Semantic Trajectories: Mobility Data Computation and Annotation

With the large-scale adoption of GPS equipped mobile sensing devices, positional data generated by moving objects (e.g., vehicles, people, animals) are being easily collected. Such data are typically modeled as streams of spatio-temporal (x,y,t) points, called ''trajectories''. In recent years trajectory management research has progressed significantly towards efficient storage and indexing techniques, as well as suitable knowledge discovery. These works focused on the geometric aspect of the raw mobility data. We are now witnessing a growing demand in several application sectors (e.g., from shipment tracking to geo-social networks) on understanding the {\it semantic'' behavior of moving objects. Semantic behavior refers to the use of semantic abstractions of the raw mobility data, including not only geometric patterns but also knowledge extracted jointly from the mobility data and the underlying geographic and application domains information. The core contribution of this paper lies in a ''Semantic Model'' and a ''Computation and Annotation Platform'' for developing a semantic approach that progressively transforms the raw mobility data into semantic trajectories enriched with annotations and segmentations. We also analyze a number of experiments we did with semantic trajectories in different domains.

Conceptual modeling of multimedia databases

Oleksandr Drutskyy

The gap between the semantic content of multimedia data and its underlying physical representation is one of the main problems in the modern multimedia research in general, and, in particular, in the field of multimedia database modeling. We believe that one of the principal reasons of this problem is the attempt to conceptually represent multimedia data in a way, which is similar to its low-level representation by applications dealing with encoding standards, feature-based multimedia analysis, etc. In our opinion, such conceptual representation of multimedia contributes to the semantic gap by separating the representation of multimedia information from the representation of the universe of discourse of an application, to which the multimedia information pertains. In this research work we address the problem of conceptual modeling of multimedia data in a way to deal with the above-mentioned limitations. First, we introduce two different paradigms of conceptual understanding of the essence of multimedia data, namely: multimedia as data and multimedia as metadata. The multimedia as data paradigm, which views multimedia data as the subject of modeling in its own right, is inherent to so-called multimedia-centric applications, where multimedia information itself represents the main part of the universe of discourse. The examples of such kind of applications are digital photo collections or digital movie archives. On the other hand, the multimedia as metadata paradigm, which is inherent to so-called multimedia-enhanced applications, views multimedia data as just another (optional) source of information about whatever universe of discourse that the application pertains to. An example of a multimedia-enhanced application is a human-resource database augmented with employee photos. Here the universe of discourse is the totality of company employees, while their photos simply represent an additional (possibly optional) kind of information describing the universe of discourse. The multimedia conceptual modeling approach that we present in this work allows addressing multimedia-centric applications, as well as, in particular, multimedia-enhanced applications. The model that we propose builds upon MADS (Modeling Application Data with Spatio-temporal features), which is a rich conceptual model defined in our laboratory, and which is, in particular, characterized by structural completeness, spatio-temporal modeling capabilities, and multirepresentation support. The proposed multimedia model is provided in the form of a new modeling dimension of MADS, whose orthogonality principle allows to integrate the new multimedia modeling dimension with already existing modeling features of MADS. The following multimedia modeling constructs are provided: multimedia datatypes, simple and complex representational constraints (relationships), a multimedia partitioning mechanism, and multimedia multirepresentation features. Following the description of our conceptual multimedia modeling approach based on MADS, we present the peculiarities of logical multimedia modeling and of conceptual-to-logical inter-layer transformations. We provide a set of mapping guidelines intended to help the schema designer in coming up with rich logical multimedia document representations of the application domain, which conform with the conceptual multimedia schema. The practical interest of our research is illustrated by a mock-up application, which has been developed to support the theoretical ideas described in this work. In particular, we show how the abstract conceptual set-based representations of multimedia data elements, as well as simple and complex multimedia representational relationships can be implemented using Oracle DBMS.

EPFL2009

SeMiTri: A Framework for Semantic Annotation of Heterogeneous Trajectories

Karl Aberer, Dipanjan Chakraborty, Christine Parent, Stefano Spaccapietra, Zhixian Yan

GPS devices allow recording the movement track of the moving object they are attached to. This data typically consists of a stream of spatio-temporal (x,y,t) points. For application purposes the stream is transformed into finite subsequences called {\em trajectories}. Existing knowledge extraction algorithms defined for trajectories mainly assume a specific context (e.g. vehicle movements) or analyze specific parts of a trajectory (e.g. stops), in association with data from chosen geographic sources (e.g. points-of-interest, road networks). We investigate a more comprehensive semantic annotation framework that allows enriching trajectories with any kind of semantic data provided by multiple 3rd party sources. This paper presents SeMiTri - the framework that enables annotating %all meaningful parts of trajectories for any kind of moving objects. Doing so, the application can benefit from a {\it \lq\lq semantic trajectory\rq\rq} representation of the physical movement. The framework and its algorithms have been designed to work on trajectories with varying data quality and different structures, with the objective of covering abstraction requirements of a wide range of applications. Performance of SeMiTri has been evaluated using many GPS datasets from multiple sources -- including both fast moving objects (e.g. cars, trucks) and people's trajectories (e.g. with smartphones). These two kinds of experiments are reported in this paper.

ACM2011

Conceptual modeling of multimedia databases

Oleksandr Drutskyy

EPFL2009