Abstract
We present a method for biologically-inspired object recognition with one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroundings using simple colour features. This map-like representation is fed into a dynamical neural network which performs pose, scale and translation estimation of the object given a set of previously observed object views. We demonstrate the feasibility of our algorithm for cognitive robotic scenarios and evaluate classification performance on a dataset of household items.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). CVIU 110, 346–359 (2008)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: An efficient alternative to SIFT or SURF. In: ICCV, Barcelona, pp. 2564–2571 (2011)
Terzić, K., Rodrigues, J., du Buf, J.: Fast cortical keypoints for real-time object recognition. In: ICIP, Melbourne, pp. 3372–3376 (2013)
Fukushima, K.: Neocognitron for handwritten digit recognition. Neurocomputing 51, 161–180 (2003)
Do Huu, N., Paquier, W., Chatila, R.: Combining structural descriptions and image-based representations for image, object, and scene recognition. In: IJCAI, pp. 1452–1457 (2005)
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., Poggio, T.: Object recognition with cortex-like mechanisms. IEEE T-PAMI 29, 411–426 (2007)
Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649 (2012)
Ullman, S.: High-Level Vision: Object Recognition and Visual Cognition. The MIT Press (1996)
Arathorn, D.: Computation in the higher visual cortices: Map-seeking circuit theory and application to machine vision. In: AIPR, pp. 73–78 (2004)
Faubel, C., Schöner, G.: A neuro-dynamic architecture for one shot learning of objects that uses both bottom-up recognition and top-down prediction. In: IROS. IEEE Press (2009)
Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernetics 27, 77–87 (1977)
Lomp, O., Zibner, S.K.U., Richter, M., Rañó, I., Schöner, G.: A Software Framework for Cognition, Embodiment, Dynamics, and Autonomy in Robotics: Cedar. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 475–482. Springer, Heidelberg (2013)
Faubel, C., Schöner, G.: Learning to recognize objects on the fly: a neurally based dynamic field approach. Neural Networks 21, 562–576 (2008)
McCann, S., Lowe, D.: Local naive bayes nearest neighbor for image classification. In: CVPR, Providence, pp. 3650–3656 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Lomp, O., Terzić, K., Faubel, C., du Buf, J.M.H., Schöner, G. (2014). Instance-Based Object Recognition with Simultaneous Pose Estimation Using Keypoint Maps and Neural Dynamics. In: Wermter, S., et al. Artificial Neural Networks and Machine Learning – ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham. https://doi.org/10.1007/978-3-319-11179-7_57
Download citation
DOI: https://doi.org/10.1007/978-3-319-11179-7_57
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11178-0
Online ISBN: 978-3-319-11179-7
eBook Packages: Computer ScienceComputer Science (R0)