☆ 4.7 Article

Histogram matching-based semantic segmentation model for crop classification with Sentinel-2 satellite imagery

GISCIENCE & REMOTE SENSING (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Geochemistry & Geophysics

A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data

Gianmarco Perantoni et al.

Summary: Deep learning has attracted attention in remote sensing image scene classification for its ability to extract semantics from complex data, but requires large training samples and is sensitive to errors in training labels. To address this, combining less reliable labeled data sources with a reliable dataset to generate multisource labeled datasets and using a new training strategy that considers the reliability of each source can effectively improve the robustness and capability of leveraging on unreliable sources of labels.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Landscape context determines soil fungal diversity in a fragmented habitat

Nier Su et al.

Summary: Habitat fragmentation is associated with increased soil fungal diversity, while the change in soil bacterial diversity is not significant. Soil characteristics play a key role in soil bacterial diversity, while landscape context has a stronger impact on maintaining soil fungal diversity.

CATENA (2022)

添加到收藏夹

Article Environmental Sciences

Knowledge-guided land pattern depiction for urban land use mapping: A case study of Chinese cities

Qiqi Zhu et al.

Summary: Accurate urban land-use maps are crucial in urban analysis, and data-driven deep learning methods combined with multisource geographic data have made significant progress in land-use mapping. However, challenges exist in open street map (OSM)-based land-use pattern depiction. In this paper, a knowledge-guided land pattern depicting framework is proposed, integrating adaptive gradient perceptive and land pattern cognitive models for effective information extraction.

REMOTE SENSING OF ENVIRONMENT (2022)

添加到收藏夹

Article Geography, Physical

Exploring the potential of multi-source unsupervised domain adaptation in crop mapping using Sentinel-2 images

Yumiao Wang et al.

Summary: This study proposed a MUDA crop classification model (MUCCM) for unsupervised crop mapping and demonstrated its high performance in multiple target domains. The results indicated that the UDA models outperformed the direct transfer models significantly, and the MUCCM achieved the highest classification accuracy in each target domain.

GISCIENCE & REMOTE SENSING (2022)

添加到收藏夹

Article Agriculture, Multidisciplinary

Deep segmentation and classification of complex crops using multi-feature satellite imagery

Lijun Wang et al.

Summary: In this study, a deep learning approach based on the UNet++ architecture was developed for large-scale land use and crop mapping. The model achieved high performance in terms of overall accuracy, kappa, and macro F1. The integration of feature fusion and upsampling enabled spatiotemporal transfer across regions and years, improving the classification accuracy for datasets with imbalanced land cover and crop types.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

添加到收藏夹

Article Geography, Physical

Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels

Zhuohong Li et al.

Summary: Large-scale high-resolution land-cover mapping is crucial for understanding the Earth's surface and addressing ecological and resource challenges. This study proposes a low-to-high network (L2HNet) that can automatically generate high-resolution land-cover maps by using low-resolution land-cover products as training labels. The L2HNet outperforms other methods in creating accurate land-cover maps, making it a valuable tool for large-scale map updating and classification tasks.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2022)

添加到收藏夹

Article Chemistry, Analytical

Detecting Pest-Infested Forest Damage through Multispectral Satellite Imagery and Improved UNet plus

Jingzong Zhang et al.

Summary: The study aims to improve forest-pest infestation area segmentation by combining multispectral, vegetation indices and RGB information into deep learning. Experimental results show the significance of vegetation indices and multispectral data in enhancing the segmentation effect.

SENSORS (2022)

添加到收藏夹

Article Agronomy

Evaluation of a deep-learning model for multispectral remote sensing of land use and crop classification

Lijun Wang et al.

Summary: This study explores the high-resolution deep-learning-based remote-sensing imagery analysis for land-use and crop-classification mapping. It investigates the influence of composite feature bands, backbone, and patch size on predictions in transferable deep models. Experimental results show that feature selection and up-sampling techniques can improve the performance of the UNet++ architecture. The optimal backbone and patch size were determined as Timm-RegNetY-320 and 256 x 256, respectively.

CROP JOURNAL (2022)

添加到收藏夹

Article Geography, Physical

Fully convolutional recurrent networks for multidate crop recognition from multitemporal image sequences

Jorge Andres Chamorro Martinez et al.

Summary: This paper introduces convolutional recurrent networks for crop recognition in tropical regions with complex spatiotemporal dynamics, achieving per-date crop classification. Experimental results show that the proposed architectures outperform state-of-the-art methods based on recurrent networks in terms of accuracy and F1 score in tropical regions.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

添加到收藏夹

Article Geochemistry & Geophysics

A Novel Approach to the Unsupervised Extraction of Reliable Training Samples From Thematic Products

Claudia Paris et al.

Summary: The article introduces a novel approach to extract reliable labeled data from existing thematic products, improving the effectiveness of supervised classification algorithms and addressing the issue of insufficient traditional data collection.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

A new attention-based CNN approach for crop mapping using time series Sentinel-2 images

Yumiao Wang et al.

Summary: The study proposed a novel attention-based convolutional neural network approach (Geo-CBAM-CNN) for crop classification using time series Sentinel-2 images. By integrating geographic information of crops and enhancing the model's attention spectrally and spatially, the Geo-CBAM-CNN model achieved the best performance in large scale applications.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Review Computer Science, Artificial Intelligence

A review of deep learning methods for semantic segmentation of remote sensing imagery

Xiaohui Yuan et al.

