Unsupervised change detection in satellite images using convolutional neural networks
KL de Jong, AS Bosman - 2019 International joint conference …, 2019 - ieeexplore.ieee.org
KL de Jong, AS Bosman
2019 International joint conference on neural networks (IJCNN), 2019•ieeexplore.ieee.orgThis paper proposes an efficient unsupervised method for detecting relevant changes
between two temporally different images of the same scene. A convolutional neural network
(CNN) for semantic segmentation is implemented to extract compressed image features, as
well as to classify the detected changes into the correct semantic classes. A difference
image is created using the feature map information generated by the CNN, without explicitly
training on target difference images. Thus, the proposed change detection method is …
between two temporally different images of the same scene. A convolutional neural network
(CNN) for semantic segmentation is implemented to extract compressed image features, as
well as to classify the detected changes into the correct semantic classes. A difference
image is created using the feature map information generated by the CNN, without explicitly
training on target difference images. Thus, the proposed change detection method is …
This paper proposes an efficient unsupervised method for detecting relevant changes between two temporally different images of the same scene. A convolutional neural network (CNN) for semantic segmentation is implemented to extract compressed image features, as well as to classify the detected changes into the correct semantic classes. A difference image is created using the feature map information generated by the CNN, without explicitly training on target difference images. Thus, the proposed change detection method is unsupervised, and can be performed using any CNN model pre-trained for semantic segmentation.
ieeexplore.ieee.org
Showing the best result for this search. See all results