Automatic tie-point matching using SURF-based image matching scheme

Jyun Ping Jhan, Jiann-Yeou Rau, Chien Chuan Lin, Yi Chen Shao

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

Abstract

In digital photogrammetry, automatic tie-point matching is necessary for photo triangulation, integrated sensor orientation, epipolar image generation, image registration, image transformation, image stitching, surface modeling, etc. The objective for this research is to find out a cost-effective way to perform automatic tie-point matching in photo triangulation. SURF (Speed-Up Robust Features) is a scale and rotation invariant feature extraction operator that is suitable for feature point matching even a certain degree of geometrical distortion exists. In this paper, based on the SURF image matching scheme, we develop three tie-point matching strategies and a robust estimation filter to remove blunder error. In the meantime, multiple images measurement is considered to increase the redundancy and internal reliability during least-squares bundle adjustment. In the experiment, the performance of the developed tie-point matching scheme is evaluated by the posterior standard error (sigma0) of image coordinate measurement after free network bundle adjustment. Images acquired from different platforms and purposes are test, such as vertical aerial DSLR images in urban area, oblique aerial DSLR images, unmanned aerial vehicle images taken in mountainous area, close-range object images. Experimental results show that the proposed scheme can match abundant of tie points and the sigma0 is less than 1/3 pixels. It demonstrates that the feasibility of the developed algorithm is high and is suitable for most of the photogrammetric applications.

Original languageEnglish
Title of host publication32nd Asian Conference on Remote Sensing 2011, ACRS 2011
Pages2336-2341
Number of pages6
Volume4
Publication statusPublished - 2011
Event32nd Asian Conference on Remote Sensing 2011, ACRS 2011 - Tapei, Taiwan
Duration: 2011 Oct 32011 Oct 7

Other

Other32nd Asian Conference on Remote Sensing 2011, ACRS 2011
CountryTaiwan
CityTapei
Period11-10-0311-10-07

Fingerprint

Image matching
Triangulation
Antennas
Photogrammetry
Image registration
Unmanned aerial vehicles (UAV)
Redundancy
Feature extraction
Pixels
Sensors
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Jhan, J. P., Rau, J-Y., Lin, C. C., & Shao, Y. C. (2011). Automatic tie-point matching using SURF-based image matching scheme. In 32nd Asian Conference on Remote Sensing 2011, ACRS 2011 (Vol. 4, pp. 2336-2341)
Jhan, Jyun Ping ; Rau, Jiann-Yeou ; Lin, Chien Chuan ; Shao, Yi Chen. / Automatic tie-point matching using SURF-based image matching scheme. 32nd Asian Conference on Remote Sensing 2011, ACRS 2011. Vol. 4 2011. pp. 2336-2341
@inproceedings{27e52c0a9c014ca8849006f1ee1449f0,
title = "Automatic tie-point matching using SURF-based image matching scheme",
abstract = "In digital photogrammetry, automatic tie-point matching is necessary for photo triangulation, integrated sensor orientation, epipolar image generation, image registration, image transformation, image stitching, surface modeling, etc. The objective for this research is to find out a cost-effective way to perform automatic tie-point matching in photo triangulation. SURF (Speed-Up Robust Features) is a scale and rotation invariant feature extraction operator that is suitable for feature point matching even a certain degree of geometrical distortion exists. In this paper, based on the SURF image matching scheme, we develop three tie-point matching strategies and a robust estimation filter to remove blunder error. In the meantime, multiple images measurement is considered to increase the redundancy and internal reliability during least-squares bundle adjustment. In the experiment, the performance of the developed tie-point matching scheme is evaluated by the posterior standard error (sigma0) of image coordinate measurement after free network bundle adjustment. Images acquired from different platforms and purposes are test, such as vertical aerial DSLR images in urban area, oblique aerial DSLR images, unmanned aerial vehicle images taken in mountainous area, close-range object images. Experimental results show that the proposed scheme can match abundant of tie points and the sigma0 is less than 1/3 pixels. It demonstrates that the feasibility of the developed algorithm is high and is suitable for most of the photogrammetric applications.",
author = "Jhan, {Jyun Ping} and Jiann-Yeou Rau and Lin, {Chien Chuan} and Shao, {Yi Chen}",
year = "2011",
language = "English",
isbn = "9781618394972",
volume = "4",
pages = "2336--2341",
booktitle = "32nd Asian Conference on Remote Sensing 2011, ACRS 2011",

