Abstract
Counting people is a basic operation in applications that include surveillance, marketing, services, and others. Recently, computer vision techniques have emerged as a non-intrusive, cost-effective, and reliable solution to the problem of counting pedestrians. In this article, we introduce a system capable of counting people using a cooperating network of depth cameras placed in zenithal position. In our method, we first detect people in each camera of the array separately. Then, we construct and consolidate tracklets based on their closeness and time stamp. Our experimental results show that the method permits to extend the narrow range of a single sensor to wider scenarios.
References
Chan, A., Vasconcelos, N.: Counting people with low-level features and Bayesian regression. IEEE Trans. Image Process. 21(4), 2160–2177 (2012)
Chen, K., Kamarainen, J.-K.: Learning to count with back-propagated information. In: International Conference on Pattern Recognition, pp. 4672–4677. IEEE (2014)
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743–761 (2012)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)
Ferryman, J., Ellis, A.-L.: Performance evaluation of crowd image analysis using the PETS2009 dataset. Pattern Recognit. Lett. 44, 3–15 (2014)
Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Galc̆ík, F., Gargalík, R.: Real-time depth map based people counting. In: International Conference on Advanced Concepts for Intelligent Vision Systems, vol. 8192, p. 330. Springer (2013)
Gao, K.: An emergency evacuation model based on computer vision smart inducing in hotel stampede environment. In: Applied Mechanics and Materials, vol. 556, pp. 5736–5739. Trans Tech Publ (2014)
Golub, G., Van Loan, C.: Matrix Computations, vol. 3. JHU Press, Baltimore (2012)
Herrera, C., Kannala, J., Heikkilä, J.: Joint depth and color camera calibration with distortion correction. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 2058–2064 (2012)
Kong, D., Gray, D., Tao, H.: A viewpoint invariant approach for crowd counting. In: International Conference on Pattern Recognition, vol. 3, pp. 1187–1190. IEEE (2006)
Kuhn, H.W.: The Hungarian Method for the Assignment Problem. Naval Res. Logist. Q. 2(1–2), 83–97 (1955)
Lee, K., Eidson, J., Weibel, H., Mohl, D.: IEEE 1588-standard for a precision clock synchronization protocol for networked measurement and control systems. In: Conference on IEEE, vol. 1588, p. 2 (2005)
Lemkens, W., Kaur, P., Buys, K., Slaets, P., Tuytelaars, T., De Schutter, J.: Multi RGB-D camera setup for generating large 3D point clouds. In: International Conference on Intelligent Robots and Systems, pp. 1092–1099. IEEE (2013)
Macknojia, R., Chávez-Aragón, A., Payeur, P., Laganiere, R.: Calibration of a network of kinect sensors for robotic inspection over a large workspace. In: IEEE Workshop on Robot Vision, pp. 184–190. IEEE (2013)
Maddalena, L., Petrosino, A., Russo, F.: People counting by learning their appearance in a multi-view camera environment. Pattern Recognit. Lett. 36, 125–134 (2014)
Maimone, A., Fuchs, H.: Reducing interference between multiple structured light depth sensors using motion. In: IEEE Virtual Reality, pp. 51–54. IEEE (2012)
Martin Martin, R., Lorbach, M., Brock, O.: Deterioration of depth measurements due to interference of multiple RGB-D sensors. In: International Conference on Intelligent Robots and Systems, pp. 4205–4212. IEEE (2014)
Mikhelson, I.V., Lee, P.G., Sahakian, A.V., Wu, Y., Katsaggelos, A.K.: Automatic, fast, online calibration between depth and color cameras. J. Vis. Commun. Image Rep. 25(1), 218–226 (2014)
Najman, L., Schmitt, M.: Geodesic saliency of watershed contours and hierarchical segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(12), 1163–1173 (1996)
Nam, W., Dollár, P., Han, J.H.: Local decorrelation for improved pedestrian detection. In: Advances in Neural Information Processing Systems, pp. 424–432 (2014)
Porzycki, J., Lubaś, R., Mycek, M., Wkas, J.: Dynamic data–driven simulation of pedestrian movement with automatic validation. In: Traffic and Granular Flow, pp. 129–136. Springer (2015)
Rauter, M.: Reliable human detection and tracking in top-view depth images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 529–534 (2013)
Ryan, D., Denman, S., Fookes, C., Sridharan, S.: Crowd counting using multiple local features. In: Digital Image Computing: Techniques and Applications, pp. 81–88. IEEE (2009)
Ryan, D., Denman, S., Sridharan, S., Fookes, C.: An evaluation of crowd counting methods, features and regression models. Comput. Vis. Image Underst. 130, 1–17 (2015)
Spinello, L., Arras, K.: People detection in RGB-D data. In: IEEE International Conference on Intelligent Robots and Systems, pp. 3838–3843 (2011)
Wang, Y., Lian, H., Chen, P., Lu, Z.: Counting people with support vector regression. In: International Conference on Natural Computation, pp. 139–143. IEEE (2014)
Yan-Yan, C., Ning, C., Yu-Yang, Z., Ke-Han, W., Wei-Wei, Z.:Pedestrian detection and tracking for counting applications in metrostation. Discrete Dyn. Nat. Soc. 2014, 1–11 (2014)
Yu, S., Wu, S., Wang, L.: SLTP: a fast descriptor for people detection in depth images. In: IEEE International Conference on Advanced Video and Signal-Based Surveillance, pp. 43–47 (2012)
Zhang, C., Zhang, Z.: Calibration between depth and color sensors for commodity depth cameras. In: Computer Vision and Machine Learning with RGB-D Sensors, pp. 47–64. Springer (2014)
Zhang, X., Yan, J., Feng, S., Lei, Z., Yi, D., Li, S.Z.: Water filling: unsupervised people counting via vertical kinect sensor. In: International Conference on Advanced Video and Signal-Based Surveillance, pp. 215–220. IEEE (2012)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Zhu, L., Wong, K.-H.: Human tracking and counting using the kinect range sensor based on adaboost and kalman filter. In: Advances in Visual Computing, pp. 582–591. Springer (2013)
Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: International Conference on Pattern Recognition, vol. 2, pp. 28–31. IEEE (2004)
Acknowledgments
This work was partially supported by the FOMIX GDF-CONACYT under Grant No. 189005, IPN-SIP under Grant No. 20140325. We thank Multilink Traductores for their comments to the document and the Facultad de Ingeniería at UAQ for providing a warm environment for the development of this work. Finally, we warmly thank the reviewers for their comments, which resulted in a much better paper than the original.
Author information
Authors and Affiliations
Corresponding author
Additional information
Joaquin Salas is on sabbatical leave at FI-UAQ.
Rights and permissions
About this article
Cite this article
Vera, P., Monjaraz, S. & Salas, J. Counting pedestrians with a zenithal arrangement of depth cameras. Machine Vision and Applications 27, 303–315 (2016). https://doi.org/10.1007/s00138-015-0739-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-015-0739-1