Guilherme N. DeSouza
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guilherme N. DeSouza has a total of 98 co-authors. Here are the top co-authors by number of shared publications:
Gbenga Omotara
Vision-Guided and Intelligent Robotics Lab (ViGIR University of Missouri Columbia MO USA
4 shared publicationsRamy Farag
Vision-Guided and Intelligent Robotics Lab (ViGIR University of Missouri Columbia MO USA
3 shared publicationsSeyed Mohamad Ali Tousi
3 shared publications- Adriano Madureira dos Santos
Operational Research Laboratory (LPO) Federal University of Pará (UFPA) Belém Brazil
2 shared publications - Jared E. Decker
Genetics Area Program, University of Missouri; Columbia, Missouri 65211, United States
2 shared publications - Jean Arthur Costa Dias
UFPA
2 shared publications
Latest Publications
- Open Access
- 5 November 2026
- Published by Wiley in Journal of Medical Virology
- Vol. 98 (11)
Quantifying the Unseen Dengue Burden: A Municipality‐Level Ascertainment Surface for Pará State, Brazilian Amazon
Passive dengue surveillance systematically underestimates true disease burden, and this under‐ascertainment is spatially structured rather than random. In the Brazilian Amazon, municipalities with the weakest notification infrastructure tend to coincide with those presenting the most favorable environmental conditions for vector proliferation. This work investigates whether municipalities with more active surveillance can serve as a structural proxy to infer cases in less active regions, allowing for the identification of localities where notification capacity fails to reflect true transmission. Building on this framework, this study aimed to estimate municipality‐level dengue under‐ascertainment in Pará by disentangling surveillance capacity from true transmission intensity through a Bayesian spatiotemporal model. A BYM2‐ST model was fitted to dengue notification data from municipalities of Pará, from January 2018 to December 2024, integrating socioeconomic indicators and time‐varying climatic covariates. A spatial ascertainment ratio was derived for each municipality from the model, benchmarking observed notifications against the structurally expected counterfactual. The results showed that only 20.1% of municipalities reported notification counts within the expected range, while 40.3% showed statistically supported evidence of under‐ascertainment.
- 5 November 2026
- Published by Wiley in Journal of Medical Virology
- Vol. 98 (11)
Open AccessQuantifying the Unseen Dengue Burden: A Municipality‐Level Ascertainment Surface for Pará State, Brazilian Amazon
Passive dengue surveillance systematically underestimates true disease burden, and this under‐ascertainment is spatially structured rather than random. In the Brazilian Amazon, municipalities with the weakest notification infrastructure tend to coincide with those presenting the most favorable environmental conditions for vector proliferation. This work investigates whether municipalities with more active surveillance can serve as a structural proxy to infer cases in less active regions, allowing for the identification of localities where notification capacity fails to reflect true transmission. Building on this framework, this study aimed to estimate municipality‐level dengue under‐ascertainment in Pará by disentangling surveillance capacity from true transmission intensity through a Bayesian spatiotemporal model. A BYM2‐ST model was fitted to dengue notification data from municipalities of Pará, from January 2018 to December 2024, integrating socioeconomic indicators and time‐varying climatic covariates. A spatial ascertainment ratio was derived for each municipality from the model, benchmarking observed notifications against the structurally expected counterfactual. The results showed that only 20.1% of municipalities reported notification counts within the expected range, while 40.3% showed statistically supported evidence of under‐ascertainment.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 170711-170735
Modeling Time-Varying Uncertainty in Dengue Dynamics Under Climatic Variability: A Hybrid ARIMAX–GARCH-Type Approach in an Amazonian Setting
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 170711-170735
Open AccessModeling Time-Varying Uncertainty in Dengue Dynamics Under Climatic Variability: A Hybrid ARIMAX–GARCH-Type Approach in an Amazonian Setting
- Open Access
Quantum Error Mitigation with Attention Graph Transformers for Burgers Equation Solvers on NISQ Hardware
We present a hybrid quantum-classical framework augmented with learned error mitigation for solving the viscous Burgers equation on noisy intermediate-scale quantum (NISQ) hardware. Using the Cole-Hopf transformation, the nonlinear Burgers equation is mapped to a diffusion equation, discretized on uniform grids, and encoded into a quantum state whose time evolution is approximated via Trotterized nearest-neighbor circuits implemented in Qiskit. Quantum simulations are executed on noisy Aer backends and IBM superconducting quantum devices and are benchmarked against high-accuracy classical solutions obtained using a Krylov-based solver applied to the corresponding discretized Hamiltonian. From measured quantum amplitudes, we reconstruct the velocity field and evaluate physical and numerical diagnostics, including the L2 error, shock location, and dissipation rate, both with and without zero-noise extrapolation (ZNE). To enable data-driven error mitigation, we construct a large parametric dataset by sweeping viscosity, time step, grid resolution, and boundary conditions, producing matched tuples of noisy, ZNE-corrected, hardware, and classical solutions together with detailed circuit metadata. Leveraging this dataset, we train an attention-based graph neural network that incorporates circuit structure, light-cone information, global circuit parameters, and noisy quantum outputs to predict error-mitigated solutions. Across a wide range of parameters, the learned model consistently reduces the discrepancy between quantum and classical solutions beyond what is achieved by ZNE alone. We discuss extensions of this approach to higher-dimensional Burgers systems and more general quantum partial differential equation solvers, highlighting learned error mitigation as a promising complement to physics-based noise reduction techniques on NISQ devices.
