Automatic image matching and georeferencing of digitized historical aerial photographs

I. Wen Chen, Hou Ren Chen, Yi-Hsing Tseng

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

Abstract

Historical aerial photographs can directly witness the historical landscape environment and link to the spatial information in the past. Which are important information sources to evaluate the temporal spatial evolution of zones of interest. In Taiwan, abundant historical aerial images have been acquired and archived by Research Center for Humanities and Social Sciences (RCHSS) of Academia Sinica. However, camera report of images was usually confidential. Most of the historical aerial images haven't been registered since there was no precise POS system for orientation assisting in the past. To handle such great quantity of images, this study was processed through methods of computer vision. Image features were extracted and matched by Scale Invariant Feature Transform (SIFT). To improve matching accuracy and efficiency of conjugate points, an improved Random Sample Consensus (RANSAC) was promoted by considering the error and recording the largest areas covered by randomly sampling points. Then, according to adjacency matrix, the relationships of conjugate points were established and stored. After image matching and alignment automatically, the relative orientation of images can be acquired. For registration, control points are needed to be added to do network adjustment based on 2D coordinate transformation (2D affine and 2D projective). Finally, those feature points matched by this procedure can be used to build control image database, and all computation is based on point data instead of image data. Also, further study such as multi-temporal environmental changes can be investigated by using this temporal spatial data system.

Original languageEnglish
Title of host publication37th Asian Conference on Remote Sensing, ACRS 2016
PublisherAsian Association on Remote Sensing
Pages1100-1108
Number of pages9
ISBN (Electronic)9781510834613
Publication statusPublished - 2016 Jan 1
Event37th Asian Conference on Remote Sensing, ACRS 2016 - Colombo, Sri Lanka
Duration: 2016 Oct 172016 Oct 21

Publication series

Name37th Asian Conference on Remote Sensing, ACRS 2016
Volume2

Other

Other37th Asian Conference on Remote Sensing, ACRS 2016
CountrySri Lanka
CityColombo
Period16-10-1716-10-21

Fingerprint

Image matching
Antennas
Social sciences
Computer vision
Cameras
Mathematical transformations
Sampling

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Chen, I. W., Chen, H. R., & Tseng, Y-H. (2016). Automatic image matching and georeferencing of digitized historical aerial photographs. In 37th Asian Conference on Remote Sensing, ACRS 2016 (pp. 1100-1108). (37th Asian Conference on Remote Sensing, ACRS 2016; Vol. 2). Asian Association on Remote Sensing.
Chen, I. Wen ; Chen, Hou Ren ; Tseng, Yi-Hsing. / Automatic image matching and georeferencing of digitized historical aerial photographs. 37th Asian Conference on Remote Sensing, ACRS 2016. Asian Association on Remote Sensing, 2016. pp. 1100-1108 (37th Asian Conference on Remote Sensing, ACRS 2016).
@inproceedings{6047631b11e645898c5f0eb4912dc722,
title = "Automatic image matching and georeferencing of digitized historical aerial photographs",
abstract = "Historical aerial photographs can directly witness the historical landscape environment and link to the spatial information in the past. Which are important information sources to evaluate the temporal spatial evolution of zones of interest. In Taiwan, abundant historical aerial images have been acquired and archived by Research Center for Humanities and Social Sciences (RCHSS) of Academia Sinica. However, camera report of images was usually confidential. Most of the historical aerial images haven't been registered since there was no precise POS system for orientation assisting in the past. To handle such great quantity of images, this study was processed through methods of computer vision. Image features were extracted and matched by Scale Invariant Feature Transform (SIFT). To improve matching accuracy and efficiency of conjugate points, an improved Random Sample Consensus (RANSAC) was promoted by considering the error and recording the largest areas covered by randomly sampling points. Then, according to adjacency matrix, the relationships of conjugate points were established and stored. After image matching and alignment automatically, the relative orientation of images can be acquired. For registration, control points are needed to be added to do network adjustment based on 2D coordinate transformation (2D affine and 2D projective). Finally, those feature points matched by this procedure can be used to build control image database, and all computation is based on point data instead of image data. Also, further study such as multi-temporal environmental changes can be investigated by using this temporal spatial data system.",
author = "Chen, {I. Wen} and Chen, {Hou Ren} and Yi-Hsing Tseng",
year = "2016",
month = "1",
day = "1",
language = "English",
series = "37th Asian Conference on Remote Sensing, ACRS 2016",
publisher = "Asian Association on Remote Sensing",
pages = "1100--1108",
booktitle = "37th Asian Conference on Remote Sensing, ACRS 2016",

