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.
The availability of remote-sensing multisource data from optical-based satellite sensors has created new opportunities and challenges for forest monitoring in the Amazon Biome. In particular, change-detection analysis has emerged in recent decades to monitor forest-change dynamics, supporting some Brazilian governmental initiatives such as PRODES and DETER projects for biodiversity preservation in threatened areas. In recent years fully convolutional network architectures have witnessed numerous proposals adapted for the change-detection task. This paper comprehensively explores state-of-the-art fully convolutional networks such as U-Net, ResU-Net, SegNet, FC-DenseNet, and two DeepLabv3+ variants on monitoring deforestation in the Brazilian Amazon. The networks’ performance is evaluated experimentally in terms of Precision, Recall, -score, and computational load using satellite images with different spatial and spectral resolution: Landsat-8 and Sentinel-2. We also include the results of an unprecedented auditing process performed by senior specialists to visually evaluate each deforestation polygon derived from the network with the highest accuracy results for both satellites. This assessment allowed estimation of the accuracy of these networks simulating a process “in nature” and faithful to the PRODES methodology. We conclude that the high resolution of Sentinel-2 images improves the segmentation of deforestation polygons both quantitatively (in terms of -score) and qualitatively. Moreover, the study also points to the potential of the operational use of Deep Learning (DL) mapping as products to be consumed in PRODES.
27 October 2020 in IEEE Geoscience and Remote Sensing Letters
Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed generator and discriminator networks rely on atrous convolutions and incorporate an atrous spatial pyramid pooling (ASPP) module to enhance fine details in the generated optical image by exploiting spatial context at multiple scales. This letter reports experiments carried out to assess the performance of atrous-cGAN for the synthesis of Landsat-8 images from Sentinel-1A data based on three public data sets. The experimental analysis indicated that the atrous-cGAN consistently outperformed the classical pix2pix counterpart in terms of visual quality, similar to the true optical image, and as a feature learning tool for semantic segmentation.
Reliable crop mapping is an essential tool for agricultural monitoring and food security. In the tropics, where cloud cover massively affects optical imagery, synthetic-aperture radar (SAR) imagery emerged as a cost-effective alternative for discriminating crops in large scale agricultural regions. Recently, unsupervised deep clustering approaches have emerged as a competitive alternative in several different applications with labeling restrictions. This paper explores this literature and evaluates the feasibility of such methods applied to crop classification in a tropical region from multi-temporal SAR image sequences. We focus on the k-Means-related deep clustering methods, specifically, on Deep Embedding Clustering and Deep K-Means. We report experiments conducted on a public dataset from a tropical region with highly complex crop dynamics. In our experiments the tested unsupervised approaches managed to deliver nearly 78% of supervised counterparts for this task 11 The source codes are available at https:/github.com/DLoboT/Project_DL_2020.
1 January 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Background: Booster vaccine hesitancy poses a challenge to sustained COVID-19 immunization even among individuals who accepted primary vaccination. This study examined associated factors and patterns of change in vaccine attitudes among university students in Ontario, Canada. Methods: A cross-sectional survey dataset was analyzed using validated psychometric scales to measure hesitancy toward primary and booster COVID-19 vaccination. Changes in hesitancy were operationalized as the continuous difference between booster and primary scores (). Gradient Boosting and XGBoost regression models were fitted to estimate from demographic characteristics (age, gender, socioeconomic status), vaccination history, and attitudinal constructs including complacency, confidence in vaccine safety, and perceived necessity of vaccination. Predictor contributions were assessed using SHapley Additive exPlanations, and Gaussian Mixture Modeling was employed to identify latent profiles among students with increased hesitancy. Results: A substantial proportion of students demonstrated higher hesitancy toward booster doses. Attitudinal factors, particularly complacency and safety perceptions, were the most influential predictors of increased hesitancy, whereas sociodemographic characteristics showed limited influence. Three distinct profiles of booster hesitancy were identified, reflecting heterogeneous patterns of vaccine attitudes and behaviors. Conclusions: These findings suggest that booster hesitancy in the study population is primarily associated with modifiable perceptions and can be effectively characterized using machine learning approaches that may inform targeted public health communication strategies.