Abstract
With the emergence of various types of indoor positioning technologies (e.g., radio-frequency identification, Wi-Fi, and iBeacon), how to rapidly retrieve indoor cells and moving objects has become a key factor that limits those indoor applications. Euclidean distance-based indexing techniques for outdoor moving objects cannot be used in indoor spaces due to the existence of indoor obstructions (e.g., walls). In addition, currently, the indexing of indoor moving objects is mainly based on space-related query and less frequently on semantic query. To address these two issues, the present study proposes a multi-floor adjacency cell and semantic-based index (MACSI). By integrating the indoor cellular space with the semantic space, the MACSI subdivides open cells (e.g., hallways and lobbies) using space syntax and optimizes the adjacency distances between three-dimensionally connected cells (e.g., elevators and stairs) based on the caloric cost that extends single floor indoor space to three dimensional indoor space. Moreover, based on the needs of semantic query, this study also proposes a multi-granularity indoor semantic hierarchy tree and establishes semantic trajectories. Extensive simulation and real-data experiments show that—compared with the indoor trajectories delta tree (ITD-tree) and the semantic-based index (SI)—the MACSI produces more reliable query results with significantly higher semantic query and update efficiencies; has superior semantic expansion capability; and supports multi-granularity complex semantic queries.
Highlights
According to the available statistics, humans spend 87% of their time in indoor spaces [1], such as private residences and office buildings
The multi-floor adjacency cell and semantic-based index (MACSI) expands single-floor indoor adjacency cellular spaces. It subdivides open cells using space syntax to ensure the reasonableness of the adjacency cellular spaces and to optimize connected cells based on the caloric cost
Given the specific needs of indoor semantic queries, the present study proposes a MGSH-tree and uses inverted indexing to improve the semantic query efficiency and expansion capability
Summary
According to the available statistics, humans spend 87% of their time in indoor spaces [1], such as private residences and office buildings. Humans produce vast numbers of indoor moving trajectories. On 5 March 2016, the 15 operation lines of the Beijing Subway handled a daily passenger volume of 9.6711 million [2]. Managing the massive data of indoor cells and moving objects is important for many applications, including object tracking [3], indoor navigation [4] and emergency evacuation [5]. Global Positioning Systems (GPS) cannot obtain accurate positioning results in indoor environments. With the development of indoor positioning technology, large volumes of tracking data have become available, greatly promoting the vigorous development of ISPRS Int. J.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
