Event Detection on Motion Activities Using a Dynamic Grid
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Event detection based on using features from a static grid can give poor results from the viewpoint of two main aspects: the position of the camera and the position of the event that is occurring in the scene. The former causes problems when training and test events are at different distances from the camera to the actual position of the event. The latter can be a source of problems when training events take place in any position in the scene, and the test events take place in a position different from the training events. Both issues degrade the accuracy of the static grid method. Therefore, this work proposes a method called a dynamic grid for event detection, which can tackle both aspects of the problem. In our experiment, we used the dynamic grid method to detect four types of event patterns: implosion, explosion, two-way, and one-way using a Multimedia Analysis and Discovery (MAD) pedestrian dataset. The experimental results show that the proposed method can detect the four types of event patterns with high accuracy. Additionally, the performance of the proposed method is better than the static grid method and the proposed method achieves higher accuracy than the previous method regarding the aforementioned aspects.
Abstract
Event detection based on using features from a static grid can give poor results from the viewpoint of two main aspects: the position of the camera and the position of the event that is occurring in the scene. The former causes problems when training and test events are at different distances from the camera to the actual position of the event. The latter can be a source of problems when training events take place in any position in the scene, and the test events take place in a position different from the training events. Both issues degrade the accuracy of the static grid method. Therefore, this work proposes a method called a dynamic grid for event detection, which can tackle both aspects of the problem. In our experiment, we used the dynamic grid method to detect four types of event patterns: implosion, explosion, two-way, and one-way using a Multimedia Analysis and Discovery (MAD) pedestrian dataset. The experimental results show that the proposed method can detect the four types of event patterns with high accuracy. Additionally, the performance of the proposed method is better than the static grid method and the proposed method achieves higher accuracy than the previous method regarding the aforementioned aspects.
참고문헌 (32)
- A. A. Sodemann, "A review of anomaly detection in automated surveillance", IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 42(6), pp.1257~1272 (2012)
- J. Y. Huang, "A smart camera network with SVM classifiers for crowd event recognition", Proceedings of the World Congress on Engineering 2014, pp.13~18 (2014)
- X. Yang, "AT&T research at TRECVID 2013: surveillance event detection", Proceedings of TRECVID Workshop (2013)
- S. Ojha, "Image processing techniques for object tracking in video surveillance: a survey", Proceedings of 2015 International Conference on Pervasive Computing (ICPC), pp.1~6 (2015)
- N. Ben Aoun, "Graph modeling based video event detection", Proceedings of 2011 International Conference on Innovations in Information Technology, pp.114~117 (2011)
- C. Piciarelli, "Surveillance-oriented event detection in video streams", IEEE Intelligent Systems, 26(3), pp.32~41 (2011)
- Y. Yan, "Event oriented dictionary learning for complex event detection", IEEE Transactions on Image Processing, 24(6), pp.1867~1878 (2015)
- M. Husni, "Crowd event detection in computer vision", Proceedings of 2010 2nd International Conference on Signal Processing Systems (ICSPS), pp.444~447 (2010)
- O. P. Popoola, "Video-based abnormal human behavior recognition : a review", IEEE Transactions on Systems, Man, and Cybernetics, Part C : Applications and Reviews, 42(6), pp.865~878 (2012)
- T. Xiao, "Learning to detect anomalies in surveillance video", IEEE Signal Processing Letters, 22(9), pp.1477~1481 (2015)
- J. Wu, "Pedestrian detection based on improved HOG feature and robust adaptive boosting algorithm", Proceedings of 2011 4th International Congress on Image and Signal Processing (CISP), pp.1535~1539 (2011)
- B. T. Morris, "A survey of vision-based trajectory learning and analysis for surveillance", IEEE Transactions on Circuits and Systems for Video Technology, 18(8), pp.1114~1127 (2008)
- W. Xu, "Intelligent Computing and Information Science", pp.556~561 (2011), Springer
- A. Hampapur, "Smart video surveillance for proactive security", IEEE Signal Processing Magazine, 25(4), pp.136~134 (2008)
- N. Suriani, "Sudden event recognition : a survey", Sensors, 13(8), pp.9966~9998 (2013)
- M. Haque, "Abnormal event detection in unseen scenarios", Proceedings of 2012 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp.378~383 (2012)
- M. S. Ahmed, "Detection of abnormal motions in video", Proceedings of International Workshop Multimodal Interactions Analysis of Users in a Controlled Environment (MIAUCE), pp.1~4 (2008)
- E. Saykol, "Keyframe labeling technique for surveillance event classification", Optical Engineering, 49(11) (2010)
- D. Zhang, "Crowd abnormal behavior detection based on machine learning", Information Technology Journal, 12(6), pp.1199~1205 (2013)
- Z. Wang, "Unusual event detection without tracking", Proceedings of 2009International Conference on Computational Intelligence and Software Engineering, pp.1~3 (2009)
- Z. Wang, "LHMM-based gathering detection in video surveillance", Proceedings of 2010International Conference on Intelligent Computing and Integrated Systems (ICISS), pp.213~216 (2010)
- S. Wang, "Anomaly detection in crowd scene using historical information", Proceedings of 2010International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp.1~4 (2010)
- V. Reddy, "Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture", Proceedings of 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.55~61 (2011)
- C. Y. Chen, "Crowd escape behavior detection and localization based on divergent centers", IEEE Sensors Journal, 15(4), pp.2431~2439 (2015)
- S. Wu, "A Bayesian model for crowd escape behavior detection", IEEE Transactions on Circuits and Systems for Video Technology, 24(1), pp.85~98 (2014)
- H. Hachiya, "NSH: normality sensitive hashing for anomaly detection", Proceedings of 2013IEEE International Conference on Computer Vision Workshops (ICCVW), pp.795~802 (2013)
- Q. Chang, "An approach of crowd abnormality detection guided by gathering and running parameters", Journal of Information and Computational Science, 9(16), pp.4835~4846 (2012)
- S. Saxena, "Advanced Concepts for Intelligent Vision Systems", pp.970~981 (2008), Springer
- J. R. van Huis, "Track-based event recognition in a realistic crowded environment", Proceedings of SPIE 9253: Optics and Photonics for Counterterrorism, Crime Fighting, and Defense X and Optical Materials and Biomaterials in Security and Defense Systems Technology XI (2014), International Society for Optics and Photonics
- T. Wang, "Histograms of optical flow orientation for abnormal events detection", Proceedings of 2013 IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), pp.45~52 (2013)
- "A MAD pedestrian dataset"[URL]
- J. Preechasuk, "Pedestrianly event detection using grid-based features", Proceedings of 2014 International Computer Science and Engineering Conference, pp.440~445 (2014)