Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery.

This study proposes and evaluates five deep fully convolutional networks (FCNs) for the semantic segmentation of a single tree species: SegNet, U-Net, FC-DenseNet, and two DeepLabv3+ variants. The performance of the FCN designs is evaluated experimentally in terms of classification accuracy and computational load. We also verify the benefits of fully connected conditional random fields (CRFs) as a post-processing step to improve the segmentation maps. The analysis is conducted on a set of images captured by an RGB camera aboard a UAV flying over an urban area. The dataset also contains a mask that indicates the occurrence of an endangered species called Dipteryx alata Vogel, also known as cumbaru, taken as the species to be identified. The experimental analysis shows the effectiveness of each design and reports average overall accuracy ranging from 88.9% to 96.7%, an F1-score between 87.0% and 96.1%, and IoU from 77.1% to 92.5%. We also realize that CRF consistently improves the performance, but at a high computational cost.

Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs.

Detection and classification of tree species from remote sensing data were performed using mainly multispectral and hyperspectral images and Light Detection And Ranging (LiDAR) data. Despite the comparatively lower cost and higher spatial resolution, few studies focused on images captured by Red-Green-Blue (RGB) sensors. Besides, the recent years have witnessed an impressive progress of deep learning methods for object detection. Motivated by this scenario, we proposed and evaluated the usage of Convolutional Neural Network (CNN)-based methods combined with Unmanned Aerial Vehicle (UAV) high spatial resolution RGB imagery for the detection of law protected tree species. Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet. A dataset was built to assess the selected methods, comprising 392 RBG images captured from August 2018 to February 2019, over a forested urban area in midwest Brazil. The target object is an important tree species threatened by extinction known as Dipteryx alata Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.

Estimating Stand Height and Tree Density in Pinus taeda plantations using in-situ data, airborne LiDAR and k-Nearest Neighbor Imputation.

Accurate forest inventory is of great economic importance to optimize the entire supply chain management in pulp and paper companies. The aim of this study was to estimate stand dominate and mean heights (HD and HM) and tree density (TD) of Pinus taeda plantations located in South Brazil using in-situ measurements, airborne Light Detection and Ranging (LiDAR) data and the non- k-nearest neighbor (k-NN) imputation. Forest inventory attributes and LiDAR derived metrics were calculated at 53 regular sample plots and we used imputation models to retrieve the forest attributes at plot and landscape-levels. The best LiDAR-derived metrics to predict HD, HM and TD were H99TH, HSD, SKE and HMIN. The Imputation model using the selected metrics was more effective for retrieving height than tree density. The model coefficients of determination (adj.R2) and a root mean squared difference (RMSD) for HD, HM and TD were 0.90, 0.94, 0.38m and 6.99, 5.70, 12.92%, respectively. Our results show that LiDAR and k-NN imputation can be used to predict stand heights with high accuracy in Pinus taeda. However, furthers studies need to be realized to improve the accuracy prediction of TD and to evaluate and compare the cost of acquisition and processing of LiDAR data against the conventional inventory procedures.

Estimating Stand Height and Tree Density in Pinus taeda plantations using in-situ data, airborne LiDAR and k-Nearest Neighbor Imputation

ABSTRACT Accurate forest inventory is of great economic importance to optimize the entire supply chain management in pulp and paper companies. The aim of this study was to estimate stand dominate and mean heights (HD and HM) and tree density (TD) of Pinus taeda plantations located in South Brazil using in-situ measurements, airborne Light Detection and Ranging (LiDAR) data and the non- k-nearest neighbor (k-NN) imputation. Forest inventory attributes and LiDAR derived metrics were calculated at 53 regular sample plots and we used imputation models to retrieve the forest attributes at plot and landscape-levels. The best LiDAR-derived metrics to predict HD, HM and TD were H99TH, HSD, SKE and HMIN. The Imputation model using the selected metrics was more effective for retrieving height than tree density. The model coefficients of determination (adj.R2) and a root mean squared difference (RMSD) for HD, HM and TD were 0.90, 0.94, 0.38m and 6.99, 5.70, 12.92%, respectively. Our results show that LiDAR and k-NN imputation can be used to predict stand heights with high accuracy in Pinus taeda. However, furthers studies need to be realized to improve the accuracy prediction of TD and to evaluate and compare the cost of acquisition and processing of LiDAR data against the conventional inventory procedures.

Changes in permanent preservation areas in rural properties of the Santa Catarina state southern plateau according to the laws No. 4,771 and 12,651 / Variação nas áreas de preservação permanente em imóveis rurais do Planalto Sul Catarinense segundo as Leis nº 4.771 e 12.651

ABSTRACT: This research aimed to study the parameters of the current and past Brazilian Forest Act based on the Federal Laws No. 4,771 and 12,651 for the determination of the permanent preservation areas (PPA). Water springs and streams for 68 rural properties located at the Santa Catarina State Southern Plateau were considered. Thematic land use/land cover (LULC) as well as PPA maps from the visual interpretation of ortho rectified aerial images were elaborated. The PPA percentage for recovering over consolidated rural areas is directly proportional to both fiscal module size and area of the rural property. Comparing to the Law No. 4,771, there was a significant reduction in the PPA to be recovered on consolidated rural areas. In small rural properties there was an average reduction ranging from 54.6% to 81.8%. A total of 122,372 hectares (7.6% of the total area) characterized as PPA in consolidated rural areas can now be used economically.

RESUMO: Estudou-se os parâmetros das Leis Federais no4.771 e 12.651 para a delimitação de PPA de nascentes e cursos d'água em 68 imóveis rurais dos municípios da Região Serrana do Estado de Santa Catarina. Elaboraram-se mapas temáticos da cobertura da terra com as áreas de PPA, a partir da interpretação de imagens aéreas ortorretificadas. Os resultados mostram que o percentual de PPA, a recompor em área rural consolidada, está diretamente relacionado com a área do imóvel e com o tamanho do módulo fiscal do município onde se encontra. Comparando-se com a Lei no4.771, houve redução significativa nas PPA a serem recompostas em áreas rurais consolidadas. Em pequenas propriedades rurais, a redução média variou de 54,6 a 81,8%. Estima-se que 122.372 hectares de terras da região serrana (7,6% da área), caracterizadas como PPA, em área rural consolidada, podem continuar sendo exploradas economicamente.