Abstract
The general public spends a significant amount of time in front of digital signage seeking information from many venues such as exhibition halls and shopping centers. This is why advertisement purchasers believe that the number of passing viewers provides crucial information for their marketing strategies. In this paper, a real-time person counting/memorizing system is designed capable of distinguishing the gender of potential customers. An adaptive boosting (Adaboost) machine learning algorithm is used to detect human faces and utilize specific filtering criteria to eliminate useless data. For each detected person, face and torso information are recorded in a database for identification. The least recently used identification record will be deleted if the database is full. Gender classification is performed by support vector machine using hair ratios extracted from gender characterizing regions. Based on a variety of experiments, the accuracy of the proposed algorithm is higher than 90 % for person-counting and higher than 94 % for gender classification. Moreover, the execution speed on personal computers may reach 15–20 fps.
Similar content being viewed by others
References
Ahn JH, Choi CM, Kwak SY, Kim KC, Byun HR (2009) Human tracking and silhouette extraction for human–robot interaction systems. Pattern Anal Applic 12(2):167–177
Alex JS, Bernhard SL (2004) A tutorial on support vector regression. Stat Comput 14:199–222
Borgefors G (1986) Distance transformations in digital images. Comput Vis Graph Image Process 34:344–371
Boser BE, Guyon IM, Vapnik VN (2002) Support vector machines are universally consistent. Journal of Complexity, Jena, pp 768–791
Chen DY, Su CW, Zeng YC, Sun SW, Lai WR, Liao HYM (2008) An online boosted people counting system for electronic advertising machines. Academia Sinica, Taiwan, Tech. Rep. No. TR-IIS-08-009, September 4
Collins RT, Lipton AJ, Kanade T, Fujiyoshi H, Duggins D, Tsin Y, Tolliver D, Enomoto N, Hasegawa O, Burt P, Wixson L (2000) A system for video surveillance and monitoring, Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep. CMU-RI-TR-00-12
Cutler R, Davis LS (2000) Robust real-time periodic motion detection, analysis, and applications. IEEE Trans Pattern Anal Mach Intell 22:781–796
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEE Comput Soc Conf Comput Vis Pattern Recogn 1:886–893
Duda RO, Hart PE, Stork DG (2000) Fisher linear discriminant. In: Pattern classification, 2nd edn. Wiley, New York, pp 117–121
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans PAMI 32(9):1627–1645
Gonzalez RC, Woods RE (2008) Use of principal components for description. In: Digital Image Processing, 3rd edn. Prentice Hall, Taiwan, pp 842–852
Haering N, Venetianer P, Lipton A (2008) The evolution of video surveillance: an overview. Mach Vis Appl 19:279–290
Haritaoglu I, Harwood D, Davis LS (2000) W4: real-time surveillance of people and their activities. IEEE Trans Pattern Anal Mach Intell 22(8):809–830
Hsieh CC, Huang YP, Chen YY, Fuh CS, Ho WJ (2008) Video super-resolution by integrated SAD and NCC matching criterion for multiple moving objects. In: Proc. of the 10th IASTED International Conference on Computer Graphics and Imaging, Innsbruck, Austria
Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behavior. IEEE Trans Syst Man Cybern C Appl Rev 34:334–352
Kai B, Uwe DH (2001) Template matching using fast normalized cross correlation. Proc SPIE Int Soc Opt Eng 4387:95–102
Khan SA, Nazir M, Akram S, Riaz N (2011) Gender classification using image processing techniques: A survey. In: Proc. IEEE 14th International Multitopic Conference (INMIC), Dec., pp. 25–30, doi: 10.1109/INMIC.2011.6151483
Kim H, Kim D, Ghahramani Z, Bang S (2006) Appearance-based gender classification with Gaussian processes. Pattern Recogn Lett 27(6):618–626
Lian XC, Lu BL (2009) Gender classification by combining facial and hair information. Adv Neuro Inf Process 5507:647–654
Lienhart R, Maydt J (2002) An extended set of Haar-like features for rapid object detection. Proc IEEE Int Conf Image Process 1:900–903
Lipton AJ (1999) Local application of optic flow to analyze rigid versus nonrigid motion. In: Proc. Int. Conf. Computer Vision Workshop Frame-Rate Vision, Corfu, Greece
Moghaddam B, Yang MH (2000) Gender classification with support vector machines. In: Proc. Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 306–311, doi: 10.1109/AFGR.2000.840651
Rodriguez M, Laptev I, Sivic J, Audibert JY (2011) Density-aware person detection and tracking in crowds. In: Proc. of the International Conference on Computer Vision
Sivic J, Everingham M, Zisserman A (2005) Person spotting: video shot retrieval for face sets. In: Proceedings of the ACM International Conference on Image and Video Retrieval
Sivic J, Everingham M, Zisserman A (2009) “Who are you?”: Learning person specific classifiers from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Vezhnevets V, Sazonov V, Andreeva A (2003) A survey on pixel-based skin color detection techniques. In: Proc. Graphicon, September, pp 85–92
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: Proc. of the IEEE Computer Vision and Pattern Recognition, vol.1, 2001, pp. 511–518
Viola P, Jones MJ, Snow D (2003) Detecting pedestrians using patterns of motion and appearance. In: IEEE International Conference on Computer Vision, pp. 734–741
Wang RR, Huang T (2004) A framework of joint object tracking and event detection. Pattern Anal Applic 7(4):343–355
Wong YS, Tam CW, Lee SM, Chan CP, Fu H (2012) Video-base people counting and gender recognition. Adv Swarm Intell Lect Note Comput Sci 7332:228–235
Wren CR, Azarbayejani A, Darrel T, Pentland AP (1997) Pfinder: real time tracking of the human body. IEEE Trans Pattern Anal Mach Intell 19:780–785
Xia B, Sun H, Lu BL (2008) Multi-view gender classification based on local Gabor binary mapping pattern and support vector machines. In: Proc. of International Joint Conference on Neural Networks, HongKong, China, pp. 3388–3395
Acknowledgments
This work was supported in part by the National Science Foundation of the Republic of China under grant NSC 97-2622-E-036-003-CC3.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hsieh, CC., Karkoub, M., Lai, WR. et al. Visual people counting using gender features and LRU updating scheme. Multimed Tools Appl 74, 1741–1759 (2015). https://doi.org/10.1007/s11042-013-1715-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1715-2