New approach to traffic density estimation based on indoor and outdoor scenes from CCTV. (English) Zbl 1334.90026

Summary: In this paper we present an algorithm for precise estimation of moving objects density (typically people and vehicles) in indoor and outdoor scenes. Automatic generation of the so-called density maps is based on video sequences acquired by surveillance systems. Our approach offers two types of solutions. The first one increments the accumulation table when a moving object is detected in a location of interest, delivering a density map of the presence of moving objects. The second algorithm increments the accumulation table only in cases of detecting a new moving object, resulting in a density map of the count of moving objects. The proposed algorithms were tested with the use of PETS 2009 database and with our own database of long-term video recordings. Finally, results of the density maps visualization and determination of the “busy hours” are presented.


90B20 Traffic problems in operations research
91D10 Models of societies, social and urban evolution
Full Text: DOI


[1] Bosch IVA 5.60 datasheet, , available at 2014-11-27;
[2] Computer Vision Systems Toolbox for MatLab: , available at 2014-05-30;
[3] Computer Vision System Toolbox User’s Guide, MathWorks, 2015 vision. KalmanFilter class documentation (MatLab): , available at 2015-03-20;
[4] Computer Vision System Toolbox User’s Guide, MathWorks, 2015 configureKalmanFilter function documentation (MatLab): , available at 2015-03-20;
[5] A. Czyżewski, P. Dalka, Moving Objects Detection and Tracking for the Purpose of Multimodal Surveillance System in Urban Areas, [in:] New Directions in Intelligent Interactive Multimedia Studies in Computational Intelligence, vol. 142, pp. 75-84, 2008. DOI: 10.1007/978-3-540-68127-4_8;
[6] V. Einselein, H. Fradi, I. Keller, T. Sikora, J. Dugelay, “Enhancing Human Detection using Crowd Density Measures and an adaptive Correction Filter”, IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 19-24, 2013.;
[7] Heatmap tool from Cognimatics datasheet, , available at 2014-11-27;
[8] K. Kopaczewski, M. Szczodak, A. Czyżewski, H. Krawczyk, “A method for counting people attending large public events”, Multimedia Tools and Applications, 2013 (online). DOI: 10.1007/s11042-013-1628-0;
[9] C. Lijun, H. Kaiqi, “Video-based crowd density estimation and prediction system for wide-area surveillance”, China Communications, vol.10, no.5, pp.79-88, 2013;
[10] S. F. Lin, J. Y. Chen, H. X. Chao, “Estimation of Number of People in Crowded Scenes Using Perspective Transformation”, IEEE Transactions on Systems, Man, Cybernetics - Part A: Systems and Humans, vol. 31, no. 6, pp. 645-654, 2001.;
[11] A. Marana, S. Velastin, L. Costa, R. Lotufo, “Estimation of crowd density using image processing”, Image Processing for Security Applications, Digest No.: 1997/074, pp 11/1-11/8, 1997.;
[12] T. Marciniak, A. Chmielewska, A. Dabrowski, A. Malina, “People counting vision system based on ARM processor programmed using Simulink environment”, Electronics - constructions, technologies, applications, pp. 55-59, 2014.;
[13] T. Marciniak, A. Dabrowski, A. Chmielewska, M. Nowakowski, “Real-Time Bi-Directional People Counting Using Video Blob Analysis” IEEE New Trends in Audio and Video / Signal Processing Algorithms, Architectures, Arrangements and Applications, pp. 161-166, 2012.;
[14] MxAnalytix tool for map creation and people counting: , available at 2014-11-27.;
[15] The NV-GS500 camera from Panasonic specifications: , available at 2014-11-27;
[16] M. Parzych, A. Chmielewska, T. Marciniak, A. Dąbrowski, “New Approach to People Density Estimation based on Video Surveillance”, International SPA Conference, pp. 94-99, 2014.;
[17] M. Parzych, A. Chmielewska, T. Marciniak, A. Dąbrowski, A. Chrostowska, M. Klincewicz, “Automatic people density maps generation with the use of movement detection analysis”, International Conference on Human-System Interaction, pp.26-31, 2013.;
[18] M. Patzold, R. H. Evangelio, T. Sikora, “Counting people in crowded enviroments by fusion of shape and motion information”, IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 157-164, 2010.;
[19] PETS 2009 database: , available at 2014-05-30;
[20] H. Rahmalan, M. Nixon, J. Carter, “On Crowd Density Estimation for Surveillance”, The Institution of Engineering and Technology Conference on Crime and Security, pp.540-545, 2006.;
[21] M. Rodriguez, I. Laptev, J. Sivic, J. Audibert, “Density-aware person detection and tracking in crowds”, IEEE International Conference on Computer Vision, pp. 2423-2430, 2001.;
[22] H. Sharif, N. Ihaddedene, C. Djeraba, “Crowd Behavior Monitoring on the Escalation Exits:, International Conference on Computer and Information Technology, pp. 194-200, 2008.;
[23] Software for tracking shoppers: , available at 2014-11-27;
[24] C. Stahlschmidt, A. Gavriilidis, A. Kummert, “Density Measurements from a Top-View Position using a Time-of-Flight Camera”, International Workshop on Multidimensional Systems, pp. 193-198, 2013.;
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.