Recognizing events in an automated surveillance system

Date

2006-01-01

Author

Orten, Birant
Alatan, Abdullah Aydın
Çiloğlu, Tolga

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

89
views

0
downloads

Event recognition is probably the ultimate purpose of an automated surveillance system. In this paper, hidden Markov models (HMM) are utilized to recognize the nature of an event occurring in a scene. For this purpose, object trajectories, which are obtained through a successful track, are obtained as a sequence of flow vectors that contain instantaneous velocity and location information. These vectors are clustered by K-means algorithm to obtain a prototype representation. HMMs are trained with sequences obtained from usual motion patterns and abnormality is detected by measuring distances to these models. In order to specify the number of models automatically, a novel approach is proposed which utilizes the clues provided by centroid clustering. Preliminary experimental results are promising for detecting abnormal events.

URI

https://hdl.handle.net/11511/52760

Journal

MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Event detection in automated surveillance systems Orten, B. Birant; Alatan, Abdullah Aydın; Ciloglu, Tolga (2006-01-01) Event recognition is probably the ultimate purpose of an automated surveillance system. In this paper, hidden Markov models (HMM) are utilized to recognize the nature of an event occurring in a scene. For this purpose, object trajectories, which are obtained through a successful track, are written as a sequence of flow vectors that contain instantaneous velocity and location information. These vectors are clustered by K-means algorithm to obtain a prototype representation. HMMs are trained with sequences ob...
Tracking in WiMAX Networks Using Cell-IDs Bshara, Mussa; Orguner, Umut; Van Biesen, Leo (2009-07-10) There is some skepticism regarding the practical implementation of a tracking system that depends on cell identification (Cell-ID) information. This pessimism is due to the fact that tracking systems are known to require high positioning accuracy, while Cell-ID positioning is known as being "low accuracy" positing technique. However, using the Cell-IDs in a different way (a novel approach) than in current positioning will allow the implementation of a tracking system capable of providing sufficient position...
HUMAN GAIT PARAMETER ESTIMATION BASED ON MICRO-DOPPLER SIGNATURES USING PARTICLE FILTERS Guldogan, M. B.; Gustafsson, F.; Orguner, Umut; Bjorklund, S.; Petersson, H.; Nezirovic, A. (2011-05-27) Monitoring and tracking human activities around restricted areas is an important issue in security and surveillance applications. The movement of different parts of the human body generates unique micro-Doppler features which can be extracted effectively using joint time-frequency analysis. In this paper, we describe the simultaneous tracking of both location and micro-Doppler features of a human using particle filters (PF). The results obtained using the data from a 77 GHz radar prove the successful usage ...
Surveillance Video Querying With A Human-in-the-Loop STONEBROKER, MICHAEL; Bhargava, Bharat; Cafarella, Michael; COLLINS, ZACHARY; McClellan, Jenna; SIPSER, AARON; Sun, Tao; NESEN, ALİNA; SOLAIMAN, K.M.A.; MANI, GANAPATHY; Kochpatcharin, Kevin; Kochpatcharin, Kevin; Angın, Pelin; MACDONALD, JAMES (2020-06-19) SurvQ is a video monitoring system appropriate for surveillance applications such as those found in security and law enforcement. It performs real time object property identification and stores all data in a scalable DBMS. Standing queries implemented as database triggers are supported. SurvQ contains novel adaptive machine learning and algorithmic property classification. The application of SurvQ to assist the West Lafayette (IN) police department at identifying suspects in video is described. This paper a...
Pedestrian zone anomaly detection by non-parametric temporal modelling Gündüz, Ayşe Elvan; Taşkaya Temizel, Tuğba; Temizel, Alptekin (2014-08-29) With the increasing focus on safety and security in public areas, anomaly detection in video surveillance systems has become increasingly more important. In this paper, we describe a method that models the temporal behavior and detects behavioral anomalies in the scene using probabilistic graphical models. The Coupled Hidden Markov Model (CHMM) method that we use shows that sparse features obtained via feature detection and description algorithms are suitable for modeling the temporal behavior patterns and ...

Citation Formats

B. Orten, A. A. Alatan, and T. Çiloğlu, “Recognizing events in an automated surveillance system,” MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY, pp. 434–441, 2006, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52760.