The Performance of a Biologically Plausible Model of Visual Attention to Localize Objects in a Virtual Reality
- 2 Citations
- 3k Downloads
Abstract
Visual attention, as a smart mechanism to reduce the computational complexity of scene understanding, is the basis of several computational models of object detection, recognition and localization. In this paper, for the first time, the robustness of a biologically-constrained model of visual attention (with the capability of object recognition and localization) against large object variations of a visual search task in virtual reality is demonstrated. The model is based on rate coded neural networks and uses both bottom-up and top-down approaches to recognize and localize learned objects concurrently. Furthermore, the virtual reality is very similar to real-world scenes in which a human-like neuro-cognitive agent can recognize and localize 15 different objects regardless of scaling, point of view and orientation. The simulation results show the neuro-cognitive agent performs the visual search task correctly in approximately 85.4 % of scenarios .
Keywords
Computational neuroscience Object localization Object recognition Virtual reality Visual attention Visual searchNotes
Acknowledgement
This work has been supported by the European Union project “Spatial Cognition” under grant agreement no 600785.
References
- 1.Miller, E.K., Buschman, T.J.: Cortical circuits for the control of attention. Curr. Opin. Neurobiol. 23(2), 216–222 (2013)CrossRefGoogle Scholar
- 2.Borji, A., Itti, L.: State-of-the-art in visual attention modelling. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 35(1), 185–207 (2013)MathSciNetCrossRefGoogle Scholar
- 3.Jamalian, A., Hamker, F.H.: Biologically-inspired models for attentive robot vision: a review. In: Innovative Research in Attention Modeling and Computer Vision Applications, pp. 69–98. Information Science Reference, Hershey (2016)Google Scholar
- 4.Beuth, F., Hamker, F.H.: Attention as cognitive, holistic control of the visual system. In: Workshop of New Challenges in Neural Computation (NCNC 2015), Aachen (2015a)Google Scholar
- 5.Antonelli, M., Gibaldi, A., Beuth, F., Duran, A.J., Canessa, A., Chessa, M., Solari, F., del Pobil, A.P., Hamker, F., Chinellato, E., Sabatini, S.P.: A hierarchical system for a distributed representation of the peripersonal space of a humanoid robot. IEEE Trans. Auton. Ment. Dev. 6(4), 259–273 (2014)CrossRefGoogle Scholar
- 6.Beuth, F., Wiltschut, J., Hamker, F.H.: Attentive stereoscopic object recognition. In: Workshop of New Challenges in Neural Computation (NCNC 2010) (2010)Google Scholar
- 7.Chikkerur, S., Serre, T., Tan, C., Poggio, T.: What and where: a bayesian inference theory of attention. Vision Res. 50(22), 2233–2247 (2010)CrossRefGoogle Scholar
- 8.Hamker, F.H.: The emergence of attention by population-based inference and its role in distributed processing and cognitive control of vision. Comput. Vis. Image Underst. 100(1-2), 64–106 (2005)CrossRefGoogle Scholar
- 9.Walther, D.B., Koch, C.: Attention in hierarchical models of object recognition. Prog. Brain Res. 165, 57–78 (2007)CrossRefGoogle Scholar
- 10.Logothetis, N.K., Pauls, J., Poggio, T.: Shape representation in the inferior temporal cortex of monkeys. Curr. Biol. 5(5), 552–563 (1995)CrossRefGoogle Scholar
- 11.Beuth, F., Hamker, F.H.: A mechanistic cortical microcircuit of attention for amplification, normalization and suppression. Vision Res. 116(B), 241–257 (2015b)Google Scholar
- 12.Nene, S.A., Nayar, S. K., Murase, H.: Columbia Object Image Library (COIL-100), CUCS-006-96. Technical report (1996)Google Scholar
- 13.Hamker, F.H.: Spatial Cognition of humans and brain-like artificial agents. Künstliche Intelligenz 29, 83–88 (2015)CrossRefGoogle Scholar
- 14.
- 15.
- 16.Vitay, J., Dinkelbach, H.Ü., Hamker, F.H.: ANNarchy: a code generation approach to neural simulations on parallel hardware. Front. Neuroinformatics 9, 1–20 (2015)CrossRefGoogle Scholar