Scene classification of high resolution remote sensing images using convolutional neural networks

Gong Cheng; Chengcheng Ma; Peicheng Zhou; Xiwen Yao; Junwei Han

doi:10.1109/IGARSS.2016.7729193

Scene classification of high resolution remote sensing images using convolutional neural networks

Gong Cheng
, Chengcheng Ma
, Peicheng Zhou
, Xiwen Yao
, Junwei Han

School of Automation

Northwestern Polytechnical University Xian

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

109 Scopus citations

Abstract

Scene classification of high resolution remote sensing images plays an important role for a wide range of applications. While significant efforts have been made in developing various methods for scene classification, most of them are based on handcrafted or shallow learning-based features. In this paper, we investigate the use of deep convolutional neural network (CNN) for scene classification. To this end, we first adopt two simple and effective strategies to extract CNN features: (1) using pre-trained CNN models as universal feature extractors, and (2) domain-specifically fine-tuning pre-trained CNN models on our scene classification dataset. Then, scene classification is carried out by using simple classifiers such as linear support vector machine (SVM). In our work, three off-the-shelf CNN models including AlexNet [1], VGGNet [2], and GoogleNet [3] are investigated. Comprehensive evaluations on a publicly available 21 classes land use dataset and comparisons with several state-of-the-art approaches demonstrate that deep CNN features are effective for scene classification of high resolution remote sensing images.

Original language	English
Title of host publication	2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	767-770
Number of pages	4
ISBN (Electronic)	9781509033324
DOIs	https://doi.org/10.1109/IGARSS.2016.7729193
State	Published - 1 Nov 2016
Event	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2016-November

Conference

Conference	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Country/Territory	China
City	Beijing
Period	10/07/16 → 15/07/16

UN SDGs

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

SDG 15 Life on Land

Keywords

Scene classification
convolutional neural network (CNN)
deep learning
feature extraction
remote sensing images

Access to Document

10.1109/IGARSS.2016.7729193

Cite this

Cheng, G., Ma, C., Zhou, P., Yao, X., & Han, J. (2016). Scene classification of high resolution remote sensing images using convolutional neural networks. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (pp. 767-770). Article 7729193 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7729193

Cheng, Gong ; Ma, Chengcheng ; Zhou, Peicheng et al. / Scene classification of high resolution remote sensing images using convolutional neural networks. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 767-770 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{2cb489f4ef6441318f9fd076d3d99cc3,

title = "Scene classification of high resolution remote sensing images using convolutional neural networks",

abstract = "Scene classification of high resolution remote sensing images plays an important role for a wide range of applications. While significant efforts have been made in developing various methods for scene classification, most of them are based on handcrafted or shallow learning-based features. In this paper, we investigate the use of deep convolutional neural network (CNN) for scene classification. To this end, we first adopt two simple and effective strategies to extract CNN features: (1) using pre-trained CNN models as universal feature extractors, and (2) domain-specifically fine-tuning pre-trained CNN models on our scene classification dataset. Then, scene classification is carried out by using simple classifiers such as linear support vector machine (SVM). In our work, three off-the-shelf CNN models including AlexNet [1], VGGNet [2], and GoogleNet [3] are investigated. Comprehensive evaluations on a publicly available 21 classes land use dataset and comparisons with several state-of-the-art approaches demonstrate that deep CNN features are effective for scene classification of high resolution remote sensing images.",

keywords = "Scene classification, convolutional neural network (CNN), deep learning, feature extraction, remote sensing images",

author = "Gong Cheng and Chengcheng Ma and Peicheng Zhou and Xiwen Yao and Junwei Han",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

year = "2016",

month = nov,

day = "1",

doi = "10.1109/IGARSS.2016.7729193",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "767--770",

booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",

}

Cheng, G, Ma, C, Zhou, P, Yao, X & Han, J 2016, Scene classification of high resolution remote sensing images using convolutional neural networks. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings., 7729193, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 767-770, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 10/07/16. https://doi.org/10.1109/IGARSS.2016.7729193

Scene classification of high resolution remote sensing images using convolutional neural networks. / Cheng, Gong; Ma, Chengcheng; Zhou, Peicheng et al.
2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 767-770 7729193 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November).

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

TY - GEN

T1 - Scene classification of high resolution remote sensing images using convolutional neural networks

AU - Cheng, Gong

AU - Ma, Chengcheng

AU - Zhou, Peicheng

AU - Yao, Xiwen

AU - Han, Junwei

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Scene classification of high resolution remote sensing images plays an important role for a wide range of applications. While significant efforts have been made in developing various methods for scene classification, most of them are based on handcrafted or shallow learning-based features. In this paper, we investigate the use of deep convolutional neural network (CNN) for scene classification. To this end, we first adopt two simple and effective strategies to extract CNN features: (1) using pre-trained CNN models as universal feature extractors, and (2) domain-specifically fine-tuning pre-trained CNN models on our scene classification dataset. Then, scene classification is carried out by using simple classifiers such as linear support vector machine (SVM). In our work, three off-the-shelf CNN models including AlexNet [1], VGGNet [2], and GoogleNet [3] are investigated. Comprehensive evaluations on a publicly available 21 classes land use dataset and comparisons with several state-of-the-art approaches demonstrate that deep CNN features are effective for scene classification of high resolution remote sensing images.

AB - Scene classification of high resolution remote sensing images plays an important role for a wide range of applications. While significant efforts have been made in developing various methods for scene classification, most of them are based on handcrafted or shallow learning-based features. In this paper, we investigate the use of deep convolutional neural network (CNN) for scene classification. To this end, we first adopt two simple and effective strategies to extract CNN features: (1) using pre-trained CNN models as universal feature extractors, and (2) domain-specifically fine-tuning pre-trained CNN models on our scene classification dataset. Then, scene classification is carried out by using simple classifiers such as linear support vector machine (SVM). In our work, three off-the-shelf CNN models including AlexNet [1], VGGNet [2], and GoogleNet [3] are investigated. Comprehensive evaluations on a publicly available 21 classes land use dataset and comparisons with several state-of-the-art approaches demonstrate that deep CNN features are effective for scene classification of high resolution remote sensing images.

KW - Scene classification

KW - convolutional neural network (CNN)

KW - deep learning

KW - feature extraction

KW - remote sensing images

UR - https://www.scopus.com/pages/publications/85007486834

U2 - 10.1109/IGARSS.2016.7729193

DO - 10.1109/IGARSS.2016.7729193

M3 - 会议稿件

AN - SCOPUS:85007486834

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 767

EP - 770

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Cheng G, Ma C, Zhou P, Yao X , Han J. Scene classification of high resolution remote sensing images using convolutional neural networks. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 767-770. 7729193. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2016.7729193

Scene classification of high resolution remote sensing images using convolutional neural networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this