|Appears in Collections:||Computing Science and Mathematics Journal Articles|
|Peer Review Status:||Refereed|
|Title:||Dynamic Multicontext Segmentation of Remote Sensing Images Based on Convolutional Networks|
Dalla Mura, Mauro
Schwartz, William Robson
dos Santos, Jefersson Alex
|Keywords:||Convolutional networks (ConvNets)|
|Citation:||Nogueira K, Dalla Mura M, Chanussot J, Schwartz WR & dos Santos JA (2019) Dynamic Multicontext Segmentation of Remote Sensing Images Based on Convolutional Networks. IEEE Transactions on Geoscience and Remote Sensing, 57 (10), pp. 7503-7520. https://doi.org/10.1109/tgrs.2019.2913861|
|Abstract:||Semantic segmentation requires methods capable of learning high-level features while dealing with large volume of data. Toward such goal, convolutional networks can learn specific and adaptable features based on the data. However, these networks are not capable of processing a whole remote sensing image, given its huge size. To overcome such limitation, the image is processed using fixed size patches. The definition of the input patch size is usually performed empirically (evaluating several sizes) or imposed (by network constraint). Both strategies suffer from drawbacks and could not lead to the best patch size. To alleviate this problem, several works exploited multicontext information by combining networks or layers. This process increases the number of parameters, resulting in a more difficult model to train. In this paper, we propose a novel technique to perform semantic segmentation of remote sensing images that exploits a multicontext paradigm without increasing the number of parameters while defining, in training time, the best patch size. The main idea is to train a dilated network with distinct patch sizes, allowing it to capture multicontext characteristics from heterogeneous contexts. While processing these varying patches, the network provides a score for each patch size, helping in the definition of the best size for the current scenario. A systematic evaluation of the proposed algorithm is conducted using four high-resolution remote sensing data sets with very distinct properties. Our results show that the proposed algorithm provides improvements in pixelwise classification accuracy when compared to the state-of-the-art methods.|
|Rights:||The publisher does not allow this work to be made publicly available in this Repository. Please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.|
|Nogueira-TGRS-2019.pdf||Fulltext - Published Version||27.68 MB||Adobe PDF||Under Permanent Embargo Request a copy|
Note: If any of the files in this item are currently embargoed, you can request a copy directly from the author by clicking the padlock icon above. However, this facility is dependent on the depositor still being contactable at their original email address.
This item is protected by original copyright
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
If you believe that any material held in STORRE infringes copyright, please contact firstname.lastname@example.org providing details and we will remove the Work from public display in STORRE and investigate your claim.