Ocupação da Terra e Conflitos de Uso com as Áreas de Preservação Permanente Nativa Remanescente de Cerrado na Sub-bacia do Córrego do Veado, Bacia do Alto Taquari, MS

A conservação das florestas é de grande interesse de toda a sociedade, pois garante os serviços ambientais básicos que sustentam a vida e a economia do país. Nesse estudo, realizou-se um diagnóstico do uso da terra e cobertura vegetal visando avaliar os conflitos entre as atividades antrópicas e as áreas de vegetação nativa remanescente de Cerrado na sub-bacia do Córrego do Veado e propor ações de adequação, do ponto de vista da conservação dos recursos naturais e da biodiversidade, com base na legislação pertinente e nas características físicas da bacia. O estudo se baseou em imagens orbitais e dados vetoriais, processados em Sistema de Informação Geográfica para a geração de produtos cartográficos. Na bacia, foram registradas 81 propriedades rurais, a maioria composta de imóveis com menos de quatro módulos fiscais, onde a principal forma de uso da terra foi a Pastagem sobre áreas consolidadas. A bacia contém em torno de 20% da área coberta por vegetação nativa de Cerrado, porém grande parte das propriedades não apresenta área de Reserva Legal e muitas nascentes de afluentes e do Córrego encontram-se degradadas. As ações propostas referem-se à recuperação das faixas de vegetação ciliar que descumprem o mínimo de largura estabelecido pela legislação, e das áreas de Reserva Legal; à readequação do uso em áreas voltadas à conservação da biodiversidade e à avaliação do potencial turístico da região, como forma de uso sustentável em áreas com alta declividade, solos altamente erodíveis e onde a vegetação de Cerrado encontra-se preservada. The conservation of forests is of great interest to all of society, as it guarantees the basic environmental services that support the life and economy of the country. In this study, a diagnosis of land use and vegetation cover was carried out in order to assess the conflicts between human activities and the areas of native Cerrado remnant in the sub-basin of the Córrego do Veado and propose adaptation actions, from the point of view of the conservation of natural resources and biodiversity, based on the legislation and the physical characteristics of the basin. The study was based on orbital images and vector data, processed in a Geographic Information System for the generation of cartographic products. In the basin, 81 rural properties were registered, the majority consisting of properties with less than four fiscal modules, where the main form of land use was Pasture over consolidated areas. The basin contains around 20% of the area covered by native Cerrado vegetation, however most of the properties do not have a Legal Reserve area and many tributary and stream springs are degraded. The proposed actions refer to the recovery of the strips of riparian vegetation that do not comply with the minimum width established by the legislation, and the areas of Legal Reserve; the readjustment of use in areas aimed at the conservation of biodiversity and the evaluation of the tourist potential of the region, as a form of sustainable use in areas with high declivity, highly erodible soils and where the Cerrado vegetation is preserved.Keywords:River Basin, Conservation, Ecosystem Service, Forest Code.

A Study on the Usability of Open Spatial Data for Road Network-Based Analysis – Using Openstreetmap as an Example

