TY - GEN
T1 - WOODLAND SEGMENTATION OF GAOFEN-6 REMOTE SENSING IMAGES BASED ON DEEP LEARNING
AU - Gui, Yuanyuan
AU - Li, Wei
AU - Zhang, Mengmeng
AU - Yue, Anzhi
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Gaofen-6 (GF-6) is a geostationary, earth-observation satellite, rely on it’s multi-spectral images, GF-6 has the ability to support the monitoring of woodland resources. In this paper, the multi-spectral images sent by GF-6 are studied as dataset, and a model called Infrared Attention Network (InfAttNet) which based on semantic segmentation method is proposed to distinguish woodland from other land types to achieve the purpose of woodland extraction. To make full use of the spectral information, InfAttNet has an additional encoder to extract the features of infrared bands independently. Besides, infrared attention blocks help InfAttNet to enhance the characteristics of woodland. The experimental results proved that InfAttNet improves the accuracy of woodland extraction, and the segmentation effect is strengthened compared with classical networks.
AB - Gaofen-6 (GF-6) is a geostationary, earth-observation satellite, rely on it’s multi-spectral images, GF-6 has the ability to support the monitoring of woodland resources. In this paper, the multi-spectral images sent by GF-6 are studied as dataset, and a model called Infrared Attention Network (InfAttNet) which based on semantic segmentation method is proposed to distinguish woodland from other land types to achieve the purpose of woodland extraction. To make full use of the spectral information, InfAttNet has an additional encoder to extract the features of infrared bands independently. Besides, infrared attention blocks help InfAttNet to enhance the characteristics of woodland. The experimental results proved that InfAttNet improves the accuracy of woodland extraction, and the segmentation effect is strengthened compared with classical networks.
KW - Attention Block
KW - Deep Learning
KW - Infrared Spectrums
KW - Remote Sensing Image
KW - Woodland Segmentation
UR - https://www.scopus.com/pages/publications/85127215068
U2 - 10.1109/IGARSS47720.2021.9554398
DO - 10.1109/IGARSS47720.2021.9554398
M3 - Conference contribution
AN - SCOPUS:85127215068
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 5409
EP - 5412
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -