ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-4-2021
https://doi.org/10.5194/isprs-annals-V-4-2021-41-2021
https://doi.org/10.5194/isprs-annals-V-4-2021-41-2021
17 Jun 2021
 | 17 Jun 2021

AN EXPERIMENTAL ANALYSIS OF SPATIAL INDEXING ALGORITHMS FOR REAL TIME SAFETY CRITICAL MAP APPLICATION

F. Çetin and M. O. Kulekci

Keywords: Spatial data processing, Space partitioning, KD-Tree, Quad-KD-Tree, PR-Tree

Abstract. This paper presents a study that compares the three space partitioning and spatial indexing techniques, KD Tree, Quad KD Tree, and PR Tree. KD Tree is a data structure proposed by Bentley (Bentley and Friedman, 1979) that aims to cluster objects according to their spatial location. Quad KD Tree is a data structure proposed by Berezcky (Bereczky et al., 2014) that aims to partition objects using heuristic methods. Unlike Bereczky’s partitioning technique, a new partitioning technique is presented based on dividing objects according to space-driven, in the context of this study. PR Tree is a data structure proposed by Arge (Arge et al., 2008) that is an asymptotically optimal R-Tree variant, enables data-driven segmentation. This study mainly aimed to search and render big spatial data in real-time safety-critical avionics navigation map application. Such a real-time system needs to efficiently reach the required records inside a specific boundary. Performing range query during the runtime (such as finding the closest neighbors) is extremely important in performance. The most crucial purpose of these data structures is to reduce the number of comparisons to solve the range searching problem. With this study, the algorithms’ data structures are created and indexed, and worst-case analyses are made to cover the whole area to measure the range search performance. Also, these techniques’ performance is benchmarked according to elapsed time and memory usage. As a result of these experimental studies, Quad KD Tree outperformed in range search analysis over the other techniques, especially when the data set is massive and consists of different geometry types.