Search

Browse

• Communities
• Authors
• Year
• Titles
• Subjects

My Space

• Login

Modeling movement relations in dynamic urban scenes

Partsinevelos Panagiotis, Stefanidis Efstratios, Peggy Agouris

Full record

---

Summary

In this paper we address the problem of analyzing and managing movement in dynamic scenes captured in videodatasets. We present an approach to summarize the important information included in video datasets by analyzing thetrajectories of objects within them. Trajectories form the basis for the construction of abstract data types upon whichsimilarity of behaviors and expected behavior processes take place. We base our selection of representative timeinstances on the segmentation of trajectory lines into break points termed “nodes”. The nodes are distributeddynamically to capture the information content of regions within the 3-D spatiotemporal space. They are computedthrough self-organizing maps of neural network processing. Additional nodes are supplementing the procedure and areoriginated from reasoning and proximity analysis. Topologic relations between moving objects in the scene anddynamic topology of the trajectories are processed in order to include the significant information of movement relationsin the product summary. This work provides a novel approach to manage dynamic scene analysis at higher levels ofabstraction, and to represent concisely the behavior of moving relations in a scene.

Available Files

Services