☆ 4.7 Article

Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography

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 Computer Science, Artificial Intelligence

UAVformer: A Composite Transformer Network for Urban Scene Segmentation of UAV Images

Shi Yi et al.

Summary: This study proposes a novel composite transformer network for urban scenes segmentation of UAV (Unmanned aerial vehicle) image. The network utilizes adaptive multi-level features fusion, contextual information, and local information to effectively extract features of large scale variation urban ground scenes. Position attention modules and a V-shaped decoder are incorporated to enhance spatial attention and achieve accurate dense prediction. Experimental results demonstrate the effectiveness and superiority of the proposed network structure over state-of-the-art methods on public available urban scenes segmentation datasets for UAV imagery.

PATTERN RECOGNITION (2023)

添加到收藏夹

Article Environmental Sciences

Combining Object-Oriented and Deep Learning Methods to Estimate Photosynthetic and Non-Photosynthetic Vegetation Cover in the Desert from Unmanned Aerial Vehicle Images with Consideration of Shadows

Jie He et al.

Summary: In the Mu Us Desert of northern China, the feasibility and efficiency of shadow-sensitive PV/NPV classification using three deep learning models (DeepLabV3+, PSPNet, and U-Net) were explored. The DeepLabV3+ model achieved the highest accuracy, exceeding 95% for PV and bare soil under light conditions and achieving an overall accuracy of 94.3% for the three categories of PV/NPV/BS. Compared to traditional machine learning methods, this approach significantly improves classification accuracy and enables the semi-automatic extraction of PV/NPV areas, which is valuable for land-use planning and land resource management.

REMOTE SENSING (2023)

添加到收藏夹

Article Environmental Sciences

An ensemble architecture of deep convolutional Segnet and Unet networks for building semantic segmentation from high-resolution aerial images

Abolfazl Abdollahi et al.

Summary: Extracting building features from high-resolution aerial imagery is challenging due to obstacles such as shadows, trees, and cars. This study proposes a new deep learning method, Seg-Unet, which combines Segnet and Unet techniques to improve the accuracy of building extraction from high-resolution remote sensing images. The proposed method outperforms other methods and achieves 92.73% accuracy on the Massachusetts building dataset.

GEOCARTO INTERNATIONAL (2022)

添加到收藏夹

Article Environmental Sciences

Mapping grassland mowing events across Germany based on combined Sentinel-2 and Landsat 8 time series

Marcel Schwieder et al.

Summary: Spatially explicit knowledge on grassland extent and management is critical to understand and monitor the impact of grassland use intensity on ecosystem services and biodiversity. This study used Sentinel-2 and Landsat 8 data to develop an algorithm for detecting mowing events in Germany from 2017 to 2020. The results showed that the detection of mowing events was influenced by data availability and regional variations, but the approach was still able to map the intensity of grassland management throughout large areas and identify regional differences.

REMOTE SENSING OF ENVIRONMENT (2022)

添加到收藏夹

Article Environmental Sciences

Continuous monitoring of forest change dynamics with satellite time series

Mathieu Decuyper et al.

Summary: This study presents a new change detection algorithm that can accurately track deforestation and regrowth of forests using satellite data. The algorithm performs well across different forest types and change conditions, and can be used to assess carbon accumulation and forest restoration targets of secondary forests.

REMOTE SENSING OF ENVIRONMENT (2022)

添加到收藏夹

Article Environmental Sciences

Detection of Invasive Black Locust (Robinia pseudoacacia) in Small Woody Features Using Spatiotemporal Compositing of Sentinel-2 Data

Tomas Rusnak et al.

Summary: Recognition and mapping of invasive species, such as black locust, in small woody features are crucial for managing and protecting native species. This study demonstrates the utility of spatiotemporal compositing of Sentinel-2 products for accurately mapping black locust in agricultural landscapes. The results show that temporal aggregation of monthly composites stacked into seasonal time series datasets provides consistently high overall accuracies.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Superpixel-Based Attention Graph Neural Network for Semantic Segmentation in Aerial Images

Qi Diao et al.

Summary: In this paper, the authors propose a Superpixel-based Attention Graph Neural Network (SAGNN) for semantic segmentation of high spatial resolution aerial images. The network utilizes attention mechanism and recursive functions to update hidden representations of nodes, extract high-quality features, and achieve accurate predictions by maintaining object boundaries through superpixels.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Near Real-Time Change Detection System Using Sentinel-2 and Machine Learning: A Test for Mexican and Colombian Forests

Ana Maria Pacheco-Pascagaza et al.

