Urban Objects Research Articles

Comparing inpainting techniques for urban object restoration from orbital images

Abstract. Based on the comparison of three established inpainting techniques, namely Criminisi, Beltamio, and Galerne and Leclaire, our study aimed to identify the most effective method for road restoration after extraction and detection using a Mathematical Morphology operators combined with hybrid techniques of digital image processing in remote sensing images. While all techniques were evaluated based on both visual analysis and quantitative metrics, the Criminisi approach emerged as the better choice. Despite introducing some additional noise, this technique demonstrated superior performance in terms of Completeness and overall Quality, achieving approximately 95.23% and 94.56%, respectively. Its ability to accurately reconstruct linear geometries while effectively removing existing noise highlighted its suitability for road restoration tasks.

Эксперименты с формой: варианты деконструкции и неоконструктивизма в архитектуре Москвы 1990-2000-х годов

At the turn of the 20th — 21st centuries, Moscow architecture was dynamic, with different architects working simultaneously, embodying individual meanings in a variety of architectural form and materials. One of the lines of the modern Moscow architecture development was experimentation with space, form and construction, which, among other things, involved references to the principles and techniques of deconstructivism and appeals to constructivism, which make the subject of this article. Deconstructivist motifs in the Moscow architecture of the 1990s — 2000s are primarily visible in the architectural works of A. Asadov’s studio and individual projects of V. Kolosnitsyn and A. Loktev. The search for non-trivial plastic solutions interested such architects as M. Khazanov, A. Bokov, S. Skuratov, S. Kiselev, G. Nadtochiy, K. Konovaltsev, B. Shabunin and others. Some of the architectural objects appeared to be full-fledged followers of constructivist traditions (e.g. the works of the architectural workshop of N. Lyzlov, some projects of A. Skokan and the Ostozhenka architectural bureau, urban objects of A. Vissarionov, A. Vorontsov, Y. Ilyin-Adaev, etc.). This article reveals one of the trends in the development of Moscow architecture which along with neomodernism, neoclassicism, capitalist romanticism (or ‘caprom’), an appeal to Art Deco, to the techniques and principles of postmodernism has permanently changed the appearance of the capital.

THE ORIGINS OF THE PROVINCIAL PHOTOGRAPHER’S CREATIVITY EARLY XX CENTURY A.A. ZIRAH

The work of the provincial Ufa photographer of the early XX century A.A. Zirakh does not go beyond the descriptive discourse in the literature of local lore. However, we believe that it is a phenomenon that needs to be interpreted from a historical and cultural point of view. We tried to understand what a small insurance employee was motivated by to selflessly give the last decade of his life to photography. The very analysis of photographs by A.A. Zirakh led to an appeal to the problem of the difference between history and memory. The surviving photographs indicate that A.A. Zirakh was more interested in the architecture and landscape of the city than in the events. This confirms the thesis that the artist considered his collection as a tool of memory, but not as a historical source. Memory, unlike history, is an area of individual perception. In this regard, our attitude differs from the one of the representatives of the "place of memory" concept. The nature of A.A. Zirakh's work is associated with the problem of the attitude of the Russian intelligentsia to the province. We believe that monotony is the defining mood of the provincial chronotope. But a creative person can’t control the time. A scholar is deprived of the opportunity to act as a subject of historical processes in province. The monotony and eventlessness of backwater time are changed only under the influence of the center. On the contrary, the monotony and, consequently, the meaninglessness of the landscape of the outskirts are amenable to creative transformation. Breaking out of the monotonous environment of familiar urban objects through photography, A.A. Zirakh forces to focus attention on them, to notice the uniqueness and thereby destroy the anonymity of the urban landscape.

Deep learning for 3D object recognition: A survey

With the growing availability of extensive 3D datasets and the rapid progress in computational power, deep learning (DL) has emerged as a highly promising approach for learning from 3D data, addressing critical tasks like object detection, segmentation, and recognition. Despite the unique challenges in processing geometry data with deep neural networks, recent advancements in DL for 3D object recognition have shown remarkable success, with various methods proposed to tackle different issues. This paper aims to stimulate future research by providing a comprehensive review of recent progress in DL techniques for 3D object recognition, which are systematically categorized based on their learning behavior. We discuss the advantages, limitations, and application of each approach, highlighting their performance in 3D object classification on benchmark datasets such as ModelNet, ScanObjectNN, and Sydney Urban Object. The survey offers insightful observations and inspires future research directions.

