Human Detection for a Video Surveillance Applied in the 'SmartMonitor' System

Human detection is one of the key and crucial tasks in video surveillance systems and is important for the purpose of object tracking, fall detection, human gait analysis or abnormal event detection. This paper concerns the application of two classifiers for human detection in the ‘SmartMonitor’ system — an intelligent security system based on image analysis. The classifiers are based on the Histogram of Oriented Gradients (HOG) descriptor and simple Haar-like features. The paper provides a brief description of the main system characteristics, discusses the problem of human detection and includes some results of the experiments performed using various parameters of HOG and Haar classifiers that were trained using benchmark databases and tested using appropriate video sequences. The paper aims at investigating the effectiveness and performance of both methods applied separately before incorporating them into the ‘SmartMonitor’ system’s video processing model.

[1]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Pawel Forczmanski,et al.  Surveillance Video Stream Analysis Using Adaptive Background Model and Object Recognition , 2010, ICCVG.

[3]  Andrea Cavallaro,et al.  Video-Based Human Behavior Understanding: A Survey , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Dariu Gavrila,et al.  A new benchmark for stereo-based pedestrian detection , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[5]  Pawel Forczmanski,et al.  “SmartMonitor” — An Intelligent Security System for the Protection of Individuals and Small Properties with the Possibility of Home Automation , 2014, Sensors.

[6]  Van-Dung Hoang,et al.  Fast human detection based on parallelogram haar-like features , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[7]  Yafei Lu,et al.  Crowd Abnormal Behavior Detection Based on Machine Learning , 2013 .

[8]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[9]  Pawel Forczmanski,et al.  Extraction of the Foreground Regions by Means of the Adaptive Background Modelling Based on Various Colour Components for a Visual Surveillance System , 2013, CORES.

[10]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  Daniela Moctezuma,et al.  HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments , 2013, Neurocomputing.

[12]  Keshab K. Parhi,et al.  Semiblind frequency-domain timing synchronization and channel estimation for OFDM systems , 2013, EURASIP J. Adv. Signal Process..

[13]  Pawel Forczmanski,et al.  The Removal of False Detections from Foreground Regions Extracted Using Adaptive Background Modelling for a Visual Surveillance System , 2013, CISIM.

[14]  Grantham Pang,et al.  People Counting and Human Detection in a Challenging Situation , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[15]  A. K. S. Kushwaha,et al.  Automatic multiple human detection and tracking for visual surveillance system , 2012, 2012 International Conference on Informatics, Electronics & Vision (ICIEV).

[16]  P. Karpagavalli,et al.  Estimating the density of the people and counting the number of people in a crowd environment for human safety , 2013, 2013 International Conference on Communication and Signal Processing.

[17]  Dariusz Frejlichowski,et al.  SmartMonitor: recent progress in the development of an innovative visual surveillance system , 2012 .

[18]  Chittaranjan A. Mandal,et al.  Automatic Detection of Human Fall in Video , 2007, PReMI.

[19]  Pei-Yung Hsiao,et al.  Combining Histograms of Oriented Gradients with Global Feature for Human Detection , 2011, MMM.

[20]  Pawel Forczmanski,et al.  SmartMonitor: An Approach to Simple, Intelligent and Affordable Visual Surveillance System , 2012, ICCVG.

[21]  Alejandro F. Frangi,et al.  Haar-like features with optimally weighted rectangles for rapid object detection , 2010, Pattern Recognition.

[22]  Youngjoon Han,et al.  Human Detection using Projected Edge Feature , 2011 .

[23]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).