For several years GIS software users could use for any purpose a dataset being to some extent an alternative to both products offered by commercial providers and official databases. It is OpenStreetMap (OSM for short) – a worldwide spatial dataset, created and edited by interested individuals and available for use by anyone with no limitations. It is built on the basis of data recorded with consumer grade GPS receivers, obtained through vectorization of aerial photographs and from other usable sources, including even sketches made in the field. The collected information is stored in a central database, the content of which is not only presented on the website as a digital map, but also offered for download as vector data. Such data can be used for, among other things, performing various analyses based on road networks, of which the most frequently used is the function of determining the optimal route connecting selected locations. The results of such analyses can only be considered reliable if the data used are of adequate quality. As the OSM database is built by enthusiasts, no plans for its systematic development are formulated and there are no built-in quality control mechanisms. Therefore, the paper proposes methods and tools to verify the usefulness of the data collected so far, as well as to correct detected errors. It focuses on the following categories of geographic data quality: location accuracy, topological consistency and temporal validity. In addition, a problem with determining the length of individual road network segments was noticed, related to data acquisition methods and ways of recording the shape of lines. Therefore, in order to carry out the so-called route calibration, it was suggested to use kilometer and hectometer posts used in transportation networks, the locations of which are successively added to the OSM database. BADANIE UŻYTECZNOŚCI OTWARTYCH DANYCH PRZESTRZENNYCH DO ANALIZ OPARTYCH NA SIECIACH DROGOWYCH – NA PRZYKŁADZIE OPENSTREETMAP Od kilkunastu już lat użytkownicy oprogramowania GIS mogą używać do dowolnych celów zbioru danych będącego do pewnego stopnia alternatywą zarówno dla produktów oferowanych przez dostawców komercyjnych, jak i urzędowych baz danych. Jest nim OpenStreetMap (w skrócie OSM) – obejmujący cały świat zbiór danych przestrzennych, tworzony i edytowany przez zainteresowane osoby i dostępny do stosowania przez każdego chętnego bez żadnych ograniczeń. Budowany jest na podstawie danych rejestrowanych turystycznymi odbiornikami GPS, pozyskiwanych poprzez wektoryzację zdjęć lotniczych oraz pochodzących z innych nadających się do wykorzystania źródeł, w tym nawet szkiców wykonywanych w terenie. Zgromadzona GEOINFORMATICA POLONICA 20: 2021 DOI 10.4467/21995923GP.21.007.14978 informacja zapisywana jest w centralnej bazie danych, której zawartość jest nie tylko prezentowana na stronie internetowej w postaci cyfrowej mapy, lecz również oferowana do pobrania jako dane wektorowe. Takie dane mogą mieć zastosowanie między innymi do przeprowadzania różnorodnych analiz bazujących na sieciach drogowych, z których najczęściej wykorzystywana jest funkcja wyznaczania optymalnej trasy łączącej wybrane lokalizacje. Wyniki takich analiz można uznać za wiarygodne tylko wtedy, gdy użyte w nich dane będą się charakteryzować odpowiednią jakością. Ponieważ baza danych OSM budowana jest przez pasjonatów, nie są formułowane żadne plany jej systematycznego rozwoju oraz brak jest wbudowanych mechanizmów kontroli jakości. Dlatego w artykule zaproponowano metody i narzędzia, które pozwolą na weryfikację przydatności zgromadzonych do tej pory danych, jak również na poprawę wykrytych błędów. Skupiono się na następujących kategoriach jakości danych geograficznych: dokładności położenia, spójności topologicznej oraz ważności czasowej. Dodatkowo dostrzeżono problem z wyznaczaniem długości poszczególnych obiektów sieci drogowej, związany z metodami pozyskiwania danych i sposobami rejestracji kształtu linii. W związku z tym do przeprowadzenia tak zwanej kalibracji trasy zasugerowano użycie stosowanych w sieciach transportowych słupków kilometrowych i hektometrowych, których lokalizacje są sukcesywnie wprowadzane do bazy danych OSM.

Abnormal actions detection of robotic arm via 3D convolution neural network and support vector data description

Robotic arms are powerful assistants in many industrial production environments, and they run periodically in accordance with preset actions to complete specified operations. However, they may act abnormally when encountering unexpected situation and then lead to unnecessary loss. Recognizing the abnormal actions of robotic arms through surveillance video can automatically help us to understand their operating status and discover possible abnormalities in time. We designed a deep learning architecture based on 3D convolution for abnormal action recognition. The 3D convolutional layer can extract the spatial and temporal features of the robotic arm movements from the video frame difference sequence. The features are compressed and streamlined by the maximum pooling layer to obtain concise and effective robotic arm action features. Finally, the fully connected layer is used to classify the features to recognize the abnormal robotic arm tasks. Support vector data description (SVDD) model is employed to detect abnormal actions of the robotic arm, and the well-trained SVDD model can distinguish the normal actions from the three kinds of abnormal actions with the Area Under Curve (AUC) 99.17% .