Деколонізація топонімів міста Вінниця: лексико-семантичний аналіз

A toponym is defined as a common name for any toponymic objects, starting from large geographical names and administrative districts and ending with small internal urban objects (names of streets, squares, settlements, regions, countries, etc.). The main purpose and function of toponyms is to highlight, individualize, and identify named objects among others. Ukrainian onomastics has consistently pointed to the necessity of a systematic study of toponymy, including microtoponymy. The attention of researchers to the microtoponymy of certain regions of Ukraine has increased significantly, and this is represented in the studies of M. Khudash, K. Tsiluiko, E. Cherepanova, D. Buchko, L. Humetska, K. Halas, I. Zheliezniak, S. Verbych, Y. Karpenko, Z. Kupchynska, V. Loboda, J. Pura, M. Torchynskyi, N. Torchynska, Y. Stepanov, and many others. Equally important is the study of urban names, including regional ones. Urban name is the name of an inner-city object that represents the semantic character of the city, records the history of urban structures, their social, ethnic and cultural function. Both Ukrainian and foreign scholars have conducted research in the field of urban names. Among them: D. Buchko, O. Belei, N. Lisniak, N. Liasovets, R. Liashenko, O. Halai, I. Sabodash, Y. Fernos, L. Masenko, P. Chuchka, T. Shmelva, V. Kamianets, M. Blicha, E. Jedrzefko, and others. The purpose of this article is to analyze the lexical and semantic aspects of the hodonyms of Vinnytsia, which appeared as a result of the decolonization of toponyms in 2023. The main research methods are: descriptive, comparative-historical, structural-semantic, and component analysis. Results. The new names immortalize the memory of outstanding figures of culture and art, significant historical episodes, heroes of the all-time liberation struggles, and heroes of the Russian-Ukrainian war. All the analyzed onyms are divided into two groups: derivatives of other proper names, including anthroponyms, microtoponyms, microhydronyms, and onyms of appellative origin. The group of hodonyms derived from anthroponyms includes about 150 names. Among them are the following: 1) hodonyms-names of the heroes of the Russian-Ukrainian war; 2) hodonyms-names of cultural and arts figures, including Ukrainian writers, publicists, journalists, literary scholars, critics, folklorists, composers, singers, actors, artists, architects, and film directors; 3) hodonyms-names of Ukrainian public figures, princes, philanthropists, human rights activists, politicians, military leaders, scientists, educators, and rebels. The group of hodonyms derived from toponyms is presented as follows: 1) derived from oikonyms, including astionym; 2) derived from chorononyms, including sovereignonyms; 3) derived from microtoponyms, microhydronyms. The group of hodonyms derived from appellatives is represented by a small number of names for natural features of the area, the location of an object, etc. Novelty consists in the fact that it is the first lexical and semantic analysis of the hodonyms of Vinnytsia as part of the decolonization of toponyms in 2023. Conclusions. Like other cities in Ukraine, Vinnytsia faced a wave of decolonization of toponyms with Russian and Soviet echoes in 2022-2023. As a result, streets, alleys, and squares were given their historical names. There are personal tributes to the fallen heroes of the Russian-Ukrainian war. The urbanonymicon of Vinnytsia is structured by onymic and appellative derivatives, among which anthroponymic and toponymic homonyms predominate. They reflect the worldview of the city's inhabitants, have important cultural significance, and perform a social, ethnic, and cultural function.

On the validation of a modelling tool for Vehicle Integrated PhotoVoltaics: Reflected irradiance in urban environments

Vehicle Integrated PhotoVoltaics (VIPV) technology holds immense promise for extending the operational range of Electric Vehicles by integrating Photovoltaic cells onto vehicle surfaces. However, VIPV faces unique challenges coming from the dynamic nature of vehicular movement and the complex urban environment. This paper presents a comprehensive methodology for the analysis of VIPV systems, addressing these challenges. Light Detection and Ranging (LiDAR) technology provides a high-resolution point cloud to characterize urban topography and enables to analyse of the impact of urban objects on the different components of the irradiance. The proposed methodology is validated through a measurement campaign, demonstrating the accuracy of the proposed modelling. By bridging empirical data collection with computational modelling, this research provides a robust foundation for analysing VIPV systems in urban environments.

