TY - GEN
T1 - Change Detection from Unlabeled Remote Sensing Images Using SIAMESE ANN
AU - Hedjam, Rachid
AU - Abdesselam, Abdelhamid
AU - Melgani, Farid
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - In this article, we propose a new semi-supervised method to detect changes occurring in a geographical area after a major event such as war, an earthquake or flood. The detection is made by processing a pair of bi-temporal remotely sensed images of the area under consideration. The proposed method adopts a patch-based approach, where successive pairs of patches from the input images are compared using a deep machine learning method trained with augmented data. Our main contribution consists of proposing an approach for generating a training dataset from unlabeled pair of input images. The genuine training patch-pairs are directly generated from the transformed maps of the image taken before the event, while the impostor patch-pairs are generated by pairing the image taken before the event with any images, from the Internet, with textures that resemble the change shown in the image taken after the event. Several experiments were conducted on pairs of images related to five major events. The obtained subjective results demonstrate the effectiveness of the proposed method.
AB - In this article, we propose a new semi-supervised method to detect changes occurring in a geographical area after a major event such as war, an earthquake or flood. The detection is made by processing a pair of bi-temporal remotely sensed images of the area under consideration. The proposed method adopts a patch-based approach, where successive pairs of patches from the input images are compared using a deep machine learning method trained with augmented data. Our main contribution consists of proposing an approach for generating a training dataset from unlabeled pair of input images. The genuine training patch-pairs are directly generated from the transformed maps of the image taken before the event, while the impostor patch-pairs are generated by pairing the image taken before the event with any images, from the Internet, with textures that resemble the change shown in the image taken after the event. Several experiments were conducted on pairs of images related to five major events. The obtained subjective results demonstrate the effectiveness of the proposed method.
KW - Siamese neural networks
KW - change detection
KW - deep learning
KW - remote sensing
KW - unlabeled data
UR - http://www.scopus.com/inward/record.url?scp=85077724965&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077724965&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2019.8898672
DO - 10.1109/IGARSS.2019.8898672
M3 - Conference contribution
AN - SCOPUS:85077724965
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 1530
EP - 1533
BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Y2 - 28 July 2019 through 2 August 2019
ER -