Multitemporal Aerial Image Registration Using Semantic Features

Ananya Gupta; Yao Peng; Simon Watson; Hujun Yin

doi:10.1007/978-3-030-33617-2_9

Multitemporal Aerial Image Registration Using Semantic Features

Ananya Gupta, Yao Peng, Simon Watson, Hujun Yin

Research output: Chapter in Book/Conference proceeding › Chapter › peer-review

Abstract

A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper. These features encode properties or information about temporally invariant objects such as roads and help deal with issues such as changing foliage in image registration, which classical handcrafted features are unable to address. These features are extracted from a semantic segmentation network and have shown good robustness and accuracy in registering aerial images across years and seasons in the experiments.

Original language	English
Title of host publication	International Conference on Intelligent Data Engineering and Automated Learning
Publisher	Springer Nature
Pages	78-86
Number of pages	9
DOIs	https://doi.org/10.1007/978-3-030-33617-2_9
Publication status	Published - 2019
Event	20th International Conference on Intelligent Data Engineering and Automated Learning - The University of Manchester, Manchester, United Kingdom Duration: 14 Nov 2019 → 16 Nov 2019 http://www.confercare.manchester.ac.uk/events/ideal2019/

Publication series

Name	Lecture Notes in Computer Science
Number	11872

Conference

Conference	20th International Conference on Intelligent Data Engineering and Automated Learning
Abbreviated title	IDEAL
Country/Territory	United Kingdom
City	Manchester
Period	14/11/19 → 16/11/19
Internet address	http://www.confercare.manchester.ac.uk/events/ideal2019/

Keywords

Image registration
Semantic features
Convolutional neural networks

Access to Document

10.1007/978-3-030-33617-2_9

Cite this

@inbook{8468144358e344968c6ed29bb5f18f2e,

title = "Multitemporal Aerial Image Registration Using Semantic Features",

abstract = "A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper. These features encode properties or information about temporally invariant objects such as roads and help deal with issues such as changing foliage in image registration, which classical handcrafted features are unable to address. These features are extracted from a semantic segmentation network and have shown good robustness and accuracy in registering aerial images across years and seasons in the experiments.",

keywords = "Image registration, Semantic features, Convolutional neural networks",

author = "Ananya Gupta and Yao Peng and Simon Watson and Hujun Yin",

year = "2019",

doi = "10.1007/978-3-030-33617-2\_9",

language = "English",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

number = "11872",

pages = "78--86",

booktitle = "International Conference on Intelligent Data Engineering and Automated Learning",

address = "United States",

note = "20th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL ; Conference date: 14-11-2019 Through 16-11-2019",

url = "http://www.confercare.manchester.ac.uk/events/ideal2019/",

}

Gupta, A, Peng, Y, Watson, S & Yin, H 2019, Multitemporal Aerial Image Registration Using Semantic Features. in International Conference on Intelligent Data Engineering and Automated Learning. Lecture Notes in Computer Science, no. 11872, Springer Nature, pp. 78-86, 20th International Conference on Intelligent Data Engineering and Automated Learning, Manchester, United Kingdom, 14/11/19. https://doi.org/10.1007/978-3-030-33617-2_9

TY - CHAP

T1 - Multitemporal Aerial Image Registration Using Semantic Features

AU - Gupta, Ananya

AU - Peng, Yao

AU - Watson, Simon

AU - Yin, Hujun

PY - 2019

Y1 - 2019

N2 - A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper. These features encode properties or information about temporally invariant objects such as roads and help deal with issues such as changing foliage in image registration, which classical handcrafted features are unable to address. These features are extracted from a semantic segmentation network and have shown good robustness and accuracy in registering aerial images across years and seasons in the experiments.

AB - A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper. These features encode properties or information about temporally invariant objects such as roads and help deal with issues such as changing foliage in image registration, which classical handcrafted features are unable to address. These features are extracted from a semantic segmentation network and have shown good robustness and accuracy in registering aerial images across years and seasons in the experiments.

KW - Image registration

KW - Semantic features

KW - Convolutional neural networks

UR - https://doi.org/10.1007/978-3-030-33617-2_9

U2 - 10.1007/978-3-030-33617-2_9

DO - 10.1007/978-3-030-33617-2_9

M3 - Chapter

T3 - Lecture Notes in Computer Science

SP - 78

EP - 86

BT - International Conference on Intelligent Data Engineering and Automated Learning

PB - Springer Nature

T2 - 20th International Conference on Intelligent Data Engineering and Automated Learning

Y2 - 14 November 2019 through 16 November 2019

ER -

Multitemporal Aerial Image Registration Using Semantic Features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this