Edge-Based Gaze Planning for Salient Proto-Objects

Abstract:

Selective attention of primates or human being has been modeled and implemented by many vision researchers in a decade. And also several attempts, which improve object recognition using selective attention model, have existed. But there are few researches in the gaze planning for the results of selective attention process. Therefore we propose a planning method based on edge information in the attended regions. And we explain the edge description methods (edge density and entropy) and also propose a new description method, edge uniformity. We evaluate the performance of the methods in the viewpoint of attentive object recognition.

• Periodical: Applied Mechanics and Materials (Volume 330)
• Pages: 1003-1007
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.330.1003
• Online since: June 2013
• Authors: Doo Jin Kim, Heon Cheol Lee, Tae Seok Lee, Kong Woo Lee, Beom Hee Lee
• Keywords: Edge Density, Edge Entropy, Edge Uniformity, Gaze Planning, Proto-Object

References

[1] L. Itti, C. Koch, and E. Niebur: A model of saliency-based visual attention for rapid scene analysis, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20 (1998) pp.1254-1259.

DOI: 10.1109/34.730558

[2] J. Harel, C. Koch, and P. Perona: Graph-Based Visual Saliency, Proc. of Advances in Neural Information Processing Systems (2006) pp.681-688.

[3] N. D. B. Bruce and J. K. Tsotsos: Saliency Based on Information Maximization, Proc. of Advances in Neural Information Processing Systems (2006) pp.155-162.

[4] H. Xiaodi and Z. Liqing: Saliency Detection: A Spectral Residual Approach, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (2007) pp.1-8.

[5] D. Walther, U. Rutishauser, C. Koch, and P. Perona: On the usefulness of attention for object recognition,Workshop on Attention and Performance in Computational Vision at ECCV(2004).

[6] S. Frintrop: VOCUS: A Visual Attention System for Object Detection and Goal-directed search, Lecture Notes in Artificial Intelligence (LNAI), vol. 3899(2006).

DOI: 10.1007/11682110_4

[7] D. Kim, H. C. Lee, and B. H. Lee: Attentional Grabcut for Object Recognition using PTZ Camera, Proc. of 7th Korea Robotics Society Annu. Conf., Gangneung, Korea(2012) pp.514-517.

[8] B. Alexe, T. Deselaers, and V. Ferrari: What is an object?, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2010, pp.73-80.

DOI: 10.1109/cvpr.2010.5540226

[9] D. M. Gavrila: A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 29(2007) pp.1408-1421.

DOI: 10.1109/tpami.2007.1062

[10] S.L. Phung and A. Bouzerdoum: Detecting People in Images: An Edge Density Approach, Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (2007).

DOI: 10.1109/icassp.2007.366136

[11] R. A. Rensink: Seeing, sensing, and scrutinizing, Vision Research, vol. 40, no. 10–12(2000), pp.1469-1487.

DOI: 10.1016/s0042-6989(00)00003-1

[12] R. A. Rensink: The Dynamic Representation of Scenes, Visual Cognition, vol. 7, no. (1/2/3) (2000), pp.17-42.

[13] D. Walther and C. Koch: Modeling attention to salient proto-objects, Neural Networks, vol. 19(2006), pp.1395-1407.

DOI: 10.1016/j.neunet.2006.10.001

[14] C. Koch and S. Ullman: Shifts in selective visual attention: Towards the underlying neural circuitry, Human Neurobiology, vol. 4(1985), pp.219-227.

DOI: 10.1007/978-94-009-3833-5_5