Open AccessQuantum Error Mitigation with Attention Graph Transformers for Burgers Equation Solvers on NISQ Hardware
We present a hybrid quantum-classical framework augmented with learned error mitigation for solving the viscous Burgers equation on noisy intermediate-scale quantum (NISQ) hardware. Using the Cole-Hopf transformation, the nonlinear Burgers equation is mapped to a diffusion equation, discretized on uniform grids, and encoded into a quantum state whose time evolution is approximated via Trotterized nearest-neighbor circuits implemented in Qiskit. Quantum simulations are executed on noisy Aer backends and IBM superconducting quantum devices and are benchmarked against high-accuracy classical solutions obtained using a Krylov-based solver applied to the corresponding discretized Hamiltonian. From measured quantum amplitudes, we reconstruct the velocity field and evaluate physical and numerical diagnostics, including the L2 error, shock location, and dissipation rate, both with and without zero-noise extrapolation (ZNE). To enable data-driven error mitigation, we construct a large parametric dataset by sweeping viscosity, time step, grid resolution, and boundary conditions, producing matched tuples of noisy, ZNE-corrected, hardware, and classical solutions together with detailed circuit metadata. Leveraging this dataset, we train an attention-based graph neural network that incorporates circuit structure, light-cone information, global circuit parameters, and noisy quantum outputs to predict error-mitigated solutions. Across a wide range of parameters, the learned model consistently reduces the discrepancy between quantum and classical solutions beyond what is achieved by ZNE alone. We discuss extensions of this approach to higher-dimensional Burgers systems and more general quantum partial differential equation solvers, highlighting learned error mitigation as a promising complement to physics-based noise reduction techniques on NISQ devices.
- Open Access
EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects
Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness, yet negative cross-task interactions often hinder performance. In this work, we introduce Edge-Guided Spatial Attention (EGSA), a fusion mechanism designed to mitigate destructive interactions by incorporating boundary information into the fusion between semantic and geometric features. On both Syn-TODD and ClearPose benchmarks, EGSA consistently improved depth accuracy over the current state of the art method (MODEST), while preserving competitive segmentation performance, with the largest improvements appearing in transparent regions. Besides our fusion design, our second contribution is a multi-modal progressive training strategy, where learning transitions from edges derived from RGB images to edges derived from predicted depth images. This approach allows the system to bootstrap learning from the rich textures contained in RGB images, and then switch to more relevant geometric content in depth maps, while it eliminates the need for ground-truth depth at training time. Together, these contributions highlight edge-guided fusion as a robust approach capable of improving transparent object perception.
Open AccessEGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects
Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness, yet negative cross-task interactions often hinder performance. In this work, we introduce Edge-Guided Spatial Attention (EGSA), a fusion mechanism designed to mitigate destructive interactions by incorporating boundary information into the fusion between semantic and geometric features. On both Syn-TODD and ClearPose benchmarks, EGSA consistently improved depth accuracy over the current state of the art method (MODEST), while preserving competitive segmentation performance, with the largest improvements appearing in transparent regions. Besides our fusion design, our second contribution is a multi-modal progressive training strategy, where learning transitions from edges derived from RGB images to edges derived from predicted depth images. This approach allows the system to bootstrap learning from the rich textures contained in RGB images, and then switch to more relevant geometric content in depth maps, while it eliminates the need for ground-truth depth at training time. Together, these contributions highlight edge-guided fusion as a robust approach capable of improving transparent object perception.
- Open Access
The Fourth Monocular Depth Estimation Challenge
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.
Open AccessThe Fourth Monocular Depth Estimation Challenge
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.
