Feature Fusion through Multitask CNN for Large-scale Remote Sensing Image Segmentation

07/24/2018

∙

In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery. How to fuse multi-modal data to improve the segmentation performance has always been a research hotspot. In this paper, a novel end-toend fully convolutional neural network is proposed for semantic segmentation of natural color, infrared imagery and Digital Surface Models (DSM). It is based on a modified DeepUNet and perform the segmentation in a multi-task way. The channels are clustered into groups and processed on different task pipelines. After a series of segmentation and fusion, their shared features and private features are successfully merged together. Experiment results show that the feature fusion network is efficient. And our approach achieves good performance in ISPRS Semantic Labeling Contest (2D).

READ FULL TEXT

Feature Fusion through Multitask CNN for Large-scale Remote Sensing Image Segmentation

Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks

Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval

Dense labeling of large remote sensing imagery with convolutional neural networks: a simple and faster alternative to stitching output label maps

Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers

Juggling With Representations: On the Information Transfer Between Imagery, Point Clouds, and Meshes for Multi-Modal Semantics

Deep Convolutional Sparse Coding Networks for Image Fusion

TreeSegNet: Automatically Constructed Tree CNNs for Subdecimeter Aerial Image Segmentation

Feature Fusion through Multitask CNN for Large-scale Remote Sensing Image Segmentation

Related Research

Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks

Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval

Dense labeling of large remote sensing imagery with convolutional neural networks: a simple and faster alternative to stitching output label maps

Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers

Juggling With Representations: On the Information Transfer Between Imagery, Point Clouds, and Meshes for Multi-Modal Semantics

Deep Convolutional Sparse Coding Networks for Image Fusion

TreeSegNet: Automatically Constructed Tree CNNs for Subdecimeter Aerial Image Segmentation