IJE TRANSACTIONS C: Aspects Vol. 28, No. 12 (December 2015) 1711-1719   

PDF URL: http://www.ije.ir/Vol28/No12/C/3-2145.pdf  
downloaded Downloaded: 117   viewed Viewed: 1642

A. Gh. Sorkhi, H. Hassanpour and P. L. Mazzeo
( Received: May 23, 2015 – Accepted: December 24, 2015 )

Abstract    Non-overlapping field-of-view (FOV) cameras are used in surveillance system to cover a wider area. Tracking in such systems is generally performed in two distinct steps. In the first step, people are identified and tracked in the FOV of a single camera. In the second step, re-identification of the people is carried out to track them in the whole area under surveillance. Various conventional features such as clothes and appearance of person have been used to identify peoples in the cameras. However, similarity between appearance and clothes of people causes unreliable results. Thus, much reliable features are still required to increase the ability of tracking system. The aim of this paper is to propose a novel algorithm to identify people in a network of cameras with disjoints views. In our proposed methodology, according to relative size of various parts, human body are divided into three portions of head, middle section and lower section. Considering histograms of these portions, matching process was done aiming to distinguish persons in FOV of cameras. The other main challenge in such multi-camera system is to deal with illumination changes and varying appearance of people at different cameras view. The cumulative brightness transform function (CBTF) was employed to alleviate the difficulty of illumination changes. Experiments were conducted in RGB, YCbCr and HSV color spaces and it was found that YCbCr color space gives a better performance result compared to other color spaces used in this work.


Keywords    People tracking, Camera networks, non-overlapping FOV, various segments of human body, Cumulative brightness transform function


چکیده    در سال­های اخیر، از شبکه­ای از دوربین­ها با دید مجزا، به منظور نظارت بر ناحیه وسیع استفاده شده است. ردیابی در این نوع از سیستم­ها، معمولا بر پایه دو مرحله اساسی می­باشد. در مرحله اول، افراد، در زاویه دید یک دوربین، شناسایی و ردیابی می­شوند. در مرحله دوم، دوباره شناسایی افراد به منظور ردیابی آنها در تمام ناحیه تحت نظارت انجام می­گیرد. در این نوع از سیستم­ها، ویژگی­های زیادی به مانند لباس و ظاهر افراد به منظور شناسایی استفاده شده است. ولی شباهت بین لباس و ظاهر افراد نتایج قابل قبولی را از خود نشان نداده است. به همین دلیل استفاده از ویژگی­های قابل اطمینان به منظور بالا بردن توانایی سیستم­های ردیابی همچنان مورد نیاز می­باشد. هدف از مقاله حاضر، ارائه الگوریتمی جدید به منظور شناسایی افراد در شبکه­ای از دوربین­ها با دید مجزا می­باشد. در روش پیشنهادی، بر اساس اندازه نسبی قسمت­های مختلف، بدن انسان به سه قسمت مجزا، سر، میان­تنه و پایین تنه تقسیم شده است. عمل شناسایی افراد با توجه به هیستوگرام قسمت­های مختلف بدن انسان در زاویه دید دوربین­ها انجام می­شود. یکی دیگر از چالش­های موجود در این نوع از سیستم­ها تغییر روشنایی و تغییر کردن ظاهر افراد در زاویه دید دوربین­های متفاوت می­باشد. تابع انتقال روشنایی تجمعی به منظور کاهش مشکلات تغییرات شدت روشنایی در این نوع از سیستم­ها استفاده شده است. آزمایشات در فضاهای رنگی RGB، YCbCr و HSV به منظور ردیابی و شناسایی مجدد افراد انجام شده است که فضای رنگی YCbCr عملکرد بهتر در مقایسه با دیگر فضا­های رنگی در این نوع از سیستم­ها از خود نشان داده است.



1.        Madden, C.S.T., "Tracking people across disjoint camera views", (2009).

2.        Ilyas, A., "Object tracking and re-identification in multi-camera environments",  (2011).

3.        Yu, Q. and Medioni, G., "Multiple-target tracking by spatiotemporal monte carlo markov chain data association", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 31, No. 12, (2009), 2196-2210.

4.        Wu, B. and Nevatia, R., "Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors", International Journal of Computer Vision,  Vol. 75, No. 2, (2007), 247-266.

5.        Pham, T.V., Worring, M. and Smeulders, A.W., "A multi-camera visual surveillance system for tracking of reoccurrences of people", in Distributed Smart Cameras,. ICDSC'07. First ACM/IEEE International Conference on, IEEE, (2007), 164-169.

6.        Prosser, B., Gong, S. and Xiang, T., "Multi-camera matching using bi-directional cumulative brightness transfer functions", in BMVC. Vol. 8, (2008), 164.161-164.110.

7.        D'Orazio, T., Mazzeo, P. and Spagnolo, P., "Color brightness transfer function evaluation for non overlapping multi camera tracking", in Distributed Smart Cameras, 2009. ICDSC 2009. Third ACM/IEEE International Conference on, IEEE., (2009), 1-6.

