Abstract
This paper deals with attention in 3D environments based upon knowledge-driven cues. Using learned 3D scenes as top-down influence, the proposed system is able to mark high saliency to locations occupied by objects that are new, changed, or even missing from their location as compared to the already learned situation. The proposal addresses a system level solution covering learning of 3D objects and scenes using visual, range and odometry sensors, storage of spatial knowledge using multiple-view theory from psychology, and validation of scenes using recognized objects as anchors. The proposed system is designed to handle the complex scenarios of recognition with partially visible objects during revisit to the scene from an arbitrary direction. Simulation results have shown success of the designed methodology under ideal sensor readings from range and odometry sensors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Congnitive Psychology 12, 97–136 (1980)
Posner, M., Snyder, C., Davidson, B.: Attention and the detection of signals. Journal of Experimental Psychology: General 109(2), 160–174 (1980)
Chen, X., Zelinsky, G.: Real-world visual search is dominated by top-down guidance. Vision Research 46(24), 4118–4133 (2006)
Chen, X., Zelinsky, G.J.: Is visual search a top-down or bottom-up process? Journal of Vision 6, 447 (2006)
Blanz, V., Tarr, M., Bülthoff, H., Vetter, T.: What object attributes determine canonical views? PERCEPTION-LONDON 28, 575–600 (1999)
Endres, D., Vintila, F., Bruce, N., Bouecke, J., Kornprobst, P., Neumann, H., Giese, M.: Hooligan detection: the effects of saliency and expert knowledge. Perception 39 ECVP Abstract Supplement 39, 193 (2010)
Olivers, C., Meijer, F., Theeuwes, J.: Feature-based memory-driven attentional capture: Visual working memory content affects visual attention. Journal of Experimental Psychology 32(5), 1243–1265 (2006)
Palmer, S.: Vision science: Photons to phenomenology, vol. 2. MIT Press, Cambridge (1999)
Oman, C.M., Shebilske, W.L., Richards, J.T., Tubré, T.C., Bealli, A.C., Natapoffi, A.: Three dimensional spatial memory and learning in real and virtual environments. Spatial Cognition and Computation 2, 355–372 (2000)
Shelton, A.L., Mcnamara, T.P.: Spatial memory and perspective taking. Memory & Cognition 32, 416–426 (2004)
Aivar, M.P., Hayhoe, M.M., Chizk, C.L., Mruczek, R.E.B.: Spatial memory and saccadic targeting in a natural task. Journal of Vision 5, 177–193 (2005)
Hoshino, E., Taya, F., Mogi, K.: Memory formation of object representation: Natural scenes. In: Wang, R., et al. (eds.) Advances in Cognitive Neurodynamics, pp. 457–462 (2008)
Follet, B., Le Meur, O., Baccino, T.: Modeling visual attention on scenes. Studia Informatica Universalis 8, 150–167 (2010)
Fay, R., Kaufmann, U., Markert, H., Palm, G.: Adaptive visual attention based object recognition. In: Proceedings of the IEEE SMC UK-RI Chapter Conference (2005)
Rasolzadeh, B., Tavakoli, A.T., Eklundh, J.O.: Attention in cognitive systems. theories and systems from an interdisciplinary viewpoint, pp. 123–140. Springer, Heidelberg (2008)
Navalpakkam, V., Itti, L.: An integrated model of top-down and bottom-up attention for optimizing detection speed. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2049–2056. IEEE, Los Alamitos (2006)
Lee, S., Kim, K., Kim, J., Kim, M., Yoo, H.: Familiarity based unified visual attention model for fast and robust object recognition. Pattern Recognition 43, 1116–1128 (2010)
Atmosukarto, I., Shapiro, L.: A learning approach to 3D object representation for classification. Structural, Syntactic, and Statistical Pattern Recognition, 267–276 (2010)
Denton, T., Demirci, M., Abrahamson, J., Shokoufandeh, A., Dickinson, S.: Selecting canonical views for view-based 3-D object recognition. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 2, pp. 273–276. IEEE, Los Alamitos (2004)
Büker, U., Hartmann, G.: Knowledge-based view control of a neural 3-D object recognition system. In: ICPR, vol. 4, pp. 24–29. IEEE, Los Alamitos (2002)
Ruhnke, M., Steder, B., Grisetti, G., Burgard, W.: Unsupervised learning of 3d object models from partial views. In: ICRA 2009, pp. 801–806. IEEE, Los Alamitos (2009)
Salamanca, S., Cerrada, C., Adan, A., Cerrada, J., Adán, M.: Free-Shaped Object Recognition Method from Partial Views Using Weighted Cone Curvatures. Progress in Pattern Recognition, Image Analysis and Applications, 222–232 (2005)
Kutter, O., Hilker, C., Simon, A., Mertsching, B.: Modeling and simulating mobile robots environments. In: 3rd International Conference on Computer Graphics Theory and Applications (GRAPP 2008), Funchal, Portugal (2008)
Kotthäuser, T., Mertsching, B.: Validating Vision and Robotic Algorithms for Dynamic Real World Environments. In: Second International Conference on Simulation, Modeling and Programming for Autonomous Robot, SIMPAR (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aziz, M.Z., Knopf, M., Mertsching, B. (2011). Knowledge-Driven Saliency: Attention to the Unseen. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2011. Lecture Notes in Computer Science, vol 6915. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23687-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-23687-7_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23686-0
Online ISBN: 978-3-642-23687-7
eBook Packages: Computer ScienceComputer Science (R0)