Shailesh Deshpande
ABSTRACT
The role played by attention in the increasingly important area of change detection is well recognized. The construction of automated visual change detection systems will benefit from an architecture based on sound cognitive principles. This paper proposes an attention-driven cognitive vision architecture for change detection and shows its utility with a remote sensing case study.
- Bridewell, W., Bello, P. Incremental object perception in an attention driven cognitive architecture. In proceedings of the 37th Annual Meeting of the Cognitive Science Society, July 22--25, 279--284 (2015).Google Scholar
- Lansdale, M., Underwood, G., Davies, C. Something overlooked? How experts in change detection use visual saliency. Applied Cognitive Psychology 24, 213--225 (2010). Google ScholarCross Ref
- Itti, L., Koch, C. A saliency-based search mechanism for overt and convert shifts of visual attention. Vision Research, 1489--1506 (2000). Google ScholarCross Ref
- Chella, A., Gaglio, M., Frixione, S. A cognitive architecture for artificial vision. Artificial Intelligence 89 (1--2), 73--111 (1997). Google ScholarDigital Library
- Chella, A., Frixione, M., Gaglio, S. An architecture of autonomous agents exploiting conceptual representations. Robotics and Autonomous Systems 25(3--4), 231--240 (1998).Google Scholar
- Chella, Gaglio, M., Chella, S., Gaglio, S., Frixione, S. Understanding Dynamic Scenes. Artifical Intelligence 123(1--2), 89--132 (2000). Google ScholarDigital Library
- Schultheis, H., Barkowsky, T. Casimir: An architecture for mental spatial knowledge processing. Topics in Cognitive Science. 3(4), 778--795 (2011). Google ScholarCross Ref
- Cohn, G., Magee, R., Galata, A., Hogg, D., Hazarika, S. Towards an architecture for cognitive vision using qualitative spatio- temporal representations and abduction. Spatial Cognition III. LNAI 2685. 232--248 (2003). Google ScholarDigital Library
- Rensink, R. Change Detection. Annu. Rev. Psychol. 53, 245--77 (2002). Google ScholarCross Ref
- Desolneux, A., Moisan, L., Morel, J.-M. From gestalt theory to image analysis - A probabilistic approach. (Accessed July 10, 2006) Available at http//www.math-info.univ-paris5.fr/~moisan/papers/2006-9.pdf.Google Scholar
- Flynn, M., Kanerva, P., Bhadkamkar, N. Sparse Distributed Memory Principles and Operation. (December 1989)Google Scholar
- Kanerva, P. Chapter 3. Sparse Distributed Memory and Related Models. 50--76 (2002).Google Scholar
- Snaider, J., McCall, R., Franklin, S. The LIDA framework as a general tool for AGI. In the proceedings of The Fourth Conference on Artificial General Intelligence, Mountain View, California, USA (2011). Google ScholarDigital Library
- Hussain, M., Chen, D., Cheng, A., Wei, H., Stanley, D. Change detection from remotely sensed images from pixel-based to object- based approaches. ISPR Journal of Photogrammetry and Remote Sensing. 80, 91--106 (2013). Google ScholarCross Ref
- CDNetA video database for testing change detection algorithms. In Changedetection.net.Google Scholar
- Gardenfors, P. Three level of inductive inference. D. Prawitz, B. Skyrms and D. Westerstahl, eds. Logic, Methodology, and Philosophy of Science IX. Elsevier Science, Amsterdam (1994).Google Scholar
- Xu, K., Lei Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y. Show attend and Tell Neural image caption generation with visual attention. In the proceedings of 32nd International Conference on Machine Learning, Lille, France (2015). Google ScholarDigital Library
- Madl, T., Baars, B., Franklin, S. The timing of the cognitive cycle. PLoSONE, 6(4):e14803. Google ScholarCross Ref
- Sowa, J. The cognitive cycle. (Accessed 2015) Available at http://www.jfsowa.com/pubs/cogcycle.pdf.Google Scholar
- Sowa, J. Semantic networks, Encyclopedia of artificial intelligence, second edition, edited by S. C. Shapiro. Wiley, New York. Updated version at http://www.jfsowa.com/pubs/semnet.pdf (1992). Google ScholarDigital Library
- Deshpande, S., Ray, K., Inamdar, A., Vin, H. Semi-supervised extraction of economic zones from urban area using hyperspectral data. In the proceedings of Asian Conference on Remote Sensing, Oct. 19--23, Manila, Philippines (2015).Google Scholar
- Desolneux, A., Moisan, L., Morel, J.-M.: Meaningful alignments. International Journal of Computer Vision, 40(1), 7--23 (2000). Google ScholarDigital Library
- Fei-Fei, L., Iyer, A., Koch, C., Perona, P. What do we perceive in a glance of a real-world scene? Journal of Vision, 7(10), 1--29 (2007). Google ScholarCross Ref
- Henderson, J., Hollingworth, A. High-level scene perception. Annual Review of Psychology, 50, 43--71 (1999). Google ScholarCross Ref
- Singh, M., Hoffman, D. Chapter 9 - Part-based Representations of Visual Shape. In Shipley, T., Kellman, P., eds. from Fragments to Objects Grouping and Segmentation in Vision. Elsevier Science, North Holland Press (2001) 401--459.Google Scholar
- Hoffman, D., Richards, W. Parts of recognition. Cognition, 18, 65--96 (1984). Google ScholarCross Ref
Index Terms
- CogVis: attention-driven cognitive architecture for visual change detection
Recommendations
Two-layer average-to-peak ratio based saliency detection
Visual saliency plays an important role in pattern recognition tasks such as rapidly seeking prominent regions in a complex scene to discover the meaningful objects. In this paper, we present a new method to detect visual saliency from an image. This ...
An intuitive model of perceptual grouping for HCI design
CHI '09: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsUnderstanding and exploiting the abilities of the human visual system is an important part of the design of usable user interfaces and information visualizations. Good design enables quick, easy and veridical perception of key components of that design. ...
Pre-attentive and attentive vision module
This paper introduces a new vision module, called PAAV, developed for the cognitive architecture ACT-R. Unlike ACT-R's default vision module that was originally developed for top-down perception only, PAAV was designed to model a wide range of tasks, ...
Comments