Jongmoo Choi
ABSTRACT
We present the design and implementation of an activity recognition system in wide area aerial video surveillance using Entity Relationship Models (ERM). In this approach, finding an activity is equivalent to sending a query to a Relational DataBase Management System (RDBMS). By incorporating reference imagery and Geographic Information System (GIS) data, tracked objects can be associated with physical meanings, and several high levels of reasoning, such as traffic patterns or abnormal activity detection, can be performed. We demonstrate that different types of activities, with hierarchical structure, multiple actors, and context information, are effectively and efficiently defined and inferred using the ERM framework. We also show how visual tracks can be better interpreted as activities by using geo information. Experimental results on both real visual tracks and GPS traces validate our approach.
- http://www.microsoft.com/sqlserver/.Google Scholar
- http://www.sdms.afrl.af.mil/index.php?collection=clif2006.Google Scholar
- P. P. Chen. The entity-relationship model - toward a unified view of data. ACM Trans. Database Syst., 1(1):9--36, 1976. Google ScholarDigital Library
- E. F. Codd. A relational model of data for large shared data banks. Commun. ACM, 13(6):377--387, 1970. Google ScholarDigital Library
- H. Gupta, L. Yu, A. Hakeem, T. E. Choe, N. Haering, and M. Locasto. Multimodal complex event detection framework for wide area surveillance. In CVPRW, pages 47--54, 2011.Google ScholarCross Ref
- R. Lange, F. Dürr, and K. Rothermel. Scalable processing of trajectory-based queries in space-partitioned moving objects databases. In 16th ACM SIGSPATIAL, GIS '08, pages 31:1--31:10, New York, NY, USA, 2008. ACM. Google ScholarDigital Library
- Y. Lin, Q. Yu, and G. Medioni. Efficient detection and tracking of moving objects in geo-coordinates. Mach. Vision Appl., 22(3):505--520, May 2011. Google ScholarDigital Library
- E. Pollard, B. Pannetier, and M. Rombaut. Convoy detection processing by using the hybrid algorithm (gmcphd/vs-immc-mht) and dynamic bayesian networks. In FUSION '09., pages 907--914, 2009.Google Scholar
- A. Pozdnoukhov. Dynamic network data exploration through semi-supervised functional embedding. In Proceedings of the 17th ACM SIGSPATIAL, pages 372--379, 2009. Google ScholarDigital Library
- J. Prokaj, M. Duchaineau, and G. Medioni. Inferring tracklets for multi-object tracking. In CVPRW, pages 37--44, 2011.Google ScholarCross Ref
- V. Reilly, H. Idrees, and M. Shah. Detection and tracking of large number of targets in wide area surveillance. In ECCV (3), pages 186--199, 2010. Google ScholarDigital Library
Index Terms
- Activity recognition in wide aerial video surveillance using entity relationship models
Recommendations
Activity recognition of the elderly
CASEMANS '10: Proceedings of the 4th ACM International Workshop on Context-Awareness for Self-Managing SystemsThe development of context aware services is one proposed way to support independent living for the elderly. Performing test scenarios with the elderly helps when developing the context aware services. However, rigorous testing is not always desirable ...
Activity recognition with hand-worn magnetic sensors
Activity recognition is a key technology for realizing ambient assisted living applications such as care of the elderly and home automation. This paper proposes a new activity recognition method that employs hand-worn magnetic sensors to recognize a ...
Activity Recognition based on High-Level Reasoning
ICPRAM 2016: Proceedings of the 5th International Conference on Pattern Recognition Applications and MethodsIn the context of Ambient Assisted Living (AAL), the detection of daily activities is an active field of research. In this study, we present an algorithm for the performed Activities of Daily Living (ADLs) related to personal hygiene, which is based on ...
Comments