Panoptic Segmentation Meets Remote Sensing

  title={Panoptic Segmentation Meets Remote Sensing},
  author={Osmar Luiz Ferreira de Carvalho and Osmar Ab'ilio de Carvalho J'unior and Cristiano Rosa e Silva and Anesmar Olino de Albuquerque and N{\'i}ckolas Castro Santana and D{\'i}bio Leandro Borges and Roberto Arnaldo Trancoso Gomes and Renato Fontes Guimar{\~a}es},
Panoptic segmentation combines instance and semantic predictions, allowing the detection of countable objects and different backgrounds simultaneously. Effectively approaching panoptic segmentation in remotely sensed data is very promising since it provides a complete classification, especially in areas with many elements as the urban setting. However, some difficulties have prevented the growth of this task: (a) it is very laborious to label large images with many classes, (b) there is no… 

Panoptic Segmentation Using Multispectral Worldview-3 Images in Beach Areas

Panoptic segmentation combines instance and semantic seg-mentation, enabling the classification of objects and back-grounds. It is still a method little explored in the remote sensing field, mostly


The automatic and accurate detection of mangroves from remote sensing data is essential to assist in conservation strategies and decision-making that minimize possible environmental damage,

HFENet: Hierarchical Feature Extraction Network for Accurate Landcover Classification

This work proposes a novel image segmentation network, named HFENet, for mining multi-level semantic information, which can perform better in the task of refining the semantic segmentation of remote sensing images.

Towards On-Board Panoptic Segmentation of Multispectral Satellite Images

A multimodal teacher network based on a cross-modality attention-based fusion strategy to improve the segmentation accuracy by exploiting data from multiple modes is proposed and compared to the existing state-of-the-art model when it is evaluated in an on-board processing setting.



Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Panoptic Segmentation

A novel panoptic quality (PQ) metric is proposed that captures performance for all classes (stuff and things) in an interpretable and unified manner and is performed a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task.

EfficientPS: Efficient Panoptic Segmentation

The Efficient Panoptic Segmentation (EfficientPS) architecture is introduced that consists of a shared backbone which efficiently encodes and fuses semantically rich multi-scale features and incorporates a new semantic head that aggregates fine and contextual features coherently.

Res2Net: A New Multi-Scale Backbone Architecture

This paper proposes a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block that represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.

ERN: Edge Loss Reinforced Semantic Segmentation Network for Remote Sensing Images

A novel edge loss reinforced semantic segmentation network (ERN) that leverages the spatial boundary context to reduce the semantic ambiguity and the effectiveness of the approach both in quantitative and qualitative evaluation is demonstrated.

Instance Segmentation for Governmental Inspection of Small Touristic Infrastructure in Beach Zones Using Multispectral High-Resolution WorldView-3 Imagery

The improved sliding window approach enables the classification of large areas providing automatic counting and estimating the size of the objects, proving to be effective for inspecting large coastal areas and providing insightful information for public managers.

Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset

A novel semi-supervised iterative learning approach using GIS software, proposing a box-free instance segmentation approach, and providing a city-scale vehicle dataset is proposed.

Building panoptic change segmentation with the use of uncertainty estimation in squeeze-and-attention CNN and remote sensing observations

ABSTRACT In conventional frameworks, the building change prediction of the deep model can be just blindly assumed accurate, but sometimes the truth is not. In this study, a new deep convolutional

Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation

This research aims to identify PV solar plants in Brazil using semantic segmentation and a mosaicking approach for large image classification using four architectures and finds that mosaicking progressively increases results when decreasing the stride value, at the cost of a higher computational cost.

Deep semantic segmentation for detecting eucalyptus planted forests in the Brazilian territory using sentinel-2 imagery

Abstract This research aims to analyze the use of deep semantic segmentation to detect eucalyptus afforestation areas using Sentinel-2 images. The study compared six architectures (U-net, DeepLabv3+,