No abstract

The increasing complexity of modern buildings has challenged the mobility of people with disabilities (PWD) in the indoor environment. To help overcome this problem, this paper proposes a data model that can be easily applied to indoor spatial information services for people with disabilities. In the proposed model, features are defined based on relevant regulations that stipulate significant mobility factors for people with disabilities. To validate the model’s capability to describe the indoor spaces in terms that are relevant to people with mobility disabilities, the model was used to generate data in a path planning application, considering two different cases in a shopping mall. The application confirmed that routes for people with mobility disabilities are significantly different from those of ordinary pedestrians, in a way that reflects features and attributes defined in the proposed data model. The latter can be inserted as an IndoorGML extension, and is thus expected to facilitate relevant data generation for the design of various services for people with disabilities.

The non-spatial information of cadastral maps must be repeatedly updated to monitor recent changes in land property and to detect illegal land registrations by tax evaders. Since non-spatial information, such as land category, is usually updated by field-based surveys, it is time-consuming and only a limited area can be updated at a time. Although land categories can be updated by remote sensing techniques, the update is typically performed through manual analysis, namely through a visually interpreted comparison between the newly generated land information and the existing cadastral maps. A cost-effective, fast alternative to the current surveying methods would improve the efficiency of land management. For this purpose, the present study analyzes the discrepancy between the existing cadastral map and the actual land use. Our proposed method operates in two steps. First, an up-to-date land cover map is generated from hyperspectral unmanned aerial vehicle (UAV) images. These images are effectively classified by a hybrid two- and three-dimensional convolutional neural network. Second, a discrepancy map, which contains the ratio of the area that is being used differently from the registered land use in each parcel, is constructed through a three-stage inconsistency comparison. As a case study, the proposed method was evaluated using hyperspectral UAV images acquired at two sites of Jeonju in South Korea. The overall classification accuracies of six land classes at Sites 1 and 2 were 99.93% and 99.75% and those at Sites 1 and 2 are 39.4% and 34.4%, respectively, which had discrepancy ratios of 50% or higher. Finally, discrepancy maps between the land cover maps and existing cadastral maps were generated and visualized. The method automatically reveals the inconsistent parcels requiring updates of their land category. Although the performance of the proposed method depends on the classification results obtained from UAV imagery, the method allows a flexible modification of the matching criteria between the land categories and land coverage. Therefore, it is generalizable to various cadastral systems and the discrepancy ratios will provide practical information and significantly reduce the time and effort for land monitoring and field surveying.

Demand for a Pedestrian Navigation Service (PNS) is on the rise. To provide a PNS for the transportation of vulnerable people, more detailed information of pedestrian facilities and obstructions should be included in Pedestrian Network Data (PND) used for PNS. Such data can be constructed efficiently by collecting GPS trajectories and integrating them with the existing PND. However, these two kinds of data have geometric differences and topological inconsistencies that need to be addressed. In this paper, we provide a methodology for integrating pedestrian facilities and obstructions information with an existing PND. At first we extracted the significant points from user-collected GPS trajectory by identifying the geometric difference index and attributes of each point. Then the extracted points were used to make an initial solution of the matching between the trajectory and the PND. Two geometrical algorithms were proposed and applied to reduce two kinds of errors in the matching: on dual lines and on intersections. Using the final solution for the matching, we reconstructed the node/link structure of PND including the facilities and obstructions information. Finally, performance was assessed with a test site and 79.2% of the collected data were correctly integrated with the PND.

The demand for place retrieval and route guidance services of indoor environments has increased owing to the extensive development of large complexes. In comparison to increasingly customizable and diversified general place retrieval services, indoor place‐related services currently offer few features. Existing knowledge graphs mostly deal with limited spatial context based on geographic location, and hence do not cover indoor environments. In this study, we propose a framework for a Spatial‐Semantic integrated Indoor Knowledge Graph (SSIKG) as a multi‐layered model of the indoor environment. The spatial layer involves knowledge of navigable paths by preserving network‐based topological relationships between places. Concurrently, the semantic layer expresses features from an end‐user perspective. To assess framework utility, place retrieval tests with resulting graphs were performed for six practical use cases, returning lists of the places and their corresponding optimal paths. Finally, the results were reviewed in terms of spatial inference and expansion of our graphs.