Reduction of the Bim Dimension of the Full Life Cycle of Building and Facilities

Постановка задачи. Предметом исследования являются информационные модели полного жизненного проекта в секторе архитектуры, проектирования, строительства и эксплуатации зданий и сооружений. Цель исследования состоит в оптимизации BIM-технологий путем построения модели, основанной на дискретном векторном описании данных. Результаты. Проанализированы основные препятствия на пути широкого внедрения BIM-технологий и процедур полного жизненного цикла строительного проекта в практику строительного комплекса РФ в течение всего жизненного цикла проекта, включая этапы строительства, эксплуатации и утилизации, а также мировые тенденции этого процесса. Сформулирован метод редукции размерности BIM, основанной на дискретном векторном описании данных. Разработана технология формирования иерархической динамически добавляющейся и обновляющейся информационной основы BIM, учитывающей возможность ее агрегации. Предложенные в работе алгоритмы реализованы в оболочке реляционной системы управления базами данных. Выводы. Редукция размерности BIM, основанная на дискретном векторном описании данных, позволяет полностью решить задачи как создания и актуализации информационной основы BIM, так и ее трансферта между участниками проекта. Форматы данных BIM определяется этапом полного жизненного цикла проекта. Полнофункциональная для этапа определения объемов работ по проекту BIM является одномерной и определяется просто вектором кластеров более низкой степени интеграции, что позволяет полностью преодолеть все препятствия на пути широкого внедрения BIM-технологий и процедур полного жизненного цикла строительного проекта в практику. Оптимальной оболочкой реализации BIM-технологий являются реляционные базы данных. Statement of the problem. The subject of the research is information models of a complete life project in the sector of architecture, design and construction and maintenance of buildings and structures. The purpose of the research is to optimize BIM technologies by means of building a model based on a discrete vector data description. Results. The main obstacles to the widespread introduction of BIM technologies and procedures for the full life cycle of a construction project in the practice of the construction complex of the Russian Federation throughout the entire life cycle of the project, including the stages of construction, operation and disposal, as well as global trends in this process have been analyzed. The method of BIM dimension reduction based on discrete vector data description is formulated. The technology of forming a hierarchical dynamically added and updated information base BIM taking into account the possibility of its aggregation has been developed. The suggested algorithms are implemented in the shell of a relational database management system. Conclusions. BIM dimension reduction based on a discrete vector description of data allows one to completely solve the problems of both designing and updating the BIM information base, and its transfer between project participants. BIM data formats are determined by the stage of the complete project life cycle. Fully functional for the stage of determining the scope of work on a project, BIM is one-dimensional and is simply determined by the vector of clusters of a lower degree of integration, which allows one to completely overcome all of the obstacles to the widespread introduction of BIM technologies and procedures of a full life cycle of a construction project into practice. The optimal shell for the implementation of BIM technologies are relational databases.

A New Algorithm for Extracting Winter Wheat Planting Area Based on Ownership Parcel Vector Data and Medium-Resolution Remote Sensing Images

In the complex planting area with scattered parcels, combining the parcel vector data with remote sensing images to extract the winter wheat planting information can make up for the deficiency of the classification from remote sensing images simply. It is a feasible direction for precision agricultural subsidies, but it is difficult to collect large-scale parcel data and obtain high spatial resolution or time-series remote sensing images in mass production. It is a beneficial exploration of making use of existing parcel data generated by the ground survey and medium-resolution remote sensing images with suitable time and spatial resolution to extract winter wheat planting areas for large-scale precision agricultural subsidies. Therefore, this paper proposes a new algorithm to extract winter wheat planting areas based on ownership parcel data and medium-resolution remote sensing images for improving classification accuracy. Initially, the segmentation of the image is carried out. To this end, the parcel data is used to generate the region of interest (ROI) of each parcel. Second, the homogeneity of each ROI is detected by its statistical indices (mean value and standard deviation). Third, the parallelepiped classifier and rule-based feature extraction classification methods are utilized to conduct the homogeneous and nonhomogeneous ROIs. Finally, two classification results are combined as the final classification result. The new algorithm was applied to a complex planting area of 103.60 km2 in central China based on the ownership parcel data and Gaofen-1 PMS and WFV remote sensing images in this paper. The experimental results show that the new algorithm can effectively extract winter wheat planting area, eliminate the problem of salt-and-pepper noise, and obtain high-precision classification results (kappa = 0.9279, overall accuracy = 96.41%, user’s accuracy = 99.16%, producer’s accuracy = 93.39%, commission errors = 0.84%, and omission errors = 6.61%) when the size of ownership parcels matches the spatial resolution of remote sensing images.