Эргонимикон как важнейший компонент языкового ландшафта современного полиэтнического города (на примере Уфы)

The aim of the study is to provide a comprehensive overview of the main structural, semantic and linguocultural features of the ergonymicon of a modern multiethnic city in relation to the specifics of its characteristic linguistic situation. The article defines the conceptual foundations for the study of the linguistic landscape of the city; examines the originality of the ergonymicon as an integral component of the onomastic urban space; carries out a multidimensional description of ergonyms recorded in the territory of the city of Ufa. The scientific novelty of the study lies in the fact that, using the example of Ufa, a systematic analysis of the ergonymicon of a modern multiethnic city is carried out according to various parameters (method of education, origin, linguistic and cultural features) and the conditionality of the specifics of these units by intra- and extra-linguistic factors is determined. As a result of the study, it was found that the main features of the Ufa ergonymicon are multilingualism, active appeal to national identity and regional affiliation in the nomination of urban objects, and widespread use of borrowings. It was also found that when creating ergonyms, Russian language units are used most often. Elements of the national (Bashkir) language are less frequently used compared to English-language ones. Urban specificity is especially noticeable in ergonyms created based on toponyms, anthroponyms, and ethno-cultural realities.

ESTATE: A Large Dataset of Under-Represented Urban Objects for 3D Point Cloud Classification

Abstract. Cityscapes contain a variety of objects, each with a particular role in urban administration and development. With the rapid growth and implementation of 3D imaging technology, urban areas are increasingly surveyed with high-resolution point clouds. This technical advancement extensively improves our ability to capture and analyse urban environments and their small objects. Deep learning algorithms for point cloud data have shown considerable capacity in 3D object classification but still face problems with generally under-represented objects (such as light poles or chimneys). This paper introduces the ESTATE dataset (https://github.com/3DOM-FBK/ESTATE), which combines available datasets of various sensors, densities, regions, and object types. It includes 13 classes featuring intensity and/or colour attributes. Tests using ESTATE demonstrate that the dataset improves the classification performance of deep learning techniques and could be a game-changer to advance in the 3D classification of urban objects.

Comparing hybrid models for recognising objects in thermal images at nighttime

This research aims to revolutionize urban object recognition by developing cloud-based Python programs using intelligent algorithms. Unlike current models that focus on colour enhancement in nighttime thermal images, this work addresses the critical challenge of accurate object detection in urban landscapes. The proposed method incorporates a binary generative adversarial network (GAN) generator that can switch bidirectionally between daytime colour (DC) and nighttime infrared (NTIR) images. memory-based visual image memory (MVAM), system extracts important descriptive information from urban landscape images, reducing problems related to small sample sizes. This discussion presents a comprehensive improvement and evaluation of a deep learning image classification pipeline using Google Colab, demonstrating advanced image processing. Using TensorFlow, Keres and scikit image libraries combined with advanced algorithms such as DenseNet121 and MobileNetV2 presents a clear approach. We created a Bidirectional GAN + MVAM for object recognition in this work. Our method performed well, with an accuracy of 81.43%, precision of 51.16, recall of 50.11, and F-score of 46.37. The systematic presentation of the code presents a careful strategy to ensure optimal performance, stability, and efficiency of deep learning and image processing tasks.

MEMORIAL URBAN NAMES OF UZHGOROD THROUGH THE PRISM OF ECOLINGUISTICS

At the current stage of the development of Ukrainian proper vocabulary, in particular in the post-Soviet period, the subsystem of modern Ukrainian urban names has undergone deeper and more systematic changes. According to linguists, this situation was caused by a distinct development trend such as de-ideologization. After all, the massive nature of the changes observed in Ukrainian urbanonymy, in particular in the western and central parts of Ukraine, is explained by the democratic procedure of replacing the proper names of streets, squares, parks, squares, microdistricts, etc., which, according to current Ukrainian legislation, is implemented on the basis of a resolution of the local council, and not the Verkhovna Rada of Ukraine, as provided by the procedure for changing the proper names of settlements. However, the democratic nature of the procedure for changing Ukrainian urban names, in our opinion, became the main reason for the insufficient or superficial linguistic examination of both urban neologisms and already traditional onims, which enables the functioning of many proper names of urban objects, the structure of which contradicts the norms of the Ukrainian language. Spelling errors are a characteristic type of violation of the norms of the Ukrainian literary language in the subsystem of Ukrainian urban names of the post-totalitarian era. Most often, when writing modern Ukrainian urban names, the rules of capitalization are violated. Urbanonymy is a specific onymic subsystem, which reacts extremely actively to social changes and is especially dependent on the political regime, which is connected with the memorial function of the names of inner-city objects. In this connection, the analysis of the concept of historical memory in urbanonymy becomes especially relevant. the negative influence of the environment affects the ecolinguistic state of various levels and even classes of the Ukrainian onymic vocabulary of the post-totalitarian era differently. Ukrainian anthroponymy, in particular people’s proper names and patronymic names, as well as oikonyms, urbanonyms, ergonyms, are adversely affected at the lexical level. Key words: concept, ecolinguistics, onim.

