Kauê de Moraes Vestena

Prof. Dr. Kauê de Moraes Vestena

Academic Department of Surveying, Federal University of Technology - Paraná, Pato Branco, Brazil
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2023 in European Journal of Geography
Verified
Journal Article
Open access
PDF file
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
SCSilvana Philippi Camboim
Silvana Philippi Camboim
Daniel Rodrigues Dos SantosDaniel Rodrigues Dos Santos
Daniel Rodrigues Dos Santos
Sidewalks are a relevant part of the living space in urban environments but are still rarely mapped. In recent years, the mapping of sidewalks has grown in importance among the OSM and academic communities as a matter of concern for many UN SDGs. To cover this gap, we propose a GitHub-hosted, fully open-source QGIS Plugin entitled "OSM SidewalKreator" to automatically draw the geometries of sidewalks for OSM crossings and curb crossing interfaces. The plugin workflow encompasses the steps of input area selection; data fetching, data cleaning, sidewalk geometries generation; crossings and kerbs generation; optional sidewalk splitting; and data exporting. Furthermore, the tool gives the user the capacity to have control over the process. Our tests revealed that the proposed method embodied by the plugin surpasses the manual process in many contexts, highlighting completeness, topological and thematic accuracies. We conclude that deepening, improving, and increasing the amount of open sidewalk mapping, mainly in the widely available OSM, can be a valuable asset to improve the development of accessibility and mobility worldwide. Highlights: SIdewalks and other footpaths are generally rarely mapped despite their huge importance OSM SIdewalKreator QGIS PLugin is a product of the research, being a valuable support tool A deep analysis compared sidewalks produced with two methods, endorsing the method’s strengths

Verified
Journal Article
Open access
PDF file
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
SCSilvana Philippi Camboim
Silvana Philippi Camboim
Maria Antonia BrovelliMaria Antonia Brovelli
Maria Antonia Brovelli
Daniel Rodrigues Dos SantosDaniel Rodrigues Dos Santos
Daniel Rodrigues Dos Santos
Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can be costly. A promising solution is to extract such geospatial features from street-level imagery. This study explores using open-vocabulary classification algorithms to segment and identify pavement types and surface materials in this scenario. Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. The methodology involves two experiments: the first uses free prompting with random street-view images, employing Grounding Dino and SAM algorithms to assess performance across categories. The second experiment evaluates standardized pavement classification using the Deep Pavements dataset and a fine-tuned CLIP algorithm optimized for detecting OSM-compliant pavement categories. The study presents open resources, such as the Deep Pavements dataset and a fine-tuned CLIP-based model, demonstrating a significant improvement in the true positive rate (TPR) from 56.04% to 93.5%. Our findings highlight both the potential and limitations of current open-vocabulary algorithms and emphasize the importance of diverse training datasets. This study advances urban feature mapping by offering a more intuitive and accurate approach to geospatial data extraction, enhancing urban accessibility and mobility mapping.

1 January 2024 in Boletim de Ciências Geodésicas
Verified
Journal Article
Open access
PDF file
JMJaime Carlos Macuácua
Jaime Carlos Macuácua
JCJorge Centeno
Jorge Centeno
CACaisse Amisse
Caisse Amisse
MJMario Ernesto Jijón-Palma
Mario Ernesto Jijón-Palma
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
Tomatoes are widely cultivated, both by family farmers and corporate producers. During the tomato growth cycle, several diseases can affect the plant. The identification of these diseases through short-range images is significant, and computer vision techniques are commonly used to identify diseases in plant leaves. In this paper, a hybrid model that combines a convolutional neural network (CNN) and a Random Forest (RF) decision tree is used for foliar spot detection in tomato leaves. High-level features learned and extracted from CNN are used as input for the RF classifier. To evaluate the proposed model’s performance for plant disease identification, a case study of 2480 low-cost digital RGB images collected in actual field conditions, under different intensities of light exposure, were used, including healthy tomato leaves and leaves with visible symptoms of powdery mildew fungus, which attacks the tomato leaf. The results were compared with six conventional machine learning classifiers: Logistic Regression (LR), Linear Discriminant Analysis (LDA), K- Nearest Neighbors (KNN), Naive Bayes (NB), Support Vector Machine (SVM) and Random Forest (RF). The results show that the proposed model outperformed conventional classifiers, reaching an accuracy of 98%. The results highlight the importance of fusing models to improve the detection plant´s diseases.