Summary: The commitment by over 100 governments to end deforestation by 2030 requires more effective forest monitoring systems. Near real-time change detection of forest cover loss enables timely monitoring and responses, and the Copernicus Sentinel-2 satellites provide suitable data for this purpose. The proposed NRT change detection system based on these satellites has been evaluated and proven to accurately detect forest cover loss and other vegetation changes. It is also scalable and adaptable to larger regions and countries.

REMOTE SENSING (2022)

添加到收藏夹

Article Agriculture, Multidisciplinary

Early detection and identification of grape diseases using convolutional neural networks

RajinderKumar M. Math et al.

Summary: Crop protection aims to develop an agriculture system resilient to threats that cause sub-optimal crop growth. This research focuses on developing a deep convolutional neural network model to accurately identify and classify grape diseases based on RGB leaf images. The model achieved an accuracy of 99.34% and demonstrated high precision, recall, and F1 score.

JOURNAL OF PLANT DISEASES AND PROTECTION (2022)

添加到收藏夹

Article Environmental Sciences

Efficient Depth Fusion Transformer for Aerial Image Semantic Segmentation

Li Yan et al.

Summary: This paper proposes a novel and efficient depth fusion transformer network for aerial image segmentation. By fusing depth features and color features, the performance of semantic segmentation is improved.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Woody Plant Encroachment: Evaluating Methodologies for Semiarid Woody Species Classification from Drone Images

Horia G. Olariu et al.

Summary: This study evaluated the ability of very high resolution drone imagery to accurately map woody plant species encroaching on semiarid grasslands. The findings showed that drone imagery can provide highly accurate classifications of woody plant species, surpassing the results achieved by aerial and drone imagery using hyperspectral sensors in more diverse landscapes.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data

Jie Yu et al.

Summary: The classification of urban land-use information is crucial for applications such as urban planning and administration. This paper presents a combined convolutional neural network named DUA-Net for complex and diverse urban land-use classification. By using GIS data, a well-tagged and high-resolution urban land-use image dataset is created, and the DUA-Net effectively fuses multi-source semantic information using channel attention. The proposed method achieves high-precision urban land-use classification, which is valuable for urban planning and national land resource surveying.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Fully Deformable Convolutional Network for Ship Detection in Remote Sensing Imagery

Hongwei Guo et al.

Summary: A novel method for ship detection in high spatial resolution remote sensing imagery is proposed, which utilizes deformable convolution networks to effectively extract features at different scales and orientations. Experimental results on public remote sensing datasets demonstrate the effectiveness of the proposed method in accurately detecting ships in remote sensing applications.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Development of Semantic Maps of Vegetation Cover from UAV Images to Support Planning and Management in Fine-Grained Fire-Prone Landscapes

Bianka Trencanova et al.

Summary: This study proposes a method for segmenting shrub cover in high-resolution UAV images by exploring the best practices to train a convolutional neural network. Data augmentation, patch cropping, and rescaling were identified as the most effective practices. Despite being trained on a relatively small dataset, the developed classification model achieved a high average F1 score on separate test datasets.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Estimating Fractional Vegetation Cover Changes in Desert Regions Using RGB Data

Lu Xie et al.

Summary: Fractional vegetation cover (FVC) is an important indicator of ecosystem changes. This study used satellite remote sensing and machine learning algorithms to estimate FVC in desert regions. The results showed that RGB images are suitable for mapping FVC, and the vegetation cover in the study area changed significantly from 2006 to 2019. Understanding these changes is crucial for understanding the evolution of desert ecosystems.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Continuous Land Cover Change Detection in a Critically Endangered Shrubland Ecosystem Using Neural Networks

Glenn R. Moncrieff

Summary: Existing efforts in monitoring land cover change have focused mostly on forested ecosystems, but this study demonstrates the potential of using neural networks to accurately detect transformation in a critically endangered shrubland ecosystem within a few days of its occurrence. The trained models achieved a high accuracy in detecting land cover change events, surpassing the performance of methods designed for forested ecosystems. Continuous monitoring of habitat loss in non-forest ecosystems can be facilitated with accurately dated datasets and machine learning classifiers.

REMOTE SENSING (2022)

添加到收藏夹

Article Geography, Physical

Object-based change detection for vegetation disturbance and recovery using Landsat time series

Zheng Wang et al.

Summary: Accurately characterizing historical trends in vegetation change at the landscape scale is important for resource management and ecological assessment. Existing pixel-based change detection methods struggle to provide reliable estimates due to neglecting spatial contextual information and being affected by noise. This study proposes a new approach, object-based change detection of trends in disturbance and recovery (Object-LT), which combines object-based image analysis and the LandTrendr algorithm. Applied to the ecologically fragile region of Guyuan, Ning Xia, this approach accurately identifies disturbance and recovery trends in vegetation and improves user accuracy.