Zero-shot urban function inference with street view images through prompting a pretrained vision-language model

Inferring urban functions using street view images (SVIs) has gained tremendous momentum. The recent prosperity of large-scale vision-language pretrained models sheds light on addressing some long-standing challenges in this regard, for example, heavy reliance on labeled samples and computing resources. In this paper, we present a novel prompting framework for enabling the pretrained vision-language model CLIP to effectively infer fine-grained urban functions with SVIs in a zero-shot manner, that is, without labeled samples and model training. The prompting framework UrbanCLIP comprises an urban taxonomy and several urban function prompt templates, in order to (1) bridge the abstract urban function categories and concrete urban object types that can be readily understood by CLIP, and (2) mitigate the interference in SVIs, for example, street-side trees and vehicles. We conduct extensive experiments to verify the effectiveness of UrbanCLIP. The results indicate that the zero-shot UrbanCLIP largely surpasses several competitive supervised baselines, e.g. a fine-tuned ResNet, and its advantages become more prominent in cross-city transfer tests. In addition, UrbanCLIP’s zero-shot performance is considerably better than the vanilla CLIP. Overall, UrbanCLIP is a simple yet effective framework for urban function inference, and showcases the potential of foundation models for geospatial applications.

Development of Real-Time Unmanned Aerial Vehicle Urban Object Detection System with Federated Learning

In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring and urban traffic management. The system includes an object detection algorithm, deep learning model training, and deployment on a real UAV. For the object detection algorithm, the Mobilenet-SSD model is applied owing to its lightweight and efficiency, which make it suitable for real-time applications on an onboard microprocessor. For model training, federated learning (FL) is used to protect privacy and increase efficiency with parallel computing. Last, the FL-trained object detection model is deployed on a real UAV for real-time performance testing. The experimental results show that the object detection algorithm can reach a speed of 18 frames per second with good detection performance, which shows the real-time computation ability of a resource-limited edge device and also validates the effectiveness of the developed system.

Evolution of Yelabuga City Ergonyms

The article analyzes Yelabuga’s ergonymicon, the evolution of ergonyms from 1897 to 2022 and compares three layers of Yelabuga’s ergonymicon in order to reveal the formation regularities of proper names. The study is based on advertising texts, the newspapers “The Kama Listok Advertising”, “The Stalin’s Way”, “The For the Five-Year Plan”, “The New Kama”, as well as the names of current city infrastructure facilities. Our research is based on following methods: the comparative method in the study of the linguistic facts, historical and cultural processes, the analysis of the concepts in finding correspondences and regularities in the formation of ergonyms, the contextual analysis method in the study of periodical publications of the 19th-20th centuries and the transformation method in identifying the functional possibilities of onyms. The article gives a number of examples (300 names of urban objects in the 19th – 21st centuries). In the course of the study, we propose our own classifications of ergonyms. The theoretical significance of the analyzed material lies in clarifying the concept of “ergonym” and the classification of ergonyms. The practical value lies in the fact that for the first time an attempt has been made to study the emergence peculiarities of ergonyms and the regularities of their change over time. The results confirm the idea that ergonyms are a linguistically flexible category of words, which change over time, responding to the needs of society.

Patterns of Interactions of the Complex City System: Emotional Urban Objects as Triggering Agents – A Secondary Publication

This article presents an analysis of the patterns of interactions resulting from the positive and negative emotional events that occur in cities, considering them as complex systems. It explores, from the imaginaries, how certain urban objects can act as emotional agents and how these events affect the urban system as a whole. An adaptive complex systems perspective is used to analyze these patterns. The results show patterns in the processes and dynamics that occur in cities based on the objects that affect the emotions of the people who live there. These patterns depend on the characteristics of the emotional charge of urban objects, but they can be generalized in the following process: (1) immediate reaction by some individuals; (2) emotions are generated at the individual level which begins to generalize, permuting to a collective emotion; (3) a process of reflection is detonated in some individuals from the reading of collective emotions; (4) integration/significance in the community both at the individual and collective level, on the concepts, roles and/or functions that give rise to the process in the system. Therefore, it is clear that emotions play a significant role in the development of cities and these aspects should be considered in the design strategies of all kinds of projects for the city. Future extensions of this work could include a deeper analysis of specific emotional events in urban environments, as well as possible implications for urban policy and decision making.

