Segmentation and Sampling of Moving Object Trajectories Based on Representativeness

Abstract

Moving Object Databases (MOD), although ubiquitous, still call for methods that will be able to understand, search, analyze, and browse their spatiotemporal content. In this paper, we propose a method for trajectory segmentation and sampling based on the representativeness of the (sub-)trajectories in the MOD. In order to find the most representative sub-trajectories, the following methodology is proposed. First, a novel global voting algorithm is performed, based on local density and trajectory similarity information. This method is applied for each segment of the trajectory, forming a local trajectory descriptor that represents line segment representativeness. The sequence of this descriptor over a trajectory gives the voting signal of the trajectory, where high values correspond to the most representative parts. Then, a novel segmentation algorithm is applied on this signal that automatically estimates the number of partitions and the partition borders, identifying homogenous partitions concerning their representativeness. Finally, a sampling method over the resulting segments yields the most representative sub-trajectories in the MOD. Our experimental results in synthetic and real MOD verify the effectiveness of the proposed scheme, also in comparison with other sampling techniques.

Semantic trajectories modeling and analysis

“…However, the real challenge is the definition of a spatio-temporal distance that would better correspond to the spatio-temporal nature of trajectories. For instance, [Pelekis et al 2011a] defines a method that groups trajectories using various distance functions based on motion properties such as spatial location, speed, acceleration and direction. The method evaluates distances over the whole trajectories.…”

Warped K-Means: An algorithm to cluster sequentially-distributed data

“…Nevertheless, in some of the works of the "full sequences" branch (e.g., [38,49]), rather than full sequences, the elements to be clustered are subsequences, which are determined by some trajectory segmentation technique. These segmentation techniques can themselves be considered to belong to a different branch of the taxonomy, closer to our proposal, and will be discussed later.…”

“…Finally, the branch labeled "optimizing a criterion function" corresponds to general purpose approaches such as the the work presented in this paper and the segmentation techniques used in [4,38,49]. Some (or all) of these techniques can be more properly viewed from a curve fitting point of view, which is considered to be conceptually different from a clustering framework.…”

“…On the other hand, in [4,38,49], the desired number of segments is not explicitly specified, although it is implicitly determined by the choice of internal thresholds or regularization parameters. In contrast, in our approach, the number of segments (or clusters) is explicitly specified as its (unique) input parameter, as in classical clustering algorithms.…”

Hermoupolis: A Trajectory Generator for Simulating Generalized Mobility Patterns

“…The rapid growth of these technologies has increased the interest for data analysis upon trajectory datasets. As such, the field of mobility data mining has already many success stories to narrate, as these are described by works that identify various types of patterns, including, among others, clusters of entire trajectories [11] or of subtrajectories [9] [14], moving clusters [7], flocks [8] [5], sequential trajectory patterns [3], convoys [6], swarms [10], and top-k representative trajectory samples [12].…”