8.        Porikli, F. and Divakaran, A., "Multi-camera calibration, object tracking and query generation", in Multimedia and Expo, 2003. ICME'03. Proceedings. International Conference on, IEEE. Vol. 1, (2003), 653-656.

9.        Kettnaker, V. and Zabih, R., "Bayesian multi-camera surveillance", in Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., IEEE. Vol. 2, , (1999).

10.     Moeslund, T.B., Hilton, A. and Krüger, V., "A survey of advances in vision-based human motion capture and analysis", Computer Vision and Image Understanding,  Vol. 104, No. 2, (2006), 90-126.

11.     Yilmaz, A., Javed, O. and Shah, M., "Object tracking: A survey", Acm Computing Surveys (CSUR),  Vol. 38, No. 4, (2006), 1-45.

12.     Enzweiler, M. and Gavrila, D.M., "Monocular pedestrian detection: Survey and experiments", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 31, No. 12, (2009), 2179-2195.

13.     Khakpour, F. and Ardeshir, G., "Using a novel concept of potential pixel energy for object tracking", International Journal of Engineering-Transactions A: Basics,  Vol. 27, No. 7, (2013), 1023-1032.

14.     Geronimo, D., Lopez, A.M., Sappa, A.D. and Graf, T., "Survey of pedestrian detection for advanced driver assistance systems", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 32, No. 7, (2010), 1239-1258.

15.     Javed, O., Shafique, K., Rasheed, Z. and Shah, M., "Modeling inter-camera space–time and appearance relationships for tracking across non-overlapping views", Computer Vision and Image Understanding,  Vol. 109, No. 2, (2008), 146-162.

16.     Makris, D., Ellis, T. and Black, J., "Bridging the gaps between cameras", in Computer Vision and Pattern Recognition,. CVPR. Proceedings of the Computer Society Conference on, IEEE. Vol. 2, , (2004), 205-210.

17.     Zhu, L., Hwang, J.-N. and Cheng, H.-Y., "Tracking of multiple objects across multiple cameras with overlapping and non-overlapping views", in Circuits and Systems,. ISCAS. IEEE International Symposium on, (2009), 1056-1060.

18.     Rahimi, A., Dunagan, B. and Darrell, T., "Simultaneous calibration and tracking with a network of non-overlapping sensors", in Computer Vision and Pattern Recognition,. CVPR. Proceedings of the IEEE Computer Society Conference on, IEEE. Vol. 1, (2004), 187 -194.

19.     Javed, O., Shafique, K. and Shah, M., "Appearance modeling for tracking in multiple non-overlapping cameras", in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, IEEE. Vol. 2, (2005), 26-33.

20.     Mahdavi, M., Shahrouzi, S. and Hasanzadeh, R., "A novel method for tracking moving objects using block-based similarity", International Journal of Engineering-Transactions B: Applications,  Vol. 22, No. 1, (2008), 35-42.

21.     Xie, Y., Yu, H., Gong, X., Dong, Z. and Gao, Y., "Learning visual-spatial saliency for multiple-shot person re-identification", Signal Processing Letters, IEEE,  Vol. 22, No. 11, (2015), 1854-1858.

22.     Liong, V.E., Ge, Y. and Lu, J., "Discriminative regularized metric learning for person re-identification", in Biometrics (ICB), International Conference on, IEEE, (2015), 52-57.

23.     Liu, C., Gong, S. and Loy, C.C., "On-the-fly feature importance mining for person re-identification", Pattern Recognition,  Vol. 47, No. 4, (2014), 1602-1615.

24.     Xiong, F., Gou, M., Camps, O. and Sznaier, M., Person re-identification using kernel-based metric learning methods, in Computer vision–ECCV , (2014), Springer, 1-16.

25.     Mazzeo, P.L., Giove, L., Moramarco, G.M., Spagnolo, P. and Leo, M., "Hsv and rgb color histograms comparing for objects tracking among non overlapping FOVs, using CBTF", in Advanced Video and Signal-Based Surveillance (AVSS), 8th IEEE International Conference on, IEEE, (2011), 498-503.

26.     Remondino, F. and Roditakis, A., 3d reconstruction of human skeleton from single images or monocular video sequences, in Pattern recognition, (2003), Springer, 100-107.

27.     Krumm, J., Harris, S., Meyers, B., Brumitt, B., Hale, M. and Shafer, S., "Multi-camera multi-person tracking for easyliving", in Visual Surveillance,. Proceedings. Third IEEE International Workshop on, IEEE., (2000), 3-10.

28.     Comaniciu, D., Ramesh, V. and Meer, P., "Kernel-based object tracking", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 25, No. 5, (2003), 564-577.

van Rijsbergen, C.J., "Information retrieval", London, Butterw,  (1979).

Download PDF 

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir