Multi-Temporal Classification And Change Detection Using UAV Images

Salma Makuti, F.C. Nex, M.Y. Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
143 Downloads (Pure)

Abstract

In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6% and the pre classification change detection have an accuracy of 46.5%. These results represent a first useful indication for future works and developments.
Original languageEnglish
Title of host publication 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy
Place of PublicationRiva Del Garda
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Pages651-658
Number of pages8
DOIs
Publication statusPublished - 6 Jun 2018

Publication series

NameThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherISPRS
VolumeXLII-2

Fingerprint

Unmanned aerial vehicles (UAV)
detection
building construction
Image acquisition
detection method
Feature extraction
indication
building
Color
methodology

Keywords

  • ITC-GOLD
  • Fully connected CRF
  • Change detection
  • UAV images
  • Random forest

Cite this

Makuti, S., Nex, F. C., & Yang, M. Y. (2018). Multi-Temporal Classification And Change Detection Using UAV Images. In 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy (pp. 651-658). (The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. XLII-2). Riva Del Garda: International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprs-archives-XLII-2-651-2018
Makuti, Salma ; Nex, F.C. ; Yang, M.Y. / Multi-Temporal Classification And Change Detection Using UAV Images. 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy. Riva Del Garda : International Society for Photogrammetry and Remote Sensing (ISPRS), 2018. pp. 651-658 (The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inproceedings{2963fb99bf994bb08f1c933c0088543e,
title = "Multi-Temporal Classification And Change Detection Using UAV Images",
abstract = "In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6{\%} and the pre classification change detection have an accuracy of 46.5{\%}. These results represent a first useful indication for future works and developments.",
keywords = "ITC-GOLD, Fully connected CRF, Change detection, UAV images, Random forest",
author = "Salma Makuti and F.C. Nex and M.Y. Yang",
year = "2018",
month = "6",
day = "6",
doi = "10.5194/isprs-archives-XLII-2-651-2018",
language = "English",
series = "The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",
pages = "651--658",
booktitle = "2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy",

}

Makuti, S, Nex, FC & Yang, MY 2018, Multi-Temporal Classification And Change Detection Using UAV Images. in 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLII-2, International Society for Photogrammetry and Remote Sensing (ISPRS), Riva Del Garda, pp. 651-658. https://doi.org/10.5194/isprs-archives-XLII-2-651-2018

Multi-Temporal Classification And Change Detection Using UAV Images. / Makuti, Salma ; Nex, F.C.; Yang, M.Y.

2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy. Riva Del Garda : International Society for Photogrammetry and Remote Sensing (ISPRS), 2018. p. 651-658 (The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. XLII-2).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Multi-Temporal Classification And Change Detection Using UAV Images

AU - Makuti, Salma

AU - Nex, F.C.

AU - Yang, M.Y.

PY - 2018/6/6

Y1 - 2018/6/6

N2 - In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6% and the pre classification change detection have an accuracy of 46.5%. These results represent a first useful indication for future works and developments.

AB - In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6% and the pre classification change detection have an accuracy of 46.5%. These results represent a first useful indication for future works and developments.

KW - ITC-GOLD

KW - Fully connected CRF

KW - Change detection

KW - UAV images

KW - Random forest

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2018/conf/nex_mul.pdf

U2 - 10.5194/isprs-archives-XLII-2-651-2018

DO - 10.5194/isprs-archives-XLII-2-651-2018

M3 - Conference contribution

T3 - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 651

EP - 658

BT - 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

CY - Riva Del Garda

ER -

Makuti S, Nex FC, Yang MY. Multi-Temporal Classification And Change Detection Using UAV Images. In 2018 ISPRS TC II Mid-term Symposium “Towards Photogrammetry 2020”, 4–7 June 2018, Riva del Garda, Italy. Riva Del Garda: International Society for Photogrammetry and Remote Sensing (ISPRS). 2018. p. 651-658. (The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprs-archives-XLII-2-651-2018