul 122004 Jul 23

Fingerprint

Optical flows
Error detection
video
Pixels
Image registration
Triangulation
triangulation
pixel
efficiency
estimation method

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Geography, Planning and Development

Cite this

@article{6ff08e1b4d6c4a4fae69d76062c2781f,
title = "A new approach for automatic selection and transfer of corresponding image points in digital video image sequences",
abstract = "We present a new approach for automatic selection and transfer of corresponding image points in digital video (DV) image sequences. This approach utilizes and extends some well-known techniques and theories (e.g. the optical flow theory) as well as a designed simple error-detection mechanism to achieve a much better efficiency than the well-known Lucas-Kanade optical flow estimation (LK) method. Our test results use the SONY DCR-PC115 DV image sequences and show that the trackable range of 3-4 pixels in the LK method can apparently be enlarged to 30 pixels in this new approach. The proposed error-detection mechanism simply utilizes the average gradient, normalized cross-correlation, and a simple image registration aided by least squares adjustment. Test results show that it can efficiently detect and delete wrong tracked points, and thus improve the quality of point transfer, and provide accurate coordinates of a large number of corresponding image points in DV image sequences. This work aims at high precision automatic image triangulation for the automatic real-time mobile mapping vehicle system (MMVS). Some future works need to be done.",
author = "Tsay, {J. R.} and Lee, {I. C.}",
year = "2004",
month = "1",
day = "1",
language = "English",
volume = "35",
pages = "725--729",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",

}

TY - JOUR

T1 - A new approach for automatic selection and transfer of corresponding image points in digital video image sequences

AU - Tsay, J. R.

AU - Lee, I. C.

PY - 2004/1/1

Y1 - 2004/1/1

N2 - We present a new approach for automatic selection and transfer of corresponding image points in digital video (DV) image sequences. This approach utilizes and extends some well-known techniques and theories (e.g. the optical flow theory) as well as a designed simple error-detection mechanism to achieve a much better efficiency than the well-known Lucas-Kanade optical flow estimation (LK) method. Our test results use the SONY DCR-PC115 DV image sequences and show that the trackable range of 3-4 pixels in the LK method can apparently be enlarged to 30 pixels in this new approach. The proposed error-detection mechanism simply utilizes the average gradient, normalized cross-correlation, and a simple image registration aided by least squares adjustment. Test results show that it can efficiently detect and delete wrong tracked points, and thus improve the quality of point transfer, and provide accurate coordinates of a large number of corresponding image points in DV image sequences. This work aims at high precision automatic image triangulation for the automatic real-time mobile mapping vehicle system (MMVS). Some future works need to be done.

AB - We present a new approach for automatic selection and transfer of corresponding image points in digital video (DV) image sequences. This approach utilizes and extends some well-known techniques and theories (e.g. the optical flow theory) as well as a designed simple error-detection mechanism to achieve a much better efficiency than the well-known Lucas-Kanade optical flow estimation (LK) method. Our test results use the SONY DCR-PC115 DV image sequences and show that the trackable range of 3-4 pixels in the LK method can apparently be enlarged to 30 pixels in this new approach. The proposed error-detection mechanism simply utilizes the average gradient, normalized cross-correlation, and a simple image registration aided by least squares adjustment. Test results show that it can efficiently detect and delete wrong tracked points, and thus improve the quality of point transfer, and provide accurate coordinates of a large number of corresponding image points in DV image sequences. This work aims at high precision automatic image triangulation for the automatic real-time mobile mapping vehicle system (MMVS). Some future works need to be done.

UR - http://www.scopus.com/inward/record.url?scp=85049727648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049727648&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85049727648

VL - 35

SP - 725

EP - 729

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

ER -