}

Jhan, JP, Rau, J-Y, Lin, CC & Shao, YC 2011, Automatic tie-point matching using SURF-based image matching scheme. in 32nd Asian Conference on Remote Sensing 2011, ACRS 2011. vol. 4, pp. 2336-2341, 32nd Asian Conference on Remote Sensing 2011, ACRS 2011, Tapei, Taiwan, 11-10-03.

Automatic tie-point matching using SURF-based image matching scheme. / Jhan, Jyun Ping; Rau, Jiann-Yeou; Lin, Chien Chuan; Shao, Yi Chen.

32nd Asian Conference on Remote Sensing 2011, ACRS 2011. Vol. 4 2011. p. 2336-2341.

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

TY - GEN

T1 - Automatic tie-point matching using SURF-based image matching scheme

AU - Jhan, Jyun Ping

AU - Rau, Jiann-Yeou

AU - Lin, Chien Chuan

AU - Shao, Yi Chen

PY - 2011

Y1 - 2011

N2 - In digital photogrammetry, automatic tie-point matching is necessary for photo triangulation, integrated sensor orientation, epipolar image generation, image registration, image transformation, image stitching, surface modeling, etc. The objective for this research is to find out a cost-effective way to perform automatic tie-point matching in photo triangulation. SURF (Speed-Up Robust Features) is a scale and rotation invariant feature extraction operator that is suitable for feature point matching even a certain degree of geometrical distortion exists. In this paper, based on the SURF image matching scheme, we develop three tie-point matching strategies and a robust estimation filter to remove blunder error. In the meantime, multiple images measurement is considered to increase the redundancy and internal reliability during least-squares bundle adjustment. In the experiment, the performance of the developed tie-point matching scheme is evaluated by the posterior standard error (sigma0) of image coordinate measurement after free network bundle adjustment. Images acquired from different platforms and purposes are test, such as vertical aerial DSLR images in urban area, oblique aerial DSLR images, unmanned aerial vehicle images taken in mountainous area, close-range object images. Experimental results show that the proposed scheme can match abundant of tie points and the sigma0 is less than 1/3 pixels. It demonstrates that the feasibility of the developed algorithm is high and is suitable for most of the photogrammetric applications.

AB - In digital photogrammetry, automatic tie-point matching is necessary for photo triangulation, integrated sensor orientation, epipolar image generation, image registration, image transformation, image stitching, surface modeling, etc. The objective for this research is to find out a cost-effective way to perform automatic tie-point matching in photo triangulation. SURF (Speed-Up Robust Features) is a scale and rotation invariant feature extraction operator that is suitable for feature point matching even a certain degree of geometrical distortion exists. In this paper, based on the SURF image matching scheme, we develop three tie-point matching strategies and a robust estimation filter to remove blunder error. In the meantime, multiple images measurement is considered to increase the redundancy and internal reliability during least-squares bundle adjustment. In the experiment, the performance of the developed tie-point matching scheme is evaluated by the posterior standard error (sigma0) of image coordinate measurement after free network bundle adjustment. Images acquired from different platforms and purposes are test, such as vertical aerial DSLR images in urban area, oblique aerial DSLR images, unmanned aerial vehicle images taken in mountainous area, close-range object images. Experimental results show that the proposed scheme can match abundant of tie points and the sigma0 is less than 1/3 pixels. It demonstrates that the feasibility of the developed algorithm is high and is suitable for most of the photogrammetric applications.

UR - http://www.scopus.com/inward/record.url?scp=84865681817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865681817&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781618394972

VL - 4

SP - 2336

EP - 2341

BT - 32nd Asian Conference on Remote Sensing 2011, ACRS 2011

ER -

Jhan JP, Rau J-Y, Lin CC, Shao YC. Automatic tie-point matching using SURF-based image matching scheme. In 32nd Asian Conference on Remote Sensing 2011, ACRS 2011. Vol. 4. 2011. p. 2336-2341