Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric

Youngmin Kim; Ram M. Narayanan; Muralidhar Rangaswamy

doi:10.1109/NAECON61878.2024.10670690

Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric

Youngmin Kim
, Ram M. Narayanan
, Muralidhar Rangaswamy

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Change detection is an important topic in remote sensing to study the effects of climate change, natural disasters, urbanization, etc. However, the need for labeled data has posed significant challenges. In this paper, we introduce a self-supervised learning model to overcome this problem. To evaluate our model performance, we propose a novel evaluation metric called recall-based operational reliability. In our study, we used a large-scale multispectral image dataset called DynamicEarthNet for testing.

Original language	English (US)
Title of host publication	NAECON 2024 - IEEE National Aerospace and Electronics Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	112-118
Number of pages	7
ISBN (Electronic)	9798350367621
DOIs	https://doi.org/10.1109/NAECON61878.2024.10670690
State	Published - 2024
Event	76th Annual IEEE National Aerospace and Electronics Conference, NAECON 2024 - Dayton, United States Duration: Jul 15 2024 → Jul 18 2024

Publication series

Name	Proceedings of the IEEE National Aerospace Electronics Conference, NAECON
ISSN (Print)	0547-3578
ISSN (Electronic)	2379-2027

Conference

Conference	76th Annual IEEE National Aerospace and Electronics Conference, NAECON 2024
Country/Territory	United States
City	Dayton
Period	7/15/24 → 7/18/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 13 Climate Action

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Computer Science Applications
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/NAECON61878.2024.10670690

Cite this

Kim, Y., Narayanan, R. M., & Rangaswamy, M. (2024). Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric. In NAECON 2024 - IEEE National Aerospace and Electronics Conference (pp. 112-118). (Proceedings of the IEEE National Aerospace Electronics Conference, NAECON). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NAECON61878.2024.10670690

Kim, Youngmin ; Narayanan, Ram M. ; Rangaswamy, Muralidhar. / Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric. NAECON 2024 - IEEE National Aerospace and Electronics Conference. Institute of Electrical and Electronics Engineers Inc., 2024. pp. 112-118 (Proceedings of the IEEE National Aerospace Electronics Conference, NAECON).

@inproceedings{ddd8586986e9406781044957567117ef,

title = "Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric",

abstract = "Change detection is an important topic in remote sensing to study the effects of climate change, natural disasters, urbanization, etc. However, the need for labeled data has posed significant challenges. In this paper, we introduce a self-supervised learning model to overcome this problem. To evaluate our model performance, we propose a novel evaluation metric called recall-based operational reliability. In our study, we used a large-scale multispectral image dataset called DynamicEarthNet for testing.",

author = "Youngmin Kim and Narayanan, \{Ram M.\} and Muralidhar Rangaswamy",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 76th Annual IEEE National Aerospace and Electronics Conference, NAECON 2024 ; Conference date: 15-07-2024 Through 18-07-2024",

year = "2024",

doi = "10.1109/NAECON61878.2024.10670690",

language = "English (US)",

series = "Proceedings of the IEEE National Aerospace Electronics Conference, NAECON",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "112--118",

booktitle = "NAECON 2024 - IEEE National Aerospace and Electronics Conference",

address = "United States",

}

Kim, Y, Narayanan, RM & Rangaswamy, M 2024, Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric. in NAECON 2024 - IEEE National Aerospace and Electronics Conference. Proceedings of the IEEE National Aerospace Electronics Conference, NAECON, Institute of Electrical and Electronics Engineers Inc., pp. 112-118, 76th Annual IEEE National Aerospace and Electronics Conference, NAECON 2024, Dayton, United States, 7/15/24. https://doi.org/10.1109/NAECON61878.2024.10670690

Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric. / Kim, Youngmin; Narayanan, Ram M.; Rangaswamy, Muralidhar.
NAECON 2024 - IEEE National Aerospace and Electronics Conference. Institute of Electrical and Electronics Engineers Inc., 2024. p. 112-118 (Proceedings of the IEEE National Aerospace Electronics Conference, NAECON).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric

AU - Kim, Youngmin

AU - Narayanan, Ram M.

AU - Rangaswamy, Muralidhar

PY - 2024

Y1 - 2024

N2 - Change detection is an important topic in remote sensing to study the effects of climate change, natural disasters, urbanization, etc. However, the need for labeled data has posed significant challenges. In this paper, we introduce a self-supervised learning model to overcome this problem. To evaluate our model performance, we propose a novel evaluation metric called recall-based operational reliability. In our study, we used a large-scale multispectral image dataset called DynamicEarthNet for testing.

AB - Change detection is an important topic in remote sensing to study the effects of climate change, natural disasters, urbanization, etc. However, the need for labeled data has posed significant challenges. In this paper, we introduce a self-supervised learning model to overcome this problem. To evaluate our model performance, we propose a novel evaluation metric called recall-based operational reliability. In our study, we used a large-scale multispectral image dataset called DynamicEarthNet for testing.

UR - https://www.scopus.com/pages/publications/85204947662

UR - https://www.scopus.com/pages/publications/85204947662#tab=citedBy

U2 - 10.1109/NAECON61878.2024.10670690

DO - 10.1109/NAECON61878.2024.10670690

M3 - Conference contribution

AN - SCOPUS:85204947662

T3 - Proceedings of the IEEE National Aerospace Electronics Conference, NAECON

SP - 112

EP - 118

BT - NAECON 2024 - IEEE National Aerospace and Electronics Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 76th Annual IEEE National Aerospace and Electronics Conference, NAECON 2024

Y2 - 15 July 2024 through 18 July 2024

ER -

Kim Y, Narayanan RM, Rangaswamy M. Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric. In NAECON 2024 - IEEE National Aerospace and Electronics Conference. Institute of Electrical and Electronics Engineers Inc. 2024. p. 112-118. (Proceedings of the IEEE National Aerospace Electronics Conference, NAECON). doi: 10.1109/NAECON61878.2024.10670690

Large Scale Multispectral Image Dataset Change Detection Based on Self-Supervised Learning with Novel Evaluation Metric

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this