Abstract
In this paper, we propose a novel method for moving foreground object extraction in sequences taken by a wearable camera, with strong motion. We use camera motion compensated frame differencing, enhanced with a novel kernel-based estimation of the probability density function of background pixels. The probability density functions are used for filtering false foreground pixels on the motion compensated difference frame. The estimation is based on a limited number of measurements; therefore, we introduce a special, spatio-temporal sample point selection and an adaptive thresholding method to deal with this challenge. Foreground objects are built with the DBSCAN algorithm from detected foreground pixels.
Similar content being viewed by others
References
Mann S (1997) Wearable computing: a first step toward personal imaging. Computer 30(2):25–32
Hodges S, Williams L, Berry E, Izadi S, Srinivasan J, Butler A, Smyth G, Kapur N, Wood K (2006) SenseCam: a retrospective memory aid, International Conference on Ubiquitous Computing. LNCS 4206:177–193
Personal and ubiquitous computing, special issue on Memory and Sharing of Experiences. (2007) Springer 11(4), pp 213–328
Perez K, Helmer C, Amieva H, Orgogozo J-M, Rouch I, Dartigues J-F, Barberger-Gateau P (2008) Natural history of decline in instrumental activities of daily living performance over the 10 years preceding the clinical diagnosis of dementia: a prospective population-based study. J Am Geriatr Soc 56(1):37–44
Megret R, Szolgay D, Benois-Pineau J, Joly Ph, Pinquier J, Dartigues J-F, Helmer C (2008) Wearable video monitoring of people with age dementia: video indexing at the service of healthcare. In: Proceedings of the International Workshop on Content-Based Multimedia Indexing, London, pp 101–108
Stauffer C, Grimson E (2000) Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell 22(8):747–757
Zivkovic Z (2004) Improved adaptive Gaussian mixture model for background subtraction. Proc Intern Conf Pattern Recognit 2:28–31
Zivkovic Z, van der Heijden F (2006) Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognit Lett 27(7):773–780
Carminati L, Benois-Pineau J (2005) Gaussian mixture classification for moving object detection in video surveillance environment. Proc IEEE Int Conf Image Process 3:113–116
Balcells-Capellades M, DeMenthon D, Doermann D (2004) An appearance-based approach for consistent labeling of humans and objects in video. Pattern Anal Appl 7(4):373–385
Kim K, Chalidabhongse TH, Harwood D, Davis L (2004) Background modeling and subtraction by codebook construction. Proceedings of IEEE International Conference of Image Processing, vol 5, pp 3061–3064
Mittal A, Paragios N (2004) Motion-based background subtraction using adaptive kernel density estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 302–309
Tiand T, Tomasi C, Heeger D (1996) Comparision of approaches to ego-motion computation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 315–320
Foresti GL, Micheloni C (2003) A robust feature tracker for active surveillance of outdoor scenes. Electron Lett Comput Vis Image Anal 1(1):21–34
Jung B, Sukhatme GS (2004) Detecting moving objects using a single camera on a mobile robot in an outdoor environment. In: the Conference on Intelligent Autonomous Systems, Amsterdam, pp 980–987
Jung-Ho A, Cheolmin C, Sooyeong K, Kilcheon K, Hyeran B (2008) Human tracking and silhouette extraction for human–robot interaction systems. Pattern Anal Appl (published online)
Veit T, Cao F, Bouthemy (2006) An a contrario decision framework for region-based motion detection. Intern J Comput Vis 68(2):163–178
Yuan C, Medioni G, Kang J, Cohen I (2007) Detecting motion regions in the presence of a strong parallax from a moving camera by multiview geometric constraints. IEEE Trans Pattern Anal Mach Intell 29(9):1627–1641
Sheikh Y, Shah M (2005) Bayesian modeling of dynamic scenes for object detection. IEEE Trans Pattern Anal Mach Intell 27(11):1778–1792
Bierling M (1988) Displacement estimation by hierarchical block matching. Proc SPIE Vis Commun Image Process 1001:942–951
Accame M, de Natale FGB, Giusto DD (1998) High performance hierarchical block-based motion estimation for real-time video coding. Real-Time Imaging 4(1):67–79
Durik M, Benois-Pineau J (2001) Robust motion characterisation for video indexing based on MPEG2 opticalflow. In: Proceedings of the International Workshop on Content-Based Multimedia Indexing, pp 57–64
Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33:1065–1076
Archambeau C, Valle M, Assenza A, Verleysen M (2006) Assessment of probability density estimation methods: Parzen window and finite Gaussian mixtures. In: Proceedings of IEEE International Symposium on Circuits and Systems, pp 1–4
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. John Wiley & Sons, Inc., NY
Bugeau A (2007) Détection et suivi d’objets en mouvement dans des scènes complexes, application à la surveillance des conducteurs, Thèse de l’université de Rennes 1, Mention Traitement du Signal et des Télécommunications
Epanechnikov (1969) Nonparametric estimates of a multivariate probability density. Theor Probab Appl 14:153–158
M. Ester, H.-P. Kriegel, J. Sander, X. Xu (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of Second International Conference on Knowledge Discovery and Data Mining. Portland, OR, pp 226–231
Sander J, Ester M, Kriegel H-P, Xu X (1998) Density-based clustering in spatial databases: the algorithm GDBSCAN and its applications. Data Min Knowl Disc 2:169–194
van Rijsbergen CJ (1979) Information retrieval, 2nd edn. Butterworth-Heinemann, London
Zivkovic Z, van der Heijden F (2004) Recursive unsupervised learning of finite mixture models. IEEE Trans Pattern Anal Mach Intell 26(5):651–656
Gupta G, Chakrabarti C (1995) Architectures for hierarchical and other block matching algorithm. IEEE Trans Circuits Sys Video Technol 5:477–489
Mazaré S, Pacalet R, Dugelay J-L (2006) Using GPU for fast block-matching. In: 14th European Signal Processing Conference, Florence, Italy
Owens JD, Luebke D, Govindaraju N, Harris M, Krüger J, Lefohn AE, Purcell T (2007) A survey of general-purpose computation on graphics hardware. Comput Graph Forum 26(1):80–113
Acknowledgments
This work has been supported by French national grant “Eiffel doctorate” and research project PEPS S2TI CNRS “Wearable video monitoring: application to surveillance of persons with age dementia”, 2007–2008 and BQR grant of University Bordeaux 1. We also thank Pr. Tamás Szirányi, PPCU, Budapest for fruitful discussion when preparing this paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Szolgay, D., Benois-Pineau, J., Megret, R. et al. Detection of moving foreground objects in videos with strong camera motion. Pattern Anal Applic 14, 311–328 (2011). https://doi.org/10.1007/s10044-011-0221-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-011-0221-2