- Open Access
A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models
Ephemeral gullies are a primary cause of soil erosion and their reliable, accurate, and early detection will facilitate significant improvements in the sustainability of global agricultural systems. In our view, prior research has not successfully addressed automated detection of ephemeral gullies from remotely sensed images, so for the first time, we present and evaluate three successful pipelines for ephemeral gully detection. Our pipelines utilize remotely sensed images, acquired from specific agricultural areas over a period of time. The pipelines were tested with various choices of Visual Language Models (VLMs), and they classified the images based on the presence of ephemeral gullies with accuracy higher than 70% and a F1-score close to 80% for positive gully detection. Additionally, we developed the first public dataset for ephemeral gully detection, labeled by a team of soil- and plant-science experts. To evaluate the proposed pipelines, we employed a variety of zero-shot classification methods based on State-of-the-Art (SOTA) open-source Vision-Language Models (VLMs). In addition to that, we compare the same pipelines with a transfer learning approach. Extensive experiments were conducted to validate the detection pipelines and to analyze the impact of hyperparameter changes in their performance. The experimental results demonstrate that the proposed zero-shot classification pipelines are highly effective in detecting ephemeral gullies in a scenario where classification datasets are scarce.
Open AccessA Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models
Ephemeral gullies are a primary cause of soil erosion and their reliable, accurate, and early detection will facilitate significant improvements in the sustainability of global agricultural systems. In our view, prior research has not successfully addressed automated detection of ephemeral gullies from remotely sensed images, so for the first time, we present and evaluate three successful pipelines for ephemeral gully detection. Our pipelines utilize remotely sensed images, acquired from specific agricultural areas over a period of time. The pipelines were tested with various choices of Visual Language Models (VLMs), and they classified the images based on the presence of ephemeral gullies with accuracy higher than 70% and a F1-score close to 80% for positive gully detection. Additionally, we developed the first public dataset for ephemeral gully detection, labeled by a team of soil- and plant-science experts. To evaluate the proposed pipelines, we employed a variety of zero-shot classification methods based on State-of-the-Art (SOTA) open-source Vision-Language Models (VLMs). In addition to that, we compare the same pipelines with a transfer learning approach. Extensive experiments were conducted to validate the detection pipelines and to analyze the impact of hyperparameter changes in their performance. The experimental results demonstrate that the proposed zero-shot classification pipelines are highly effective in detecting ephemeral gullies in a scenario where classification datasets are scarce.
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 969-981
SARLBP: Scale Adaptive Robust Local Binary Patterns for Texture Representation
Local Binary Pattern (LBP) and its variants have considerable success in a wide range of computer vision and pattern recognition applications, especially in tasks related to texture classification. However, the LBP method is sensitive to noise, scale variations and unable to capture macro-structure information. We propose a novel texture classification descriptor called Scale Adaptive Robust LBP (SARLBP) that enhances macro-level descriptive information by incorporating significantly larger scales, and a novel encoding scheme, which is designed to overcome the limitations of traditional LBP schemes. SARLBP method dynamically determines a single optimal scale for each radial direction from multiple scales based on the local area’s characteristics. Subsequently, this descriptor extracts four distinct patterns derived from regional image medians of center pixel, radially-optimized neighbor pixels, optimized fixed scale-based pixels, and radial-difference-based pixels. This method adeptly captures texture information at both micro and macro scales by employing scale adaptation based on the distinctive attributes of the local region. As a result, it provides a comprehensive and robust representation of the texture images. Extensive experimentation was conducted on four publicly available texture databases (ALOT, CUReT, UMD, and Kylberg), considering both the presence and absence of two distinct types of interference (Gaussian noise and Salt-and-Pepper noise). The results reveal that our SARLBP method achieves significantly better performance than other state-of-the-art LPB variants with a fixed smaller feature dimension.
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 969-981
SARLBP: Scale Adaptive Robust Local Binary Patterns for Texture Representation
Local Binary Pattern (LBP) and its variants have considerable success in a wide range of computer vision and pattern recognition applications, especially in tasks related to texture classification. However, the LBP method is sensitive to noise, scale variations and unable to capture macro-structure information. We propose a novel texture classification descriptor called Scale Adaptive Robust LBP (SARLBP) that enhances macro-level descriptive information by incorporating significantly larger scales, and a novel encoding scheme, which is designed to overcome the limitations of traditional LBP schemes. SARLBP method dynamically determines a single optimal scale for each radial direction from multiple scales based on the local area’s characteristics. Subsequently, this descriptor extracts four distinct patterns derived from regional image medians of center pixel, radially-optimized neighbor pixels, optimized fixed scale-based pixels, and radial-difference-based pixels. This method adeptly captures texture information at both micro and macro scales by employing scale adaptation based on the distinctive attributes of the local region. As a result, it provides a comprehensive and robust representation of the texture images. Extensive experimentation was conducted on four publicly available texture databases (ALOT, CUReT, UMD, and Kylberg), considering both the presence and absence of two distinct types of interference (Gaussian noise and Salt-and-Pepper noise). The results reveal that our SARLBP method achieves significantly better performance than other state-of-the-art LPB variants with a fixed smaller feature dimension.