INTEGRATED RESEARCH TOOLS IN URBAN AND SPATIAL PLANNING

In working with urban projects, we are usually faced with the need to study the design object, regardless of its scale, significance and value in the city and the functions it performs. The larger the scale of the research object, the more voluminous our research becomes and, accordingly, requires a clear division into different layers and gradation in order of importance to simplify the conduct of the research itself and the ability to predict the expected results. A classic way of analyzing large territorial, urban and spatial objects is a comprehensive urban planning analysis. However, today's urban and spatial studies go beyond urban planning analysis and require a synthesis with the methods of other social and humanitarian disciplines, going beyond mono-discipline into multidisciplinarity and complexity. Also, changes in values in urban and spatial design, when attention is focused on reuse, mixed use, programmatic design, sustainability and consideration of climate change, the importance of public spaces in the life of the city led to the use of another format of urban studies. For urban objects of different sizes, such as a fragment of the city within the boundaries of the streets, a block, a combination of blocks, an undeveloped part of the city, a post-industrial area that is being revitalized, the author has created a list of seven layers necessary for analysis, which include physical, morphological, social and historical and cultural aspects of the study: 1) territory in the structure of the city, 2) functions and content, 3) accessibility and mobility, 4) morphology and buildings development, 5) inhabitants and stakeholders, 6) open spaces, 7) history and identity. The characteristic features of this urban planning and spatial analysis are, firstly, a proposal at all levels of analysis to fix proposals for changes that will be detailed at the design phase. Secondly, at each layer of research, it is suggested to interact with residents and users and capture their feedback for each layer of analysis. These layers of analytical urban research can be supplemented depending on the complexity and specificity of the research object. And also depending on the direction and requests of the research, the expected results.

Classification of Typical Static Objects in Road Scenes Based on LO-Net

Mobile LiDAR technology is a powerful tool that accurately captures spatial information about typical static objects in road scenes. However, the precise extraction and classification of these objects pose persistent technical challenges. In this paper, we employ a deep learning approach to tackle the point cloud classification problem. Despite the popularity of the PointNet++ network for direct point cloud processing, it encounters issues related to insufficient feature learning and low accuracy. To address these limitations, we introduce a novel layer-wise optimization network, LO-Net. Initially, LO-Net utilizes the set abstraction module from PointNet++ to extract initial local features. It further enhances these features through the edge convolution capabilities of GraphConv and optimizes them using the “Unite_module” for semantic enhancement. Finally, it employs a point cloud spatial pyramid joint pooling module, developed by the authors, for the multiscale pooling of final low-level local features. Combining three layers of local features, LO-Net sends them to the fully connected layer for accurate point cloud classification. Considering real-world scenarios, road scene data often consist of incomplete point cloud data due to factors such as occlusion. In contrast, models in public datasets are typically more complete but may not accurately reflect real-world conditions. To bridge this gap, we transformed road point cloud data collected by mobile LiDAR into a dataset suitable for network training. This dataset encompasses nine common road scene features; hence, we named it the Road9 dataset and conducted classification research based on this dataset. The experimental analysis demonstrates that the proposed algorithm model yielded favorable results on the public datasets ModelNet40, ModelNet10, and the Sydney Urban Objects Dataset, achieving accuracies of 91.2%, 94.2%, and 79.5%, respectively. On the custom road scene dataset, Road9, the algorithm model proposed in this paper demonstrated outstanding classification performance, achieving a classification accuracy of 98.5%.

A Review Geospatial Artificial Intelligence (GEO-AI): Implementation Of Machine Learning On Urban Planning

