OPEN ACCESS
In this article we propose a novel approach for the detection and localisation of stationary objects using a pair of Pan-Tilt-Zoom (PTZ) cameras monitoring a wide scene. Our contribution is twofold. First we propose a stationary object detection and segmentation technique. It relies on the re-identification of foreground descriptors followed by a segmentation of these regions into objects, using Markov Random Fields. Our method allows the foreground to be dated and, under some conditions, to segment the different objects composing a single foreground blob. The second contribution concerns the matching of object silhouettes detected in each camera. This correspondence stage is only based on geometric constraints. Finally we tested our system on sequences which highlight its robustness to occlusions, even in the case of non planar scenes whose geometry is unknown.
RÉSUMÉ
Dans cet article, nous proposons une approche originale pour détecter et localiser des objets stationnaires sur une scène étendue en exploitant une paire de caméras PTZ. Tout d’abord, nous présentons une méthode de détection et de segmentation d’objets stationnaires. Celle-ci est basée sur la ré-identification de descripteurs de l’avant-plan et une segmentation de ces régions en objets à l’aide de champs de Markov. Notre méthode permet de dater l’avantplan de la scène, et sous certaines conditions de segmenter différents objets contenus dans une seule composante connexe du premier plan. La seconde contribution concerne la mise en correspondance entre les deux caméras PTZ des silhouettes d’objets détectées dans chaque image. L’appariement, effectué à partir de contraintes purement géométriques, permet d’associer directement des ensembles de silhouettes. Notre système est finalement testé sur des séquences qui montrent sa robustesse aux occultations.
stationary object detection, PTZ camera, stereo-matching
MOTS-CLÉS
détection d’objets stationnaires, caméra PTZ, appariement stéréo
Alahari K., Kohli P., Torr P. H. S. (2008). Reduce, reuse & recycle: Efficiently solving multilabel MRFs. In Proceedings of ieee conference on computer vision and pattern recognition.
Bay H., Ess A., Tuytelaars T., Gool L. V. (2008). Surf: Speeded up robust features. In Cviu.
Bayona A., SanMiguel J., Martinez J. (2009). Comparative evaluation of stationary foreground object detection algorithms based on background subtraction techniques. In Advanced video and signal based surveillance.
Bayona A., SanMiguel J., Martinez J. (2010). Stationary foreground detection using background subtraction and temporal difference in video surveillance. In International conference on image processing.
Beynon M. D., Van Hook D. J., Seibert M., Peacock A., Dudgeon D. (2003). Detecting abandoned packages in a multi-camera video surveillance system. In Conference on advanced video and signal based surveillance.
Bhargava M., Chen C.-C., Ryoo M., Aggarwal J. (2007, sept.). Detection of abandoned objects in crowded environments. In Advanced video and signal based surveillance, 2007. avss 2007. ieee conference on, p. 271 -276.
Boykov Y., Kolmogorov V. (2004). An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell.
Cipolla R., Astrom K., Giblin P. (1995). Motion from the frontier of curved surfaces. In Fifth international conference on computer vision.
Fleuret F., Berclaz J., Lengagne R., Fua P. (2008). Multicamera people tracking with a probabilistic occupancy map. Pattern Analysis and Machine Intelligence, IEEE Transactions on.
Guillot C., Sayd P., Pham Q.-C., Tilmant C., Lavest J.-M. (2012). Détection et localisation d?objets stationnaires par une paire de caméras ptz. In Reconnaissance des formes et intelligence artificielle.
Guillot C., Taron M., Sayd P., Pham Q.-C., Tilmant C., Lavest J.-M. (2010). Background subtraction for ptz cameras performing a guard tour and application to cameras with very low frame rate. In Accv workshop on visual surveillance.
Guler S., Silverstein J., Pushee I. (2007). Stationary objects in multiple object tracking. In Advanced video and signal based surveillance. i-lids dataset for avss 2007. (s. d.). http://www.eecs.qmul.ac.uk/˜ andrea/avss2007_d.html.
Khan S. M., Shah M. (2009). Tracking multiple occluding people by localizing on multiple scene planes. Pattern Analysis and Machine Intelligence, IEEE Transactions on.
Kohli P., Torr P. (2005). Efficiently solving dynamic markov random fields using graph cuts. In Iccv, p. II: 922-929.
Kolmogorov V. (2006, October). Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, p. 1568–1583. http://dx.doi.org/10.1109/TPAMI.2006.200
Liao H.-H., Chang J.-Y., Chen L.-G. (2008). A localized approach to abandoned luggage detection with foreground-mask sampling. In Advanced video and signal based surveillance.
Lv F., Song X., Wu B., Kumar V., Nevatia S. R. (2006). Left luggage detection using bayesian inference. In Pets.
Mathew R., Yu Z., Zhang J. (2005). Detecting new stable objects in surveillance video. In Multimedia signal processing, 2005 ieee 7th workshop on.
Miezianko R., Pokrajac D. (2008). Localization of detected objects in multi-camera network. In Icip.
Porikli F., Ivanov Y., Haga T. (2008, January). Robust abandoned object detection using dual foregrounds. EURASIP J. Adv. Signal Process, vol. 2008. http://dx.doi.org/10.1155/2008/197875
San Miguel J., Martinez J. (2008). Robust unattended and stolen object detection by fusing simple algorithms. In Advanced video and signal based surveillance, 2008. avss ’08. ieee fifth international conference on, p. 18 -25.
Utasi A., Csaba B. (2010). Multi-camera people localization and height estimation using multiple birth and death dynamics. In Accv workshop on visual surveillance.
Valentine B., Apewokin S., Wills L., Wills S., Gentile A. (2007). Midground object detection in real world video scenes. In Conference on advanced video and signal based surveillance.
Venetianer P., Zhang Z., Yin W., Lipton A. (2007, sept.). Stationary target detection using the objectvideo surveillance system. In Advanced video and signal based surveillance, 2007. avss 2007. ieee conference on, p. 242 -247.