Studies designed to discriminate different successional forest stages play a strategic role in forest management, forest policy and environmental conservation in tropical environments. The discrimination of different successional forest stages is still a challenge due to the spectral similarity among the concerned classes. Considering this, the objective of this paper was to investigate the performance of Sentinel-2 and Landsat-8 data for discriminating different successional forest stages of a patch located in a subtropical portion of the Atlantic Rain Forest in Southern Brazil with the aid of two machine learning algorithms and relying on the use of spectral reflectance data selected over two seasons and attributes thereof derived. Random Forest (RF) and Support Vector Machine (SVM) were used as classifiers with different subsets of predictor variables (multitemporal spectral reflectance, textural metrics and vegetation indices). All the experiments reached satisfactory results, with Kappa indices varying between 0.9, with Landsat-8 spectral reflectance alone and the SVM algorithm, and 0.98, with Sentinel-2 spectral reflectance alone also associated with the SVM algorithm. The Landsat-8 data had a significant increase in accuracy with the inclusion of other predictor variables in the classification process besides the pure spectral reflectance bands. The classification methods SVM and RF had similar performances in general. As to the RF method, the texture mean of the red-edge and SWIR bands were considered the most important ranked attributes for the classification of Sentinel-2 data, while attributes resulting from multitemporal bands, textural metrics of SWIR bands and vegetation indices were the most important ones in the Landsat-8 data classification.

The use of remote sensing data for tree species classification in tropical forests is still a challenging task, due to their high floristic and spectral diversity. In this sense, novel sensors on board of unmanned aerial vehicle (UAV) platforms are a rapidly evolving technology that provides new possibilities for tropical tree species mapping. Besides the acquisition of high spatial and spectral resolution images, UAV-hyperspectral cameras operating in frame format enable to produce 3D hyperspectral point clouds. This study investigated the use of UAV-acquired hyperspectral images and UAV-photogrammetric point cloud (PPC) for classification of 12 major tree species in a subtropical forest fragment in Southern Brazil. Different datasets containing hyperspectral visible/near-infrared (VNIR) bands, PPC features, canopy height model (CHM), and other features extracted from hyperspectral data (i.e., texture, vegetation indices-VIs, and minimum noise fraction-MNF) were tested using a support vector machine (SVM) classifier. The results showed that the use of VNIR hyperspectral bands alone reached an overall accuracy (OA) of 57% (Kappa index of 0.53). Adding PPC features to the VNIR hyperspectral bands increased the OA by 11%. The best result was achieved combining VNIR bands, PPC features, CHM, and VIs (OA of 72.4% and Kappa index of 0.70). When only the CHM was added to VNIR bands, the OA increased by 4.2%. Among the hyperspectral features, besides all the VNIR bands and the two VIs (NDVI and PSSR), the first four MNF features and the textural mean of 565 and 679 nm spectral bands were pointed out as more important to discriminate the tree species according to Jeffries–Matusita (JM) distance. The SVM method proved to be a good classifier for the tree species recognition task, even in the presence of a high number of classes and a small dataset.

No abstract

No abstract

No abstract

RESUMOEste trabalho objetivou avaliar o processo de restauração em uma Área de Preservação Permanente (APP) degradada em Pouso Redondo, SC, seis anos após o plantio de mudas e proteção da área. Foi realizado o levantamento da vegetação arbórea e, a partir da relação das espécies plantadas inicialmente, foi quantificado o aumento da riqueza que ocorreu por meio do estabelecimento natural de novas espécies. Foram determinadas as síndromes de dispersão de propágulos e as guildas de regeneração. Foram encontrados 918 indivíduos pertencentes a 73 espécies, sendo que 48 (65,8%) não correspondem àquelas que foram plantadas em 2007, tratando-se de novas espécies que se estabeleceram. 71,2% das espécies foram classificadas como zoocóricas e 54,8% como clímax exigente em luz. Após seis anos, o processo de restauração foi caracterizado pela tendência do aumento da riqueza e da substituição de espécies iniciais por tardias, indicando a relevância do mecanismo de regeneração natural.Palavras-chave: regeneração natural, recuperação de áreas degradadas, sucessão florestal. Evaluation of Forest Restoration in a Degraded Permanent Preservation Area in Santa Catarina State, Brazil ABSTRACTThis study evaluated the process of restoration in a degraded Permanent Preservation Area (PPA) in the municipality of Pouso Redondo, Santa Catarina state, six years after the initial plantation of trees and isolation of the area. Tree species were surveyed and increment of richness by natural establishment was quantified. Syndromes of propagule dispersion and regeneration guilds were determined. A total of 918 individuals from 73 species were found; 48 (65.8%) of them were species naturally established in the area. 71.2% of the species were classified as zoochoric (71.2%), and 54.8% as light demanding for climax. After six years, the restoration process was characterized by a trend of richness increment and replacement of initial by late successional species, indicating the relevance of the natural regeneration mechanism.

In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available.

Resumo:A classificação remota dos diferentes estádios sucessionais da vegetação ainda constitui um desafio devido à similaridade espectral destas classes. Este artigo tem o objetivo de avaliar o desempenho de imagens Landsat-8 e RapidEye para a classificação do estádio sucessional da vegetação em um fragmento de Floresta Ombrófila Mista, localizado no Parque Nacional de São Joaquim-SC. Para isto, três grupos de variáveis gerados a partir de cada imagem foram avaliados, sendo: (1) composto somente pelas bandas espectrais puras; (2) composto pelas métricas texturais GLCM geradas a partir das bandas espectrais; e (3) composto pelas variáveis dos dois grupos anteriores, além de dois índices de vegetação no caso da imagem Landsat-8, e três índices para a RapidEye. Cada grupo foi testado com os classificadores florestas randômicas (Random Forest-RF), máquinas de vetor de suporte (Support Vector Machine -SVM) e máxima verossimilhança (Maxver). Todos os experimentos alcançaram resultados satisfatórios, com índice Kappa variando de 0,66 a 0,88 e acurácia de usuário e produtor superiores a 50%. O melhor resultado alcançado foi com a imagem Landsat-8, grupo 3, associado ao algoritmo RF. A medida de importância das variáveis obtida com o algoritmo RF mostrou que as métricas texturais média, contraste e dissimilaridade destacaram-se na classificação para ambas as imagens.Palavras-chave: Sucessão florestal; Máquinas de Vetor de Suporte; Florestas Randômicas; Atributos. Abstract:The remote classification of the different vegetation successional stages still represents a challenging task in face of the similar spectral response of such classes. This paper is committed to evaluate the performance of Landsat-8 and RapidEye images in the classification of