GISCIENCE & REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Comparison of Different Transfer Learning Methods for Classification of Mangrove Communities Using MCCUNet and UAV Multispectral Images

Yuyang Li et al.

Summary: This study developed a new deep learning algorithm, MCCUNet, and presented three transfer learning strategies to classify mangrove communities. The results showed that MCCUNet outperformed other algorithms in terms of classification accuracy and performance. Dimension reduction improved the classification performance of deep learning algorithms.

REMOTE SENSING (2022)

添加到收藏夹

Review Environmental Sciences

Monitoring and Mapping Vegetation Cover Changes in Arid and Semi-Arid Areas Using Remote Sensing Technology: A Review

Raid Almalki et al.

Summary: Vegetation cover change is an important indicator for monitoring environmental quality, especially in arid and semi-arid regions. Remote sensing data can be used to monitor and map vegetation cover changes, and their accuracy can be improved by combining them with ground truth data. Additionally, ancillary data can help detect vegetation cover changes at the species level.

REMOTE SENSING (2022)

添加到收藏夹

Article Environmental Sciences

Hedgerow object detection in very high-resolution satellite images using convolutional neural networks

Steve Ahlswede et al.

Summary: This study demonstrates the successful application of transfer learning in neural networks for hedgerow mapping, outperforming traditional methods. RGB sensors can be used for hedgerow detection, and training with images across seasons yields better results. Data augmentations impacting object geometries are beneficial for improving network performance.

JOURNAL OF APPLIED REMOTE SENSING (2021)

添加到收藏夹

Article Environmental Sciences

Mapping Riparian Habitats of Natura 2000 Network (91E0*, 3240) at Individual Tree Level Using UAV Multi-Temporal and Multi-Spectral Data

Elena Belcore et al.

Summary: In this study, vegetation species of riparian habitats in North-West Italy were monitored at individual tree level using machine learning and a multi-temporal phenology-based approach via UAV. The results showed better performance in multi-epoch phenology-based classification compared to single-epoch classification, with certain vegetation classes significantly influenced by multi-temporality, resulting in an increase in F1 score of 0.3 points.

REMOTE SENSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CT-UNet: Context-Transfer-UNet for Building Segmentation in Remote Sensing Images

Sheng Liu et al.

Summary: The paper proposes a UNet-based network called Context-Transfer-UNet (CT-UNet) to address the challenge of accurately segmenting buildings in remote sensing images. By introducing Dense Boundary Block and Spatial Channel Attention Block, the CT-UNet outperforms baseline models and achieves remarkable results in IoU and F1-score on multiple datasets.

NEURAL PROCESSING LETTERS (2021)

添加到收藏夹

Article Environmental Sciences

Shrub decline and expansion of wetland vegetation revealed by very high resolution land cover change detection in the Siberian lowland tundra

Runa I. Magnusson et al.

Summary: Vegetation changes in the Arctic are impacted by permafrost degradation, with a need for mechanistic understanding to accurately assess responses to climate change. The understudied Siberian Arctic region shows spatial variability in browning trends, suggesting localized impacts.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

添加到收藏夹

Article Environmental Sciences

Efficient Transformer for Remote Sensing Image Segmentation

Zhiyong Xu et al.

Summary: This study introduces a novel Efficient Transformer model to address edge classification issues in remote sensing image semantic segmentation, significantly improving accuracy while balancing computational complexity. By accelerating inference speed and introducing edge enhancement methods, improvements were achieved on the Potsdam and Vaihingen datasets.

REMOTE SENSING (2021)

添加到收藏夹

Article Environmental Sciences

Development and Application of Earth Observation Based Machine Learning Methods for Characterizing Forest and Land Cover Change in Dilijan National Park of Armenia between 1991 and 2019

Nathalie Morin et al.

Summary: The study monitored forest degradation and deforestation in Dilijan National Park of Armenia over the past 30 years using remote sensing technology. Results showed high accuracy in forest density modeling and land cover classification. While protection measures have had some success, anthropogenic pressure remains a threat that needs to be addressed.

REMOTE SENSING (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Toward a High Spatial Resolution Aerial Monitoring Network for Nature Conservation-How Can Remote Sensing Help Protect Natural Areas?

Gabor Bako et al.

Summary: Aerial surveys combined with remote sensing technology can effectively monitor temporal changes in natural features, enabling precise monitoring of vegetation species and forest edge dynamics through high-resolution digital photos and spatial data models.

SUSTAINABILITY (2021)

添加到收藏夹

Article Remote Sensing

Comparison of RGB and Multispectral Unmanned Aerial Vehicle for Monitoring Vegetation Coverage Changes on a Landslide Area

Flavio Furukawa et al.