1 January 2024 in Boletim de Ciências Geodésicas
Verified
Journal Article
Open access
PDF file
FSFelipe Rodrigues Santana
Felipe Rodrigues Santana
CKClaudia Pereira Krueger
Claudia Pereira Krueger
ÉBÉrica Santos Matos Baluta
Érica Santos Matos Baluta
TSTulio Alves Santana
Tulio Alves Santana
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
The use of the ellipsoidal heights of a vessel for measuring the tide allows the diminution of uncertainties of sounding reduction in hydrographic surveys. In this article, the Precise Point Positioning (PPP) and Post-Processing Kinematic (PPK) methods were evaluated by comparing them with data from a tide gauge station while the boat remained moored nearby. When traversing sounding lines, the PPK solution was used as a reference to validate the PPP solution. In all, 12 different periods of surveys were analyzed, distributed throughout the year 2021, in the Guanabara and Ilha Grande Bays, in Rio de Janeiro. The results showed that in comparison with the tide station, when the vessel was moored, the PPK was able to fulfill the strictest criteria (Exclusive Order) of the IHO (International Hydrographic Organization) in 100% of the surveys, while the PPP in 50%. Regarding the use of the PPK as a reference, with the boat both moored and sailing, the PPP met these criteria in 67% for Exclusive Order, 25% for Order 1A and 8% for the 1B. Reducing the vertical uncertainties of hydrographic surveys in shallow waters is useful for all marine and coastal vertical positioning applications, such as integrating terrestrial and marine vertical references.

1 January 2024 in Boletim de Ciências Geodésicas
Verified
Journal Article
Open access
PDF file
JMJaime Carlos Macuácua
Jaime Carlos Macuácua
JCJorge Centeno
Jorge Centeno
FFFernando Alves Barros Firmino
Fernando Alves Barros Firmino
JCJorgiana Kamila Teixeira Do Crato
Jorgiana Kamila Teixeira Do Crato
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
CACaisse Amisse
Caisse Amisse
Urban infrastructure element detection is important for the domain of public management in large urban centres. The diversity of objects in the urban environment makes object detection and classification a challenging task, requiring fast and accurate methods. Advances in deep learning methods have driven improvement in detection techniques (processing, speed, accuracy) that do not rely on manually crafted models, but, instead, use learning approaches with corresponding large training sets to detect and classify objects in images. We applied an object detection model to identify and classify four urban infrastructure elements in the Mappilary dataset. We use YOLOv5, one of the top-performing object detection models, a recent release of the YOLO family, pre-trained on the COCO dataset but fine-tuned on Mappilary dataset. Experimental results from the dataset show that YOLOv5 can make qualitative predictions, for example, the power grid pole class presented the mean Average Precision (mAP) of 78% and the crosswalk class showed mAP around 79%. A lower degree of certainty was verified in the detection of public lighting (mAP=64%) and accessibility (mAP=61%) classes due to the low resolution of certain objects. However, the proposed method showed the capability of automatically detection and location of urban infrastructure elements in real-time, which could contribute to improve decision-making.

22 July 2024 in Revista Tamoios
Verified
Journal Article
Open access
PDF file
AMAngelica Carvalho Di Maio
Angelica Carvalho Di Maio
MCMarcus Vinícius Alves de Carvalho
Marcus Vinícius Alves de Carvalho
KSKellen Milene Gomes e Santos
Kellen Milene Gomes e Santos
RSRaquel Dezidério Souto
Raquel Dezidério Souto
Kauê de Moraes VestenaKauê de Moraes Vestena
Kauê de Moraes Vestena
A V edição da Olimpíada Brasileira de Cartografia (OBRAC 2023), com o tema "A Amazônia no Mapa", focou no mapeamento de recursos naturais e povos indígenas da Amazônia utilizando geotecnologias. O evento destacou a importância da Amazônia através de mapas que exploraram biodiversidade, desmatamento, bacias hidrográficas e questões sociais. A metodologia envolveu provas teóricas e práticas, com atividades de mapeamento participativo e colaborativo, utilizando plataformas como OpenStreetMap (OSM) e ferramentas como uMap, QGIS e Jamboard. O mapeamento participativo engajou estudantes e comunidades na criação de mapas que representassem a cultura e as potencialidades da Amazônia, enquanto o mapeamento colaborativo permitiu a participação remota via internet, utilizando bases cartográficas digitais. Esses métodos visaram empoderar comunidades e tornar visíveis suas questões locais, além de preencher lacunas cartográficas, especialmente em áreas rurais e subnormais. As equipes produziram mapas que refletiram as dinâmicas regionais, destacando aspectos positivos e desafios da região amazônica. Durante a etapa final presencial, as equipes visitaram instituições como o Instituto Nacional de Pesquisas Espaciais e o CEMADEN. A equipe vencedora do Instituto Federal do Pará desenvolverá um projeto de iniciação científica júnior sobre a Floresta de Carajás em 2024.