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

Costa, Luciana Borges da; Carvalho, Osmar Luiz Ferreira de; Albuquerque, Anesmar Olino de; Gomes, Roberto Arnaldo Trancoso; Guimarães, Renato Fontes; Júnior, Osmar Abílio de Carvalho

doi:10.1080/10106049.2021.1943009

Cited by 19 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors used own neural network model for the land cover and crop type classification, as well as the method of filtering agricultural land classification maps, which allow to increase the accuracy and reduce the "noisiness" of the resulting classification raster map, which is an important prerequisite for the analysis of land cover changes. A proprietary algorithm based on a neural network with the U-Net architecture, its modification using the Efficientnet B3 encoder [35], as well as an ensemble of these networks was also used to detect forest cuts.…”

Section: Discussionmentioning

confidence: 99%

Complex method for land degradation estimation

Kussul

Shumilo

Yailymova

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Satellite data of high spatial resolution have become publicly available since the launch of the EU Copernicus program, and their automated processing methods for solving a large number of diverse applied problems have received further development. Our task in this article is to analyze the dynamics of the land degradation level using land degradation assessment approaches based on satellite monitoring and taking appropriate measures. Within this work authors have developed the complex method for land degradation estimation that uses different schemes for separate land cover and crop types at country level based on satellite and modelling data. The deforestation was considered as land degradation in forest areas. For agricultural land, land degradation is determined by comparing the actual leaf area index (LAI) with the simulated (ideal) LAI, and for uncultivated land it is based on normalized difference vegetation index trend analysis from satellite information.

show abstract

Section: Discussionmentioning

confidence: 99%

Complex method for land degradation estimation

Kussul

Shumilo

Yailymova

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Some studies have explored the ability of the DeepLabV3+ algorithm to identify vegetation [42,43], and the DeepLabV3+ algorithm had problems of unclear boundary segmentation and small area misjudgment [44]. This paper proposed an improved algorithm, MCCUNet, by replacing part of the convolution layers of Xception in DeepLabV3+ with mix depth-wise separable convolutions and adding two additional layers of low-level features to the decoder.…”

Section: Discussionmentioning

confidence: 99%

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

Sun

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Mangrove-forest classification by using deep learning algorithms has attracted increasing attention but remains challenging. The current studies on the transfer classification of mangrove communities between different regions and different sensors are especially still unclear. To fill the research gap, this study developed a new deep-learning algorithm (encoder–decoder with mixed depth-wise convolution and cascade upsampling, MCCUNet) by modifying the encoder and decoder sections of the DeepLabV3+ algorithm and presented three transfer-learning strategies, namely frozen transfer learning (F-TL), fine-tuned transfer learning (Ft-TL), and sensor-and-phase transfer learning (SaP-TL), to classify mangrove communities by using the MCCUNet algorithm and high-resolution UAV multispectral images. This study combined the deep-learning algorithms with recursive feature elimination and principal component analysis (RFE–PCA), using a high-dimensional dataset to map and classify mangrove communities, and evaluated their classification performance. The results of this study showed the following: (1) The MCCUNet algorithm outperformed the original DeepLabV3+ algorithm for classifying mangrove communities, achieving the highest overall classification accuracy (OA), i.e., 97.24%, in all scenarios. (2) The RFE–PCA dimension reduction improved the classification performance of deep-learning algorithms. The OA of mangrove species from using the MCCUNet algorithm was improved by 7.27% after adding dimension-reduced texture features and vegetation indices. (3) The Ft-TL strategy enabled the algorithm to achieve better classification accuracy and stability than the F-TL strategy. The highest improvement in the F1–score of Spartina alterniflora was 19.56%, using the MCCUNet algorithm with the Ft-TL strategy. (4) The SaP-TL strategy produced better transfer-learning classifications of mangrove communities between images of different phases and sensors. The highest improvement in the F1–score of Aegiceras corniculatum was 19.85%, using the MCCUNet algorithm with the SaP-TL strategy. (5) All three transfer-learning strategies achieved high accuracy in classifying mangrove communities, with the mean F1–score of 84.37%~95.25%.

show abstract

“…A traditional way is to take the mean average among the overlapping pixels. Moreover, this approach reduces errors at the borders of the frames, exemplified in recent works [106], [107], [108]. A drawback of using this method is the computational cost.…”

Section: ) Large Image Classificationmentioning

confidence: 98%

“…The large-area predictions using DL is an important topic that may be improved. Previous work shows that sliding windows with low step values correct errors at frame edges, improving results [107], [108], [106], [90]. It takes about one hour to classify our entire study area (57,856 x 42,496pixel dimensions) using a 128-pixel stride.…”

Section: B Box-free Instance Segmentationmentioning

confidence: 99%

Bounding Box-Free Instance Segmentation Using Semi-Supervised Iterative Learning for Vehicle Detection

Carvalho

Albuquerque

Santana

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Vehicle classification is a hot computer vision topic, with studies ranging from ground-view to top-view imagery. Topview images allow understanding city patterns, traffic management, among others. However, there are some difficulties for pixel-wise classification: (a) most vehicle classification studies use object detection methods, and most publicly available datasets are designed for this task, (b) creating instance segmentation datasets is laborious, and (c) traditional instance segmentation methods underperform on this task since the objects are small. Thus, the present research objectives are: (1) propose a novel semi-supervised iterative learning approach using GIS software, (2) propose a box-free instance segmentation approach, and (3) provide a city-scale vehicle dataset. The iterative learning procedure considered: (1) labeling a few vehicles from the entire scene, (2) choosing training samples near those areas, ( 3) training the DL model (U-net with Efficient-net-B7 backbone), (4) classifying the whole scene, (5) converting the predictions into shapefile, (6) correcting areas with wrong predictions, (7) including them in the training data, (8) repeating until results are satisfactory. We considered vehicle interior and borders to separate instances using a semantic segmentation model. When removing the borders, the vehicle interior becomes isolated, allowing for unique object identification. Our procedure is very efficient and accurate for generating data iteratively, which resulted in 122,567 mapped vehicles. Metrics-wise, our method presented higher IoU when compared to box-based methods (82% against 72%), and per-object metrics surpassed 90% for precision and recall.

show abstract

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

Cited by 19 publications

References 39 publications

Complex method for land degradation estimation

Complex method for land degradation estimation

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

Bounding Box-Free Instance Segmentation Using Semi-Supervised Iterative Learning for Vehicle Detection

Contact Info

Product

Resources

About