&lt;title&gt;STRG-QL: spatio-temporal region graph query language for video databases&lt;/title&gt;

Lee, Jeong-Kyu; Çelebi, Mehmet

doi:10.1117/12.765531

Cited by 13 publications

(20 citation statements)

References 21 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to a spatial location of a hurricane track, i.e., longitude and latitude, there are more features to be considered for the hurricane data analysis, such as wind speed, pressure, and temperature. Another example is moving objects in video surveillance system [72,73,74] where a set of features includes not only a location of a moving object, but also size, color, and speed of an object.…”

Section: Model Formationmentioning

confidence: 99%

A Graph-Based Approach for Modeling and Indexing Video Data

Lee

2006

Eighth IEEE International Symposium on Multimedia (ISM'06)

Self Cite

View full text Add to dashboard Cite

Section: Model Formationmentioning

confidence: 99%

A Graph-Based Approach for Modeling and Indexing Video Data

Lee

2006

Eighth IEEE International Symposium on Multimedia (ISM'06)

Self Cite

View full text Add to dashboard Cite

“…This method is specific to video data and we are not sure if it can be applied to more general histories. Also the assumption that data follows some basic model (Gaussian in [21]) can be violated, which would result in missing qualifying histories. Other domain specific approaches have been proposed.…”

Section: Related Workmentioning

confidence: 99%

“…Lee et al [21] propose a graph based data structure to capture spatial and temporal features of video data. They use a model-based expectation maximization approach to group similar object graphs.…”

Section: Related Workmentioning

confidence: 99%

“…For instance, a Minimum Bounding hyper-Rectangle (MBR) extracted from a segment of a d-dimensional history is a 2(d + 1)-dimensional vector. We are not aware of any work that addresses the problem for larger values of d, except two works on indexing video sequences; one work does not consider the order of the frames [29] while the other uses techniques specialized to video sequences [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On efficiently searching trajectories and archival data for historical similarities

Sherkat

Rafiei

2008

Proc. VLDB Endow.

View full text Add to dashboard Cite

We study the problem of efficiently evaluating similarity queries on histories, where a history is a d-dimensional time series for d ≥ 1. While there are some solutions for timeseries and spatio-temporal trajectories where typically d ≤ 3, we are not aware of any work that examines the problem for larger values of d. In this paper, we address the problem in its general case and propose a class of summaries for histories with a few interesting properties. First, for commonly used distance functions such as the Lp-norm, LCSS, and DTW, the summaries can be used to efficiently prune some of the histories that cannot be in the answer set of the queries. Second, histories can be indexed based on their summaries, hence the qualifying candidates can be efficiently retrieved. To further reduce the number of unnecessary distance computations for false positives, we propose a finer level approximation of histories, and an algorithm to find an approximation with the least maximum distance estimation error. Experimental results confirm that the combination of our feature extraction approaches and the indexability of our summaries can improve upon existing methods and scales up for larger values of d and database sizes, based on our experiments on real and synthetic datasets of 17-dimensional histories.

show abstract

“…3,4 Most existing methods for the clustering focus on finding the optimum of overall partitioning. However, these approaches cannot provide any descriptions of the clusters.…”

Section: -4mentioning

confidence: 99%

A model-based conceptual clustering of moving objects in video surveillance

Lee¹,

Rajauria²,

Shah³

2007

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Data mining techniques have been applied in video databases to identify various patterns or groups. Clustering analysis is used to find the patterns and groups of moving objects in video surveillance systems. Most existing methods for the clustering focus on finding the optimum of overall partitioning. However, these approaches cannot provide meaningful descriptions of the clusters. Also, they are not very suitable for moving object databases since video data have spatial and temporal characteristics, and high-dimensional attributes. In this paper, we propose a model-based conceptual clustering (MCC) of moving objects in video surveillance based on a formal concept analysis. Our proposed MCC consists of three steps: 'model formation', 'model-based concept analysis', and 'concept graph generation'. The generated concept graph provides conceptual descriptions of moving objects. In order to assess the proposed approach, we conduct comprehensive experiments with artificial and real video surveillance data sets. The experimental results indicate that our MCC dominates two other methods, i.e., generality-based and error-based conceptual clustering algorithms, in terms of quality of concepts.

show abstract

<title>STRG-QL: spatio-temporal region graph query language for video databases</title>

Cited by 13 publications

References 21 publications

A Graph-Based Approach for Modeling and Indexing Video Data

A Graph-Based Approach for Modeling and Indexing Video Data

On efficiently searching trajectories and archival data for historical similarities

A model-based conceptual clustering of moving objects in video surveillance

Contact Info

Product

Resources

About