- Open Access
High-Throughput and Accurate 3D Scanning of Cattle Using Time-of-Flight Sensors and Deep Learning
We introduce a high-throughput 3D scanning system designed to accurately measure cattle phenotypes. This scanner employs an array of depth sensors, i.e., time-of-flight (ToF) sensors, each controlled by dedicated embedded devices. The sensors generate high-fidelity 3D point clouds, which are automatically stitched using a point could segmentation approach through deep learning. The deep learner combines raw RGB and depth data to identify correspondences between the multiple 3D point clouds, thus creating a single and accurate mesh that reconstructs the cattle geometry on the fly. In order to evaluate the performance of our system, we implemented a two-fold validation process. Initially, we quantitatively tested the scanner for its ability to determine accurate volume and surface area measurements in a controlled environment featuring known objects. Next, we explored the impact and need for multi-device synchronization when scanning moving targets (cattle). Finally, we performed qualitative and quantitative measurements on cattle. The experimental results demonstrate that the proposed system is capable of producing high-quality meshes of untamed cattle with accurate volume and surface area measurements for livestock studies.
Open AccessHigh-Throughput and Accurate 3D Scanning of Cattle Using Time-of-Flight Sensors and Deep Learning
We introduce a high-throughput 3D scanning system designed to accurately measure cattle phenotypes. This scanner employs an array of depth sensors, i.e., time-of-flight (ToF) sensors, each controlled by dedicated embedded devices. The sensors generate high-fidelity 3D point clouds, which are automatically stitched using a point could segmentation approach through deep learning. The deep learner combines raw RGB and depth data to identify correspondences between the multiple 3D point clouds, thus creating a single and accurate mesh that reconstructs the cattle geometry on the fly. In order to evaluate the performance of our system, we implemented a two-fold validation process. Initially, we quantitatively tested the scanner for its ability to determine accurate volume and surface area measurements in a controlled environment featuring known objects. Next, we explored the impact and need for multi-device synchronization when scanning moving targets (cattle). Finally, we performed qualitative and quantitative measurements on cattle. The experimental results demonstrate that the proposed system is capable of producing high-quality meshes of untamed cattle with accurate volume and surface area measurements for livestock studies.
- Open Access
High-Throughput and Accurate 3D Scanning of Cattle Using Time-of-Flight Sensors and Deep Learning
We introduce a high throughput 3D scanning solution specifically designed to precisely measure cattle phenotypes. This scanner leverages an array of depth sensors, i.e. time-of-flight (Tof) sensors, each governed by dedicated embedded devices. The system excels at generating high-fidelity 3D point clouds, thus facilitating an accurate mesh that faithfully reconstructs the cattle geometry on the fly. In order to evaluate the performance of our system, we have implemented a two-fold validation process. Initially, we test the scanner’s competency in determining volume and surface area measurements within a controlled environment featuring known objects. Secondly, we explore the impact and necessity of multi-device synchronization when operating a series of time-of-flight sensors. Based on the experimental results, the proposed system is capable of producing high-quality meshes of untamed cattle for livestock studies.
Open AccessHigh-Throughput and Accurate 3D Scanning of Cattle Using Time-of-Flight Sensors and Deep Learning
We introduce a high throughput 3D scanning solution specifically designed to precisely measure cattle phenotypes. This scanner leverages an array of depth sensors, i.e. time-of-flight (Tof) sensors, each governed by dedicated embedded devices. The system excels at generating high-fidelity 3D point clouds, thus facilitating an accurate mesh that faithfully reconstructs the cattle geometry on the fly. In order to evaluate the performance of our system, we have implemented a two-fold validation process. Initially, we test the scanner’s competency in determining volume and surface area measurements within a controlled environment featuring known objects. Secondly, we explore the impact and necessity of multi-device synchronization when operating a series of time-of-flight sensors. Based on the experimental results, the proposed system is capable of producing high-quality meshes of untamed cattle for livestock studies.