An Automated Image-Based Approach for Tracking Pedestrian Movements from Top-View Video

In order to gain better and more understanding of pedestrian safety video, better tracking of pedestrian movements is necessary. However, existing works on video tracking of pedestrian movements focus in some specific places or situations, extracted limited data from the video and in some cases, a lot of human interventions are required in handling the data extraction. This paper presents an automated image-based approach for tracking pedestrian movements that takes advantage of the top-view video. The proposed approach consists of several steps namely detection, tracking, image calibration and extracting characteristics of a pedestrian from a video. The methods used in these steps are adapted or enhanced from some of the existing work in this area. These steps also allow automated video monitoring and require less human efforts. Besides, it is also used to estimate the speed of a pedestrian. The results of the experiment for the proposed approach using five videos with different scenario are presented. The pedestrian movement was plotted accurately and the numbers of pedestrians detected in the video were recorded correctly whereas the speed of the pedestrians from the framework was very close to the actual speed. The proposed approach can be used to monitor pedestrians in a sparse environment such as at the entrance of a hall or building or along a corridor.

[1]  M. Drahansky,et al.  Real-time Terrain Deformations , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[2]  Shi Zhong-ke,et al.  The Study of the Detection and Tracking of Moving Pedestrian Using Monocular-Vision , 2006, International Conference on Computational Science.

[3]  A. Seyfried,et al.  Methods for measuring pedestrian density, flow, speed and direction with minimal scatter , 2009, 0911.2165.

[4]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[5]  A. Enis Çetin,et al.  Silhouette-Based Method for Object Classification and Human Action Recognition in Video , 2006, ECCV Workshop on HCI.

[6]  Antonio Fernández-Caballero,et al.  A Proposal for Local and Global Human Activities Identification , 2010, AMDO.

[7]  Matthew N. Dailey,et al.  Multiple human tracking in high-density crowds , 2012, Image Vis. Comput..

[8]  L. Li,et al.  On pixel count based crowd density estimation for visual surveillance , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[9]  Mario Vento,et al.  A Method for Counting Moving People in Video Surveillance Videos , 2010, EURASIP J. Adv. Signal Process..

[10]  Z. M. Hefed.  Object tracking , 1999 .

[11]  Alan Hanjalic,et al.  Towards a Robust Solution to People Counting , 2006, 2006 International Conference on Image Processing.

[12]  Tim J. Ellis,et al.  Path detection in video surveillance , 2002, Image Vis. Comput..

[13]  Hao Yue,et al.  Study on Moving Pedestrian Tracking Based on Video Sequences , 2007 .

[14]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[15]  Song Zheng,et al.  An Improved Moving Object Detection Algorithm Based on Frame Difference and Edge Detection , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[16]  Thomas Sikora,et al.  Comparison of static background segmentation methods , 2005, Visual Communications and Image Processing.

[17]  Gian Luca Foresti,et al.  Trajectory clustering and its applications for video surveillance , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[18]  Chandrika Kamath,et al.  Robust techniques for background subtraction in urban traffic video , 2004, IS&T/SPIE Electronic Imaging.

[19]  David C. Hogg,et al.  Learning the distribution of object trajectories for event recognition , 1996, Image Vis. Comput..

[20]  Siuming Lo,et al.  Experimental study on microscopic moving characteristics of pedestrians in built corridor based on digital image processing , 2010 .

[21]  P. Fua,et al.  Evaluation of probabilistic occupancy map people detection for surveillance systems , 2009 .

[22]  Tieniu Tan,et al.  Trajectory Series Analysis based Event Rule Induction for Visual Surveillance , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Halimatul Saadiah Md. Yatim,et al.  A Practical and Automated Image-based Framework for TrackingPedestrian Movements from a Video , 2013 .

[24]  Sangkeun Lee,et al.  Correction of radial distortion using a planar checkerboard pattern and its image , 2009, 2009 Digest of Technical Papers International Conference on Consumer Electronics.

[25]  Hai Tao,et al.  A Viewpoint Invariant Approach for Crowd Counting , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[26]  Jiting Li,et al.  Vision-Based Dynamic Tracking of Motion Trajectories of Human Fingertips , 2007 .

[27]  Tobias Bjerregaard,et al.  A survey of research and practices of Network-on-chip , 2006, CSUR.

[28]  Luis Jiménez,et al.  A supervised learning approach to automate the acquisition of knowledge in surveillance systems , 2009, Signal Process..

[29]  Vittorio Murino,et al.  A Comparison of Multi Hypothesis Kalman Filter and Particle Filter for Multi-target Tracking , 2009, CVPR 2009.

[30]  Stefania Bandini,et al.  A qualitative evaluation of technologies and techniques for data collection on pedestrians and crowded situations , 2007, SCSC.

[31]  Fazilah Haron,et al.  CDES: A pixel-based crowd density estimation system for Masjid al-Haram , 2011, Safety Science.

[32]  Jun Zhang,et al.  Extraction and quantitative analysis of microscopic evacuation characteristics based on digital image processing , 2009 .

[33]  Andreas Schadschneider,et al.  Automatic Extraction of Pedestrian Trajectories from Video Recordings , 2010 .

[34]  Jianhu Zheng,et al.  Intelligent Pedestrian Flow Monitoring Systems in Shopping Areas , 2010, 2010 2nd International Symposium on Information Engineering and Electronic Commerce.