Summary: This study compared the capabilities of RGB and Multispectral UAVs in characterizing vegetation in landslide areas, finding higher overall accuracy with the Multispectral UAV. Despite lower overall accuracy, the vegetation class of the RGB UAV showed high producer's and user's accuracy over time, indicating reliability. Image quality, with higher accuracy values on cloudy days, played a crucial role in determining accuracy levels.

DRONES (2021)

添加到收藏夹

Article Environmental Studies

Monitoring Invasive Plant Species Using Hyperspectral Remote Sensing Data

Levente Papp et al.

Summary: The study focused on mapping and monitoring the spread of the common milkweed, an invasive plant species in Europe, in Hungary. By analyzing hyperspectral remote sensing data and applying classification algorithms, the researchers successfully distinguished common milkweed individuals with high accuracy, providing a new method for invasive species monitoring.

LAND (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Fine-scale detection of vegetation in semi-arid mountainous areas with focus on riparian landscapes using Sentinel-2 and UAV data

Ardalan Daryaei et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2020)

添加到收藏夹

Review Environmental Sciences

lidR: An R package for analysis of Airborne Laser Scanning (ALS) data

Jean-Romain Roussel et al.

REMOTE SENSING OF ENVIRONMENT (2020)

添加到收藏夹

Article Computer Science, Information Systems

Semantic Segmentation of Remote Sensing Images Using Transfer Learning and Deep Convolutional Neural Network With Dense Connection

Binge Cui et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Ecology

Mapping vegetation types in semi-arid riparian regions using random forest and object-based image approach: A case study of the Colorado River Ecosystem, Grand Canyon, Arizona

Uyen Nguyen et al.

ECOLOGICAL INFORMATICS (2019)

添加到收藏夹

Article Forestry

The Use of Low-Altitude UAV Imagery to Assess Western Juniper Density and Canopy Cover in Treated and Untreated Stands

Nicole Durfee et al.

FORESTS (2019)

添加到收藏夹

Article Geography, Physical

Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks

Michael Wurm et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2019)

添加到收藏夹

Article Ecology

Unmanned Aerial Vehicle - Based Rangeland Monitoring: Examining a Century of Vegetation Changes

Temuulen Ts Sankey et al.

RANGELAND ECOLOGY & MANAGEMENT (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

High-Resolution Aerial Images Semantic Segmentation Using Deep Fully Convolutional Network With Channel Attention Mechanism

Haifeng Luo et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2019)

添加到收藏夹

Article Geography, Physical

TreeUNet: Adaptive Tree convolutional neural networks for subdecimeter aerial image segmentation

Kai Yue et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery

Teja Kattenborn et al.

SCIENTIFIC REPORTS (2019)

添加到收藏夹

Article Computer Science, Information Systems

GEOBIA at the Terapixel Scale: Toward Efficient Mapping of Small Woody Features from Heterogeneous VHR Scenes

Francois Merciol et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2019)

添加到收藏夹

Article Agriculture, Multidisciplinary

A novel approach for vegetation classification using UAV-based hyperspectral imaging

Tetsuro Ishida et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2018)

添加到收藏夹

Article Engineering, Electrical & Electronic

Tree Species Extraction and Land Use/Cover Classification From High-Resolution Digital Orthophoto Maps

Akhtar Jamil et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2018)

添加到收藏夹

Article Remote Sensing

Comparative study of three satellite image time-series decomposition methods for vegetation change detection

Ali Ben Abbes et al.

EUROPEAN JOURNAL OF REMOTE SENSING (2018)

添加到收藏夹

Article Environmental Sciences

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

Shuo Liu et al.

REMOTE SENSING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

添加到收藏夹

Article Geography, Physical

Wide-area mapping of small-scale features in agricultural landscapes using airborne remote sensing

Jerome O'Connell et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2015)

添加到收藏夹

Article Environmental Sciences

Mapping trees outside forests using high-resolution aerial imagery: a comparison of pixel- and object-based classification approaches

Dacia M. Meneguzzo et al.

ENVIRONMENTAL MONITORING AND ASSESSMENT (2013)

添加到收藏夹

Article Environmental Sciences

An Object-Based Approach for Mapping Shrub and Tree Cover on Grassland Habitats by Use of LiDAR and CIR Orthoimages

Thomas Hellesen et al.

REMOTE SENSING (2013)

添加到收藏夹

Article Geochemistry & Geophysics

Automatic Mapping of Linear Woody Vegetation Features in Agricultural Landscapes Using Very High Resolution Imagery

Selim Aksoy et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2010)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.