Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 56
-
ItemIndoor view graph: A model to capture route and configurational information(SAGE Publications, 2024-01-01)This paper presents a graph model that simultaneously stores route and configurational information about indoor spaces. Existing indoor information models either capture route information to compute shortest paths and to generate route descriptions (i.e., answering how-to-get-to questions), or they store configurational information about objects and places and their spatial relationships to enable spatial querying and inference (i.e., answering where-questions). Consequently, multiple representations of an indoor environment must be stored in information systems to address the various information needs of their users. In this paper, we propose a graph that can capture both configurational and route information in a unified manner. The graph is the dual representation of connected lines of sight, or views. Views can represent continuous movement in an indoor environment, and at the same time, the visible configurational information of each view can be explicitly captured. In this paper, we discuss the conceptual design of the model and an automatic approach to derive the view graph from floorplans. Finally, we demonstrate the capabilities of our model in performing different tasks such as calculating shortest paths, generating route descriptions, and deriving place graphs.
-
ItemBenchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation From MLS(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2024)Vegetation is crucial for sustainable and resilient cities providing various ecosystem services and well-being of humans. However, vegetation is under critical stress with rapid urbanization and expanding infrastructure footprints. Consequently, mapping of this vegetation is essential in the urban environment. Recently, deep learning (DL) for point cloud semantic segmentation has shown significant progress. Advanced models attempt to obtain state-of-the-art performance on benchmark datasets, comprising multiple classes and representing real-world scenarios. However, class-specific segmentation with respect to vegetation points has not been explored. Therefore, selection of a DL model for vegetation points segmentation is ambiguous. To address this problem, we provide a comprehensive assessment of point-based DL models for semantic segmentation of vegetation class. We have selected seven representative-point-based models, namely, PointCNN, KPConv (omni-supervised), RandLANet, SCFNet, PointNeXt, SPoTr, and PointMetaBase. These models are investigated on three different datasets, specifically Chandigarh, Toronto3D, and Kerala, which are characterized by diverse nature of vegetation and varying scene complexity combined with changing per-point features and classwise composition. PointMetaBase and KPConv (omni-supervised) achieve the highest mIoU on the Chandigarh (95.24%) and Toronto3D datasets (91.26%), respectively while PointCNN provides the highest mIoU on the Kerala dataset (85.68%). The article develops a deeper insight, hitherto not reported, into the working of these models for vegetation segmentation and outlines the ingredients that should be included in a model specifically for vegetation segmentation. This article is a step toward the development of a novel architecture for vegetation points segmentation.
-
ItemNo Preview AvailableGranularity of origins and clustering destinations in indoor wayfinding(ELSEVIER SCI LTD, 2023-01)
-
ItemTranslating Place-Related Questions to GeoSPARQL Queries(ASSOC COMPUTING MACHINERY, 2022)Many place-related questions can only be answered by complex spatial reasoning, a task poorly supported by factoid question retrieval. Such reasoning using combinations of spatial and non-spatial criteria pertinent to place-related questions is increasingly possible on linked data knowledge bases. Yet, to enable question answering based on linked knowledge bases, natural language questions must first be re-formulated as formal queries. Here, we first present an enhanced version of YAGO2geo, the geospatially-enabled variant of the YAGO2 knowledge base, by linking and adding more than one million places from OpenStreetMap data to YAGO2. We then propose a novel approach to translate the place-related questions into logical representations, theoretically grounded in the core concepts of spatial information. Next, we use a dynamic template-based approach to generate fully executable GeoSPARQL queries from the logical representations. We test our approach using the Geospatial Gold Standard dataset and report substantial improvements over existing methods.
-
ItemNo Preview AvailableNeural factoid geospatial question answering(UNIV MAINE, 2021)Existing question answering systems struggle to answer factoid questions when geospatial information is involved. This is because most systems cannot accurately detect the geospatial semantic elements from the natural language questions, or capture the semantic relationships between those elements. In this paper, we propose a geospatial semantic encoding schema and a semantic graph representation which captures the semantic relations and dependencies in geospatial questions. We demonstrate that our proposed graph representation approach aids in the translation from natural language to a formal, executable expression in a query language. To decrease the need for people to provide explanatory information as part of their question and make the translation fully automatic, we treat the semantic encoding of the question as a sequential tagging task, and the graph generation of the query as a semantic dependency parsing task. We apply neural network approaches to automatically encode the geospatial questions into spatial semantic graph representations. Compared with current template-based approaches, our method generalises to a broader range of questions, including those with complex syntax and semantics. Our proposed approach achieves better results on GeoData201 than existing methods.
-
ItemNo Preview AvailableThe semantics of place-related questions(UNIV MAINE, 2021)The trend to equip information systems with question-answering capabilities raises the design problem of deciding which questions a system should be able to answer. Typical solutions build on mining human conversations or logs from similar systems for question patterns. For the case of questions about geographic places, we present a complementary approach, showing how to derive possible questions from an ontology of spatial information and a classification of place facets. We argue that such an approach reduces the inherent and substantial data bias of current solutions. At a more general level, we provide a novel understanding of spatial questions and their role in designing and using spatial information systems.
-
ItemNo Preview AvailablePose-aware monocular localization of occluded pedestrians in 3D scene space(Elsevier BV, 2021-12-01)
-
ItemNo Preview AvailableTowards detecting, characterizing, and rating of road class errors in crowd-sourced road network databases(UNIV MAINE, 2021-01-01)OpenStreetMap (OSM), with its global coverage and Open Database License, has recently gained popularity. Its quality is adequate for many applications, but since it is crowd-sourced, errors remain an issue. Errors in associated tags of the road network, for example, are impacting routing applications. Particularly road classification errors of ten lead to false assumptions about capacity, maximum speed, or road quality, possibly resulting in detours for routing applications. This study aims at finding potential classifi cation errors automatically, which can then be checked and corrected by a human expert. We develop a novel approach to detect road classification errors in OSM by searching for disconnected parts and gaps in different levels of a hierarchical road network. Different parameters are identified that indicate gaps in road networks. These parameters are then combined in a rating system to obtain an error probability to suggest possible misclassifi cations to a human user. The methodology is applied to an exemplar case for the state of New South Wales in Australia. The results demonstrate that (1) more classification errors are found at gaps than at disconnected parts, and (2) the gap search enables the user to find classification errors quickly using the developed rating system that indicates an error probability. In future work, the methodology can be extended to include available tags in OSM for the rating system. The source code of the implementation is available via GitHub.
-
ItemDecentralized management of ephemeral traffic incidents(WILEY, 2022-08)Abstract Ephemeral traffic incidents, such as a fallen tree on a road, pose traffic safety hazards, and impact locally on traffic. While these incidents are neither predictable nor persistent, their existence is relevant for all vehicles planning to pass by while the impact continues. This article develops a novel communication strategy for vehicular ad hoc networks aiming to inform all the affected vehicles, while involving only the minimum number of non‐affected vehicles. This strategy exploits time geography as a spatial and temporal filter, ensuring also that the information broadcasting timely terminates when the incident is over. Agent‐based traffic simulations show that, when a road is temporarily blocked due to an ephemeral incident, the proposed decentralized information management model achieves significant improvement in travel efficiency and automatically updates outdated incident information in time.
-
ItemSpatial Concepts in the Conversation With a Computer(ASSOC COMPUTING MACHINERY, 2021-07)Conversing about places with a computer poses a range of challenges to current AI.