Summary: This paper reviews the application of deep learning methods for semantic segmentation of remote sensing imagery and identifies challenges in handling non-traditional data as well as small datasets. Researchers are still facing difficulties in developing and evaluating new deep learning methods for remote sensing analysis.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Article Geography, Physical

Sentinel SAR-optical fusion for crop type mapping using deep learning and Google Earth Engine

Jarrett Adrian et al.

Summary: Accurate crop type mapping is crucial for understanding food systems and yield prediction. Recent advances in big data, high-resolution imagery, and cloud-based analytics have enabled scientists to improve crop type mapping algorithms using remote sensing, computer vision, and machine learning. Research shows that deep learning techniques, particularly when fusing multi-temporal SAR and optical data, outperform traditional methods for crop type mapping.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

添加到收藏夹

Article Agronomy

Assessing the Sentinel-2 Capabilities to Identify Abandoned Crops Using Deep Learning

Enrique Portales-Julia et al.

Summary: The abandonment of agro-forestry practices leads to abandoned land parcels that do not meet the requirements for European agricultural policy subsidies. This study proposes a methodology using remote sensing data and deep learning classifiers to detect abandoned crops in the Valencian Community, achieving a high accuracy in distinguishing between abandoned and active parcels. The results indicate that Sentinel-2 features are suitable for land use identification, including abandoned lands, and suggest the potential for implementing this remote sensing-based methodology in monitoring agricultural subsidy payments under the CAP.

AGRONOMY-BASEL (2021)

添加到收藏夹

Article Environmental Sciences

PCNet: Cloud Detection in FY-3D True-Color Imagery Using Multi-Scale Pyramid Contextual Information

Wangbin Li et al.

Summary: A novel neural network named the Pyramid Contextual Network (PCNet) was proposed for accurate cloud detection in satellite imagery, achieving better performance in cloud detection experiments.

REMOTE SENSING (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deep Learning Based Land Cover and Crop Type Classification: A Comparative Study

Asim Hameed Khan et al.

Summary: This study investigates segmentation models for landcover and crop type classification tasks, with experimental results showing good performance of the models in accurate classification across different geographical areas.

2021 INTERNATIONAL CONFERENCE ON DIGITAL FUTURES AND TRANSFORMATIVE TECHNOLOGIES (ICODT2) (2021)

添加到收藏夹

Article Environmental Sciences

An evaluation of Landsat, Sentinel-2, Sentinel-1 and MODIS data for crop type mapping

Xiao-Peng Song et al.

Summary: In this study, the utility of Landsat, Sentinel, and MODIS satellite data for mapping corn and soybean in the United States was evaluated. Results showed that individual satellite/sensor data could reach accuracies of 94.8-96.8%, while combining all data improved accuracy to 97.0%. Landsat was identified as most useful for soybean classification, Sentinel-2 for corn, and optical data were preferred over SAR data.

SCIENCE OF REMOTE SENSING (2021)

添加到收藏夹

Article Geography, Physical

ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data

Foivos Diakogiannis et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2020)

添加到收藏夹

Article Remote Sensing

An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing

Emma Izquierdo-Verdiguier et al.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2020)

添加到收藏夹

Article Environmental Sciences

Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network

Francois Waldner et al.

REMOTE SENSING OF ENVIRONMENT (2020)

添加到收藏夹

Article Environmental Sciences

DeepCropMapping: A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping

Jinfan Xu et al.

REMOTE SENSING OF ENVIRONMENT (2020)

添加到收藏夹

Article Environmental Sciences

Transfer Learning for Crop classification with Cropland Data Layer data (CDL) as training samples

Pengyu Hao et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2020)

添加到收藏夹

Review Environmental Sciences

Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review

Michel E. D. Chaves et al.

REMOTE SENSING (2020)

添加到收藏夹

Article Environmental Sciences

Accurate cloud detection in high-resolution remote sensing imagery by weakly supervised deep learning

Yansheng Li et al.

REMOTE SENSING OF ENVIRONMENT (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Histogram shape based Gaussian sub-histogram specification for contrast enhancement

S. Jayasankari et al.

INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Deep Attention and Multi-Scale Networks for Accurate Remote Sensing Image Segmentation

Xingqun Qi et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Geography, Physical

Combining Sentinel-1 and Sentinel-2 Satellite Image Time Series for land cover mapping via a multi-source deep learning architecture

Dino Ienco et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2019)

添加到收藏夹

Proceedings Paper Geosciences, Multidisciplinary

AUTOMATIC EXTRACTION OF WEAK LABELED SAMPLES FROM EXISTING THEMATIC PRODUCTS FOR TRAINING CONVOLUTIONAL NEURAL NETWORKS

Claudia Paris et al.

2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019) (2019)

添加到收藏夹

Article Geochemistry & Geophysics

Learning Aerial Image Segmentation From Online Maps

Pascal Kaiser et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2017)

添加到收藏夹

Article Geochemistry & Geophysics

Deep Learning in Remote Sensing

Xiao Xiang Zhu et al.

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE (2017)

添加到收藏夹

Article Optics

An improved histogram matching algorithm for the removal of striping noise in optical remote sensing imagery

Biao Cao et al.

OPTIK (2015)

添加到收藏夹

Article Geography, Physical

Cloud-free satellite image mosaics with regression trees and histogram matching

EH Helmer et al.

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.