Geospatial Artificial Intelligence (Geo-AI) is an interesting topic in its development and application in our lives. One of them is spatial planning, which contributes to the economic and social development of a region or country. Spatial data is the main thing in this research, which maximizes the effectiveness of land use spatial data on the area as upstream data and develops GIS-based urban planning applications to display the results of analysis and predictions of urban objects automatically. On the other hand, to maximize tourism revenue, the government plans urban areas for both spatial and land use and makes a lot of spatial data based on geographical and environmental conditions. This study will analyze the benefits of Geo-AI in urban planning and the tourism sector. The method used in this study is the Systematic Literature Review (SLR), where the search for the required articles comes from electronic databases obtained using the NVivo software with article sources from Publish or Perish. This study discusses the main steps for the analysis of geospatial data that have been successful in the main areas, namely the development of applications and models, including visualization. By treating issues in geospatial artificial intelligence, the overall aim of the research is to improve the quality of life for Indonesia's growing urban population. The results of the study with the systematic literature review of Geo-AI found a gap in the research implementation of the machine learning model used where five models were compared and relevant to the geospatial dataset displayed in the form of a literature review matrix and visually included in the relevant keywords in the bibliometric analysis. Interdisciplinary results are developing and are urgently needed by both government and private stakeholders in the development of smart cities to prepare spatial planning in urban areas and strategies in optimizing technology in the field of spatial planning in implementing systems based on Geo-AI.

The Geographical Analysis of Megacities Through Changes in Their Individual Urban Objects

This research utilized global coverage, annual, high‐quality land cover time‐series data to explore the urban growth process in the core area, and in several buffer zones, of Beijing, Guangzhou, Shanghai, and Tokyo. We developed a conceptual model in which growth is characterized at the per‐object level by four active growth events: introduction, establishment, dispersal, and coalescence, with a fifth inactivity event, stability. We developed a rule‐base which allowed the direct measurement of establishment, dispersal and coalescence from observed inter‐annual changes in the urban objects over time. By aggregating the object‐level events to the landscape level we showed that these three events generally followed a synchronous temporal trend in terms of magnitude within the core area and within each buffer zone. There was no evidence for a logical sequence of events through time. The identified events dominated alternately over time, although synchronicity in magnitude far outweighed any differences in proportion between them. This points to a single underlying urbanization process: urban growth with a specific dynamic rate. Interestingly, synchronicity was not generally observed between the core and buffer zones. This proposed object‐based method provides insights into the underlying urban growth process and could be used to build new urban growth models.

PanorAMS: Automatic Annotation for Detecting Objects in Urban Context

Large collections of geo-referenced panoramic images are freely available for cities across the globe, as well as detailed maps with location and meta-data on a great variety of urban objects. They provide a potentially rich source of information on urban objects, but manual annotation for object detection is expensive, laborious and challenging. Can we utilize such multimedia sources to automatically annotate street level images as an inexpensive alternative to manual labeling? With the PanorAMS framework we introduce a method to automatically generate bounding box annotations for panoramic images based on urban context information. Following this method, we acquire large-scale, albeit noisy, annotations for an urban dataset solely from open data sources in a fast and automatic manner. The dataset covers the City of Amsterdam and includes over 14 million noisy bounding box annotations of 22 object categories present in 771,299 panoramic images. For many objects further fine-grained information is available, obtained from geospatial meta-data, such as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">building value</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">function</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">average surface area</i> . Such information would have been difficult, if not impossible, to acquire via manual labeling based on the image alone. For detailed evaluation, we introduce an efficient crowdsourcing protocol for bounding box annotations in panoramic images, which we deploy to acquire 147,075 ground-truth object annotations for a subset of 7,348 images, the PanorAMS-clean dataset. For our PanorAMS-noisy dataset, we provide an extensive analysis of the noise and how different types of noise affect image classification and object detection performance. We make both datasets, PanorAMS-noisy and PanorAMS-clean, benchmarks and tools presented in this paper openly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://panorams.inskegroenen.nl/</uri> .

ГЕОПОЭТИКА ПРОСТРАНСТВА: ВЕНЕЦИЯ В АНГЛОЯЗЫЧНОЙ ЭССЕИСТИКЕ И. БРОДСКОГО

The article provides research into geopoetic image of Venice represented in the essay “Watermark” by I. Brodsky. Research approach includes methods of conceptual, narrative, stylistic analyses as well as fictional text interpretation method. The study is based on the analysis of narrative-conceptual models, that contain urban objects as one of their components. Within this approach, the following models were singled out: “city perceived by senses”, “city and season”, “city as retrospection”, and “city as water”. Each of the models is distinguished by a certain set of spatial objects and their characteristic features. Symbolic interpretation of these objects receives considerable attention in the paper as well. The study shows that the largest number of city objects is perceived by senses, mostly eyesight/eye. This concept is characterized by nominative density, text recurrence, wide scope of symbolic interpretations. The largest number of objects associated with Venice are represented within the model “city as retrospection” connected with walks, meetings, memories, and life situations. Water may be defined as the essay