Flag Counter
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893

Anomaly Detection with Structural Similarity and Optical Flow Histogram

Yapısal Benzerlik ve Optik Akış Histogramı ile Anomali Tespiti

How to cite: Öz K, Karaş R. Anomaly detection with structural similarity and optical flow histogram. J Intell Syst Appl 2018; 1(2): 127-130. DOI: 10.54856/jiswa.201812040

Full Text: PDF, in Turkish.

Total number of downloads: 392

Title: Anomaly Detection with Structural Similarity and Optical Flow Histogram

Abstract: In this paper, we present an anomaly detection and localization system for surveillance systems. A new feature descriptor is proposed. The spatio-temporal identifiers are obtained by using optical flow histogram and the structural similarity index from the videos that contain normal conditions. An artificial neural network, Selforganizing maps are used in modeling. The proposed system has been tested on the UCSD dataset.

Keywords: Anomaly detection; optical flow histogram; structural similarity index; video surveillance


Başlık: Yapısal Benzerlik ve Optik Akış Histogramı ile Anomali Tespiti

Özet: Bu çalışmada, gözetim sistemleri için tasarlanmış bir anomali tespit ve lokalizasyon sistemi sunulmaktadır. Yeni bir özellik tanımlayıcı önerilmektedir. Normal durumları içeren videolardan optik akış histogramı ve yapısal benzerlik indeksi kullanılarak konum-zamansal tanımlayıcılar elde edilmektedir. Modellemede yapay sinir ağlarından öz düzenleyici haritalar kullanılmaktadır. Önerilen sistem UCSD verisetinde denenmiştir.

Anahtar kelimeler: Anomali tespiti; optik akış histogramı; yapısal benzerlik indisi; video gözetim


Bibliography:
  • Oz K, Gorgunoglu S. A review on anomaly detection in video surveillance systems. El-Cezeri Journal 2016; 3(3): 506–512.
  • Kim J, Grauman K. Observe locally, infer globally: A spacetime MRF for detecting abnormal activities with incremental updates. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA, pp. 2921–2928.
  • Parvathy R, Thilakan S, Joy M, Sameera KM. Anomaly detection using motion patterns computed from optical flow. In 2013 Third International Conference on Advances in Computing and Communications, August 29-31, 2013, Cochin, India, pp. 58-61.
  • Liu Y. Abnormal crowd behavior detection based on optical flow and dynamic threshold. In Proceeding of the 11th World Congress on Intelligent Control and Automation, June 29-July 4, 2014, Shenyang, China, pp. 2902–2906.
  • Risha KP, Kumar AC. Gradient operator in video after object detection by optical flow and morphological operation. In 2016 10th International Conference on Intelligent Systems and Control (ISCO), January 7-8, 2016, Coimbatore, India, pp. 1–4.
  • Colque RVHM, Caetano C, de Andrade MTL, Schwartz WR. Histograms of optical flow orientation and magnitude and entropy to detect anomalous events in videos. IEEE Transactions on Circuits and Systems for Video Technology 2017; 27(3): 673–682.
  • Oz K, Gorgunoglu S. Anomaly detection system with optical flow method. In 2nd International Conference on Science, Ecology and Technology-2016 (ICONSETE’2016), August 23-25, 2016. Barcelona, Spain, p. 490.
  • Xu D, Wu X, Song D, Li N, Chen YL. Hierarchical activity discovery within spatio-temporal context for video anomaly detection. In 2013 IEEE International Conference on Image Processing, September 15-18, 2013, Melbourne, VIC, Australia, pp. 3597–3601.
  • Horn B, Schunck B. Determining optical flow: A retrospective. Artificial Intelligence 1993; 59(1–2): 81–87.
  • Liu C. Beyond pixels: Exploring new representations and applications for motion analysis. Massachusetts Institute of Technology, Cambridge, MA, USA, 2009.
  • Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 2004; 13(4): 600–612.
  • Brunet D, Vrscay ER, Wang Z. On the mathematical properties of the structural similarity index. IEEE Transactions on Image Processing 2012; 21(4): 1488–1495.
  • Fan X, Zheng B, Li M, Li W, Zhang J, Zhang Z. Characterization for complex trajectory and anomaly detection. In 2014 International Conference on Information Science, Electronics and Electrical Engineering, April 26-28, 2014, Sapporo, Japan, pp. 725-730.
  • Fathy M, Sabokrou M, Hosseini M. Abnormal event detection and localization in crowded scenes based on similarity structure. The Modares Journal of Electrical Engineering 2016; 14(3): 1–12.
  • Sabokrou M, Fathy M, Hosseini M, Klette R. Real-time anomaly detection and localization in crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence 2015; 36(1): 18–32.
  • Kohonen T. Self-organized formation of topologically correct feature maps. Biological Cybernetics 1982; 43(1): 59–69.
  • Kohonen T. MATLAB Implementations and Applications of the Self-Organizing Map. Unigrafia Oy, Helsinki, Finland, 2014.
  • UCSD Anomaly Detection Dataset. 2013, Reteived from http://www.svcl.ucsd.edu/projects/anomaly/dataset.htm