}

Chen, IW, Chen, HR & Tseng, Y-H 2016, Automatic image matching and georeferencing of digitized historical aerial photographs. in 37th Asian Conference on Remote Sensing, ACRS 2016. 37th Asian Conference on Remote Sensing, ACRS 2016, vol. 2, Asian Association on Remote Sensing, pp. 1100-1108, 37th Asian Conference on Remote Sensing, ACRS 2016, Colombo, Sri Lanka, 16-10-17.

Automatic image matching and georeferencing of digitized historical aerial photographs. / Chen, I. Wen; Chen, Hou Ren; Tseng, Yi-Hsing.

37th Asian Conference on Remote Sensing, ACRS 2016. Asian Association on Remote Sensing, 2016. p. 1100-1108 (37th Asian Conference on Remote Sensing, ACRS 2016; Vol. 2).

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

TY - GEN

T1 - Automatic image matching and georeferencing of digitized historical aerial photographs

AU - Chen, I. Wen

AU - Chen, Hou Ren

AU - Tseng, Yi-Hsing

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Historical aerial photographs can directly witness the historical landscape environment and link to the spatial information in the past. Which are important information sources to evaluate the temporal spatial evolution of zones of interest. In Taiwan, abundant historical aerial images have been acquired and archived by Research Center for Humanities and Social Sciences (RCHSS) of Academia Sinica. However, camera report of images was usually confidential. Most of the historical aerial images haven't been registered since there was no precise POS system for orientation assisting in the past. To handle such great quantity of images, this study was processed through methods of computer vision. Image features were extracted and matched by Scale Invariant Feature Transform (SIFT). To improve matching accuracy and efficiency of conjugate points, an improved Random Sample Consensus (RANSAC) was promoted by considering the error and recording the largest areas covered by randomly sampling points. Then, according to adjacency matrix, the relationships of conjugate points were established and stored. After image matching and alignment automatically, the relative orientation of images can be acquired. For registration, control points are needed to be added to do network adjustment based on 2D coordinate transformation (2D affine and 2D projective). Finally, those feature points matched by this procedure can be used to build control image database, and all computation is based on point data instead of image data. Also, further study such as multi-temporal environmental changes can be investigated by using this temporal spatial data system.

AB - Historical aerial photographs can directly witness the historical landscape environment and link to the spatial information in the past. Which are important information sources to evaluate the temporal spatial evolution of zones of interest. In Taiwan, abundant historical aerial images have been acquired and archived by Research Center for Humanities and Social Sciences (RCHSS) of Academia Sinica. However, camera report of images was usually confidential. Most of the historical aerial images haven't been registered since there was no precise POS system for orientation assisting in the past. To handle such great quantity of images, this study was processed through methods of computer vision. Image features were extracted and matched by Scale Invariant Feature Transform (SIFT). To improve matching accuracy and efficiency of conjugate points, an improved Random Sample Consensus (RANSAC) was promoted by considering the error and recording the largest areas covered by randomly sampling points. Then, according to adjacency matrix, the relationships of conjugate points were established and stored. After image matching and alignment automatically, the relative orientation of images can be acquired. For registration, control points are needed to be added to do network adjustment based on 2D coordinate transformation (2D affine and 2D projective). Finally, those feature points matched by this procedure can be used to build control image database, and all computation is based on point data instead of image data. Also, further study such as multi-temporal environmental changes can be investigated by using this temporal spatial data system.

UR - http://www.scopus.com/inward/record.url?scp=85018455217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018455217&partnerID=8YFLogxK

M3 - Conference contribution

T3 - 37th Asian Conference on Remote Sensing, ACRS 2016

SP - 1100

EP - 1108

BT - 37th Asian Conference on Remote Sensing, ACRS 2016

PB - Asian Association on Remote Sensing

ER -

Chen IW, Chen HR, Tseng Y-H. Automatic image matching and georeferencing of digitized historical aerial photographs. In 37th Asian Conference on Remote Sensing, ACRS 2016. Asian Association on Remote Sensing. 2016. p. 1100-1108. (37th Asian Conference on Remote Sensing, ACRS 2016).