Anomaly Detection in Surveillance Video of Natural Environment

This work demonstrates the effectiveness of the median filter combined with morphological operators in the detection of anomalies in video surveillance of scenes of natural environment. Natural environment is characterized by backgrounds that are not static but whose dynamics are limited and do not include the appearance or disappearance of background objects in the scene. Examples include background images with seawater or river surfaces, or landscapes with trees, in which the wind produces waves and other movements of limited amplitude. The performance on four publicly available benchmark videos is compared to that of other published state-of-the-art works. The results obtained are promising.

[1]  Boyang Wan,et al.  Weakly Supervised Video Anomaly Detection via Center-Guided Discriminative Learning , 2020, 2020 IEEE International Conference on Multimedia and Expo (ICME).

[2]  Zhou Wang,et al.  Image Quality Assessment: From Error Measurement to Structural Similarity , 2004 .

[3]  Martin D. Levine,et al.  An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions , 2013, Comput. Vis. Image Underst..

[4]  Thierry Bouwmans,et al.  Background Subtraction in Real Applications: Challenges, Current Models and Future Directions , 2019, Comput. Sci. Rev..

[5]  Olga Isupova,et al.  Machine learning methods for behaviour analysis and anomaly detection in video , 2018 .

[6]  Charles Guyon,et al.  Robust Principal Component Analysis for Background Subtraction: Systematic Evaluation and Comparative Analysis , 2012 .

[7]  Michael K. Ng,et al.  Median filtering‐based methods for static background extraction from surveillance video , 2015, Numer. Linear Algebra Appl..

[8]  Erkki Oja,et al.  Principal components, minor components, and linear neural networks , 1992, Neural Networks.

[9]  Zheng Wang,et al.  Deep Unsupervised Anomaly Detection , 2021, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[10]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[11]  Jeny Rajan,et al.  An Improved Contextual Information Based Approach for Anomaly Detection via Adaptive Inference for Surveillance Application , 2016, CVIP.

[12]  Nenghai Yu,et al.  A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis , 2019, ArXiv.

[13]  Stuart J. Russell,et al.  Image Segmentation in Video Sequences: A Probabilistic Approach , 1997, UAI.

[14]  Vishal M. Patel,et al.  One-Class Classification: A Survey , 2021, ArXiv.

[15]  Nikos Paragios,et al.  Motion-based background subtraction using adaptive kernel density estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[16]  Rita Cucchiara,et al.  Detecting Moving Objects, Ghosts, and Shadows in Video Streams , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Matteo Matteucci,et al.  A revaluation of frame difference in fast and robust motion detection , 2006, VSSN '06.

[18]  Nilanjan Ray,et al.  Snake Validation: A PCA-Based Outlier Detection Method , 2009, IEEE Signal Processing Letters.

[19]  Olaf Munkelt,et al.  Adaptive Background Estimation and Foreground Detection using Kalman-Filtering , 1995 .

[20]  Ranga Rodrigo,et al.  Abnormal activity recognition using spatio-temporal features , 2014, 7th International Conference on Information and Automation for Sustainability.