REDUCTION OF THE BIM DIMENSION OF THE FULL LIFE CYCLE OF BUILDING AND FACILITIES

Statement of the problem. The subject of the research is information models of a complete life project in the sector of architecture, design and construction and maintenance of buildings and structures. The purpose of the research is to optimize BIM technologies by building a model based on a discrete vector data description. Results. Analyzed the main obstacles to the widespread introduction of BIM technologies and procedures for the full life cycle of a construction project in the practice of the construction complex of the Russian Federation throughout the entire life cycle of the project, including the stages of construction, operation and disposal, as well as global trends in this process. The method of BIM dimension reduction based on discrete vector data description is formulated. The technology of forming a hierarchical dynamically added and updated information base BIM, taking into account the possibility of its aggregation, has been developed. The algorithms proposed in this work are implemented in the shell of a relational database management system. Conclusions. BIM dimension reduction, based on a discrete vector description of data, allows youto completely solve the problems of both designing and updating the BIM information base, and its transfer between project participants. BIM data formats are determined by the stage of the complete project life cycle. Fully functional for the stage of determining the scope of work on a project, BIM is one-dimensional and is simply determined by the vector of clusters of a lower degree of integration, which allows you to completely overcome all obstacles to the widespread introduction of BIM technologies and procedures of the full life cycle of a construction project into practice. The optimal shell for the implementation of BIM technologies is relational databases.

3DPlanNet: Generating 3D Models from 2D Floor Plan Images Using Ensemble Methods

Research on converting 2D raster drawings into 3D vector data has a long history in the field of pattern recognition. Prior to the achievement of machine learning, existing studies were based on heuristics and rules. In recent years, there have been several studies employing deep learning, but a great effort was required to secure a large amount of data for learning. In this study, to overcome these limitations, we used 3DPlanNet Ensemble methods incorporating rule-based heuristic methods to learn with only a small amount of data (30 floor plan images). Experimentally, this method produced a wall accuracy of more than 95% and an object accuracy similar to that of a previous study using a large amount of learning data. In addition, 2D drawings without dimension information were converted into ground truth sizes with an accuracy of 97% or more, and structural data in the form of 3D models in which layers were divided for each object, such as walls, doors, windows, and rooms, were created. Using the 3DPlanNet Ensemble proposed in this study, we generated 110,000 3D vector data with a wall accuracy of 95% or more from 2D raster drawings end to end.

Suburban Morphology Dynamics: The Case of the Tricity Agglomeration, Poland

Suburbanization is a phase of the development of cities that consists in the growth of the suburban zone at the expense of the city center, which becomes gradually depopulated. The phenomenon of uncontrolled suburbanization (urban sprawl) causes infrastructural (including transport), environmental, social, economic, and legal problems. This paper presents the results of a study of the phenomenon of suburbanization conducted on the basis of vector data using two methods: one based on the use of a grid of primary square fields, and one based on the use of concentric zones/rings. The analyses were conducted in the surroundings of the Tricity agglomeration, which is located in the northern part of Poland on the Gulf of Gdansk, and covered the period from 2000 to 2018. Using a grid of primary fields, the areas of the greatest increase and decrease in the developed areas, irrespective of administrative boundaries, were determined for the selected periods, and the areas of the constant positive and negative balance of the buildings were identified. Using concentric rings, the process of the shifting of the new development zones was traced. The paper also refers to the route of the Pomeranian Metropolitan Railway (PKM), which was commissioned in 2015, and its potential impact on suburbanization in the Tricity area. The results made it possible to trace the suburbanization process in time and space and to learn the advantages and disadvantages of the use of vector data in spatial studies.