Successional stages and their evolution in tropical forests using multi-temporal photogrammetric surface models and superpixels

Berveglieri, Adilson; Imai, Nilton Nobuhiro; Tommaselli, Antônio Maria Garcia; Casagrande, Baltazar; Honkavaara, Eija

doi:10.1016/j.isprsjprs.2018.11.002

Cited by 22 publications

(24 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our study area is located in the highly diverse Brazilian Atlantic forest and comprises a great number of tree species at varying successional stages, which makes tree species identification in the field challenging. Most of the study area is in the initial stage of regeneration [39], which indicates that the tree heights have a low degree of variation, as verified in Figure 5. The southernmost part of the study area is more preserved and exhibits a medium degree of regeneration [39], as supported by the existence of taller trees in Figure 5.…”

Section: Discussionmentioning

confidence: 70%

“…More than 25 tree species with a diameter at breast height (DBH) greater than 3.8 cm were detected during fieldwork [38]. Tree species were in different successional stages, with the northernmost part of the study area containing trees in the initial stage of succession and the southernmost in a more advanced stage [39]. Moreover, we located 90 trees of eight species that fragment, a protected area belonging to the Black Lion Tamarin Ecological Station.…”

Section: Reference Datamentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest

et al. 2020

Self Cite

View full text Add to dashboard Cite

The monitoring of forest resources is crucial for their sustainable management, and tree species identification is one of the fundamental tasks in this process. Unmanned aerial vehicles (UAVs) and miniaturized lightweight sensors can rapidly provide accurate monitoring information. The objective of this study was to investigate the use of multitemporal, UAV-based hyperspectral imagery for tree species identification in the highly diverse Brazilian Atlantic forest. Datasets were captured over three years to identify eight different tree species. The study area comprised initial to medium successional stages of the Brazilian Atlantic forest. Images were acquired with a spatial resolution of 10 cm, and radiometric adjustment processing was performed to reduce the variations caused by different factors, such as the geometry of acquisition. The random forest classification method was applied in a region-based classification approach with leave-one-out cross-validation, followed by computing the area under the receiver operating characteristic (AUCROC) curve. When using each dataset alone, the influence of different weather behaviors on tree species identification was evident. When combining all datasets and minimizing illumination differences over each tree crown, the identification of three tree species was improved. These results show that UAV-based, hyperspectral, multitemporal remote sensing imagery is a promising tool for tree species identification in tropical forests.

show abstract

Section: Discussionmentioning

confidence: 70%

Section: Reference Datamentioning

confidence: 99%

Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Três classes de altura foram determinadas para avaliar a evolução do crescimento vertical do dossel: baixa, média e alta, as quais têm a seguinte relação com a floresta, segundo validações realizadas em campo por Berveglieri et al (2018):…”

Section: Classificação Do Dosselunclassified

“…A partir disso, o modelo é subdividido em pequenas regiões, conforme as características locais, para que o estudo da evolução do dossel seja feito em um período de 39 anos. Alguns estudos nessa floresta tropical têm sido desenvolvidos por Berveglieri et al (2018Berveglieri et al ( , 2016 para classificar os estádios de sucessão florestal e, adicionalmente, uma análise sobre a regeneração da floresta é realizada neste trabalho.…”

Section: Introductionunclassified

Canopy Height Model Generation from Historical Images for Monitoring of Regeneration in Atlantic Rain Forest

Berveglieri¹,

Imai²,

Tommaselli³

et al. 2019

Anuário IGEO UFRJ

View full text Add to dashboard Cite

ResumoA reconstrução 3D do dossel de florestas para estudos retrospectivos em longas datas é possível a partir de fotografias aéreas históricas, usando modernos algoritmos fotogramétricos. Isto permite a análise de mudanças estruturais em florestas e o monitoramento do status de conservação ou de regeneração em áreas degradadas ao longo do tempo. Nesse contexto, este artigo realiza a aplicação de técnicas fotogramétricas, combinadas com um modelo de terreno, obtido pelo processamento de uma nuvem LASER, para a geração de modelos de alturas de árvores. Dois modelos, um datado de 1978 e outro de 2017, foram produzidos para avaliar a regeneração de uma floresta tropical de Mata Atlântica. Em seguida, uma segmentação em superpixels foi feita em ambos os modelos de alturas para formar sub-regiões homogêneas no dossel, coincidentes entre as duas datas, e permitir análises estatísticas locais, viabilizando uma classificação em três níveis de altura, a qual foi validada com dados de campo. Como resultado, verificou-se que as áreas desmatadas estão se regenerando, porém apresentam dificuldades para atingir o dossel mais alto. O erro estimado em altura no modelo de superfície histórico foi de 0,55 m, o que é aceitável para os estudos em floresta e é comparável aos resultados obtidos em floresta boreal. Palavras-chave: Fotogrametria histórica; Reconstrução 3D; Modelo de altura absoluta Abstract 3D reconstruction of forest canopy for retrospective studies over time is possible from historical aerial photographs using modern photogrammetric algorithms. This enables the structural change analysis in forested areas and the conservation or regeneration monitoring in degraded areas. In this context, the article presents an application of photogrammetric techniques (combined with a terrain model derived from a LASER point cloud) to generate tree height models. Two height models, one dating from 1978 and another from 2017, were produced to evaluate the regeneration of an Atlantic Rainforest forest. A segmentation based on superpixels was made in both heights models to subdivide the canopy into homogeneous regions (coincident between the two dates). A local statistical analysis was conducted based on a classification in three levels of heights, which was validated with data of field. As a result, it was found that deforested areas are regenerating; however, such areas present difficulties to grow to the highest canopy. The error in height, estimated in the historical surface model, was 0.55 m, which is acceptable for forest studies and is comparable to results obtained in boreal forests.

show abstract

“…On the other hand, image segmentation technology has been widely used in the field of image classification, as it can simultaneously utilize spatial and spectral information of HSIs [18][19][20][21][22][23][24][25][26]. By segmenting the image into multiple homogeneous regions and performing corresponding operations on each homogeneous region, the classification performance can be greatly improved.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Zhang

Shen

2019

Remote Sensing

View full text Add to dashboard Cite

Dimensionality reduction (DR) is an important preprocessing step in hyperspectral image applications. In this paper, a superpixelwise kernel principal component analysis (SuperKPCA) method for DR that performs kernel principal component analysis (KPCA) on each homogeneous region is proposed to fully utilize the KPCA’s ability to acquire nonlinear features. Moreover, for the proposed method, the differences in the DR results obtained based on different fundamental images (the first principal components obtained by principal component analysis (PCA), KPCA, and minimum noise fraction (MNF)) are compared. Extensive experiments show that when 5, 10, 20, and 30 samples from each class are selected, for the Indian Pines, Pavia University, and Salinas datasets: (1) when the most suitable fundamental image is selected, the classification accuracy obtained by SuperKPCA can be increased by 0.06%–0.74%, 3.88%–4.37%, and 0.39%–4.85%, respectively, when compared with SuperPCA, which performs PCA on each homogeneous region; (2) the DR results obtained based on different first principal components are different and complementary. By fusing the multiscale classification results obtained based on different first principal components, the classification accuracy can be increased by 0.54%–2.68%, 0.12%–1.10%, and 0.01%–0.08%, respectively, when compared with the method based only on the most suitable fundamental image.

show abstract

Successional stages and their evolution in tropical forests using multi-temporal photogrammetric surface models and superpixels

Cited by 22 publications

References 26 publications

Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest

Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest

Canopy Height Model Generation from Historical Images for Monitoring of Regeneration in Atlantic Rain Forest

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Contact Info

Product

Resources

About