Anomalous Situation Detection in Complex Scenes

In this paper we investigate a robust method to identify anomalies in complex scenes. This task is performed by evaluating the collective behavior by extracting the local binary patterns (LBP) and Laplacian of Gaussian (LoG) features. We fuse both features together which are exploited to train an MLP neural network during the training stage, and the anomaly is identified on the test samples. Considering the challenge of tracking individuals in dense crowded scenes due to multiple occlusions and clutter, in this paper we extract LBP and LoG features and use them as an approximate representation of the anomalous situation. These features well match the appearance of anomaly and their consistency, and accuracy is higher both in regular and irregular areas compared to other descriptors. In this paper, these features are exploited as input prior to train the neural network. The MLP neural network is subsequently explored to consider these features that can detect the anomalous situation. The experimental tests are conducted on a set of benchmark video sequences commonly used for anomaly situation detection.

[1]  Asif Khan,et al.  Coordinated unmanned aerial vehicles for surveillance of targets , 2015 .

[2]  Michael Blumenstein,et al.  A study on detecting drones using deep convolutional neural networks , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[3]  Stefania Bandini,et al.  Analyzing crowd behavior in naturalistic conditions: Identifying sources and sinks and characterizing main flows , 2016, Neurocomputing.

[4]  Stefania Bandini,et al.  Detection of Social Groups in Pedestrian Crowds Using Computer Vision , 2015, ACIVS.

[5]  Francesco G. B. De Natale,et al.  Traffic accident detection through a hydrodynamic lens , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[6]  Muhammad Saqib,et al.  Detecting dominant motion patterns in crowds of pedestrians , 2017, International Conference on Graphic and Image Processing.

[7]  Michael Blumenstein,et al.  Texture-based feature mining for crowd density estimation: A study , 2016, 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ).

[8]  Nicola Conci,et al.  Real-time anomaly detection in dense crowded scenes , 2014, Electronic Imaging.

[9]  Muhammad Uzair,et al.  A hybrid social influence model for pedestrian motion segmentation , 2018, Neural Computing and Applications.

[10]  Aakash Ahmad,et al.  CrashSafe: a formal model for proving crash-safety of Android applications , 2018, Human-centric Computing and Information Sciences.

[11]  Michael Blumenstein,et al.  Extracting descriptive motion information from crowd scenes , 2017, 2017 International Conference on Image and Vision Computing New Zealand (IVCNZ).

[12]  Habib Ullah,et al.  Crowd Motion Analysis: Segmentation, Anomaly Detection, and Behavior Classification , 2015 .

[13]  Ahmed B. Altamimi,et al.  Anomalous entities detection and localization in pedestrian flows , 2018, Neurocomputing.

[14]  Mohib Ullah,et al.  Comparative Study : The Evaluation of Shadow Detection Methods , 2013 .

[15]  Nicu Sebe,et al.  Particles cross-influence for entity grouping , 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

[16]  Bernhard Rinner,et al.  Multiscale observation of multiple moving targets using Micro Aerial Vehicles , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[17]  Nicola Conci,et al.  Dominant Motion Analysis in Regular and Irregular Crowd Scenes , 2014, HBU.

[18]  Saleh Basalamah,et al.  Counting of People in the Extremely Dense Crowd using Genetic Algorithm and Blobs Counting , 2013 .

[19]  Muhammad Uzair,et al.  Background modeling using corner features: An effective approach , 2009, 2009 IEEE 13th International Multitopic Conference.

[20]  Giuseppe Vizzari,et al.  Integrated Analysis and Synthesis of Pedestrian Dynamics: First Results in a Real World Case Study , 2013, WOA@AI*IA.

[21]  Nicola Conci,et al.  Structured learning for crowd motion segmentation , 2013, 2013 IEEE International Conference on Image Processing.

[22]  Habib Ullah,et al.  Authentication and Secure Communication in GSM, GPRS, and UMTS Using Asymmetric Cryptography , 2010 .

[23]  Farid Melgani,et al.  Ensemble of Deep Models for Event Recognition , 2018, ACM Trans. Multim. Comput. Commun. Appl..

[24]  Ayaz Ahmad,et al.  Density independent hydrodynamics model for crowd coherency detection , 2017, Neurocomputing.

[25]  Ihtesham Ul Islam,et al.  Illumination normalization using independent component analysis and filtering , 2017 .

[26]  Stefania Bandini,et al.  Estimating Speeds of Pedestrians in Real-World Using Computer Vision , 2014, ACRI.

[27]  Habib Ullah,et al.  Energy-Efficient Mutual Authentication Protocol for Handhled Devices Based on Public Key Cryptography , 2013 .

[28]  Stefania Bandini,et al.  A Computer Vision Tool Set for Innovative Elder Pedestrians Aware Crowd Management Support Systems , 2016, AI*AAL@AI*IA.

[29]  S Khan.  Automatic Detection and Computer VisionAnalysis of Flow Dynamics and Social Groups in Pedestrian Crowds , 2016 .

[30]  Francesco G. B. De Natale,et al.  Crowd behavior identification , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[31]  Stefania Bandini,et al.  Simulation and Evaluation of Spiral Movement of Pedestrians: Towards the Tawaf Simulator , 2016, J. Cell. Autom..

[32]  Sohaib Khan,et al.  Towards a Crowd Analytic Framework For Crowd Management in Majid-al-Haram , 2017, ArXiv.

[33]  Nicola Conci,et al.  Gaussian mixtures for anomaly detection in crowded scenes , 2013, Electronic Imaging.

[34]  Francesco G. B. De Natale,et al.  A saliency-based approach to event recognition , 2018, Signal Process. Image Commun..