Dynamic Multi-Context Segmentation of Remote Sensing Images based on Convolutional Networks

Abstract

Semantic segmentation requires methods capable of learning high-level features while dealing with large volume of data. Towards 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 multi-context information by combining networks or layers. This process increases the number of parameters resulting in a more difficult model to train. In this work, we propose a novel technique to perform semantic segmentation of remote sensing images that exploits a multi-context 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 multi-context 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 datasets with very distinct properties. Our results show that the proposed algorithm provides improvements in pixelwise classification accuracy when compared to state-of-the-art methods.

arXiv commentAccepted to Transactions on Geoscience & Remote Sensing (TGRS)

References in corpus (6)

• Deep learning in remote sensing: a review
• Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
• Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning
• Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks
• High-Resolution Semantic Labeling with Convolutional Neural Networks
• Exploiting ConvNet Diversity for Flooding Identification

Cited by in corpus (7)

• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• A Review on Deep Learning in UAV Remote Sensing
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Imbalance Knowledge-Driven Multi-modal Network for Land-Cover Semantic Segmentation Using Images and LiDAR Point Clouds
• Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers
• MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images
• Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation