Abstract
In recent years there has been increasing interest in constructing cognitive vision systems capable of interpreting the high level semantics of dynamic scenes. Purely quantitative approaches to the task of constructing such systems have met with some success. However, qualitative analysis of dynamic scenes has the advantage of allowing easier generalisation of classes of di.erent behaviours and guarding against the propagation of errors caused by uncertainty and noise in the quantitative data. Our aim is to integrate quantitative and qualitative modes of representation and reasoning for the analysis of dynamic scenes. In particular, in this paper we outline an approach for constructing cognitive vision systems using qualitative spatial-temporal representations including prototypical spatial relations and spatio-temporal event descriptors automatically inferred from input data. The overall architecture relies on abduction: the system searches for explanations, phrased in terms of the learned spatio-temporal event descriptors, to account for the video data.
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
Yanai, K., Deguchi, K.: Recognition of indoor images employing qualitative model fitting and supporting relation between objects. In Sanfeliu, A., Villanueva, J., Vanrell, M., Alquezar, R., Eklundh, J.O., Aloimonos, Y., eds.: Proceedings 15th International Conference on Pattern Recognition. Volume 1., Barcelona, Spain, IEEE Press (2000) 964–967
Howarth, R.: Interpreting a dynamic and uncertain world: High-level vision. Artificial Intelligence Review 9 (1995) 37–63
Buxton, H., Howarth, R.: Spatial and temporal reasoning in the generation of dynamic scene descriptions. In RodrÃguez, R.V., ed.: Proceedings on Spatial and Temporal Reasoning, Montréal, Canada, IJCAI-95 Workshop (1995) 107–115
Fernyhough, J., Cohn, A., Hogg, D.: Constructing qualitative event models automatically from video input. Image and Vision Computing 18 (2000) 81–103
Cootes, T., Taylor, C., Cooper, D., Graham, J.: Training models of shape from sets of examples. In: Proc. British Machine Vision Conference. (1992) 9–18
Baumberg, A., Hogg, D.: Learning flexible models from image sequences. In: European Conference on Computer Vision, Springer Verlag (1994) 299–308
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. In: Proc. First International Conference on Computer Vision. (1989) 259–268
Blake, A., Curwen, R., Zisserman, A.: A framework for spatiotemporal control in the tracking of visual contours. International Journal of Computer Vision 11 (1993) 127–145
Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3 (1991) 71–86
Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77 (1989) 257–286
Starner, T., Pentland, A.: Real-time american sign language recognition from video using hidden markov models. In: Int. Symposium on Computer Vision. (1995)
Cohn, A.G., Hazarika, S.M.: Qualitative spatial representation and reasoning: An overview. Fundamenta Informaticae 46 (2001) 1–29
Cohn, A.G., Bennett, B., Gooday, J., Gotts, N.: RCC: a calculus for region based qualitative spatial reasoning. GeoInformatica 1 (1997) 275–316
Egenhofer, M., Franzosa, R.: Point-set topological spatial relations. International Journal of Geographical Information Systems 5 (1991) 161–174
Cohn, A.G., Gotts, N.M.: Representing spatial vagueness: a mereological approach. In L C Aiello, J.D., Shapiro, S., eds.: Proceedings of the 5th conference on principles of knowledge representation and reasoning (KR-96), Morgan Kaufmann (1996) 230–241
Clementini, E., Di Felice, P.: Approximate topological relations. International Journal of Approximate Reasoning 16 (1997) 173–204
Schlieder, C.: Reasoning about ordering. In A Frank, W.K., ed.: Spatial Information Theory: a theoretical basis for GIS. Number 988 in Lecture Notes in Computer Science, Berlin, Springer Verlag (1995) 341–349
Isli, A., Cohn, A.: A new approach to cyclic ordering of 2d orientations using ternary relation algebras. Artificial Intelligence 122 (2000) 137–187
Frank, A.U.: Qualitative spatial reasoning about distance and directions in geograp hic space. Journal of Visual Languages and Computing 3 (1992) 343–373
Meathrel, R.C., Galton, A.P.: A heirarchy of boundary-based shape descriptors. In Nebel, B., ed.: Proc. 17th IJCAI, Morgan Kaufmann (2001) 1359–1364
Bennett, B., Cohn, A.G., Torrini, P., Hazarika, S.M.: Describing rigid body motions in a qualitative theory of spatial regions. In Kautz, H.A., Porter, B., eds.: Proceedings of AAAI-2000. (2000) 503–509
Cristani, M., Cohn, A., Bennett, B.: Spatial locations via morpho-mereology. In: Proc. KR’2000, Morgan Kaufmann (2000)
Cohn, A.G., Bennett, B., Gooday, J., Gotts, N.: Representing and reasoning with qualitative spatial relations about regions. In Stock, O., ed.: Temporal and spatial reasoning, Kluwer (1997)
Wolter, F., Zakharyaschev, M.: Spatio-temporal representation and reasoning based on RCC-8. In: Proceedings of the seventh Conference on Principles of Knowledge Representation and Reasoning, Morgan Kaufman (2000) 3–14
Wolter, F., Zakharyaschev, M.: Qualitative spatio-temporal representation and reasoning: a computational perspective. In: Exploring Artifitial Intelligence in the New Millenium. Morgan Kaufmann (To appear)
Bennett, B., Cohn, A., Wolter, F., Zakharyaschev, M.: Multi-dimensional modal logic as a framework for spatio-temporal reasoning. Applied Intelligence (2002) To appear.
Hayes, P.J.: Naive physics I: Ontology for liquids. In Hobbs, J.R., Moore, B., eds.: Formal Theories of the Commonsense World. Ablex (1985) 71–89
Muller, P.: A qualitative theory of motion based on spatio-temporal primitives. In Cohn, A.G., Schubert, L.K., Shapiro, S., eds.: Principles of Knowledge Representation and Reasoning: Proceedings of the 6th International Conference (KR-98), Morgan Kaufman (1998) 131–141
Muller, P.: Space-time as a primitive for space and motion. In Guarino, N., ed.: Formal ontology in information systems: Proceedings of the 1st international conference (FOIS-98). Volume 46 of Frontiers in Artificial Intelligence and Applications., Trento, Italy, Ios Press (1998) 63–76
Hazarika, S.M., Cohn, A.G.: Qualitative spatio-temporal continuity. In Montello, D.R., ed.: Spatial Information Theory: Foundations of Geographic Information Science; Proceedings of COSIT’01. Volume 2205 of LNCS., Morro Bay,CA, Springer (2001) 92–107
Cui, Z., Cohn, A.G., Randell, D.A.: Qualitative simulation based on a logical formalism of space and time. In: Proceedings of AAAI-92, Menlo Park, California, AAAI Press (1992) 679–684
Shanahan, M.: Noise, non-determinism and spatial uncertainty. In: Proceedings of AAAI-97. (1997) 153–158
Shanahan, M.: A logical account of the common sense informatic situation for a mobile robot. Electronic Transactions on Artificial Intelligence (1999)
Remolina, E., Kuipers, B.: A logical account of causal and topological maps. In: Proceedings of Seventeenth International Conference on Artificial Intelligence (IJCAI-01). Volume I., Seattle, Washington, USA (2001) 5–11
Shanahan, M.: A logical account of perception incorporating feedback and expectation. In: Proc. 8th Int. Conf. on Knowledge Representation and Reasoning, San Mateo, Morgan Kaufmann (2002)
Galata, A., Cohn, A.G., Magee, D., Hogg, D.: Modelling interaction using learnt qualitative spatio-temporal relations and variable length markov models. In: Proc. European Conference on AI (ECAI). (2002)
Galata, A., Johnson, N., Hogg, D.: Learning behaviour models of human activities. In: British Machine Vision Conference, BMVC’99. (1999)
Galata, A., Johnson, N., Hogg, D.: Learning Variable Length Markov Models of Behaviour. Computer Vision and Image Understanding (CVIU) Journal 81 (2001) 398–413
Ron, D., Singer, S., Tishby, N.: The Power of Amnesia. In: Advances in Neural Information Processing Systems. Volume 6. Morgan Kauffmann (1994) 176–183
Guyon, I., Pereira, F.: Design of a Linguistic Postprocessor using Variable Memory Length Markov Models. In: International Conference on Document Analysis and Recognition. (1995) 454–457
Cormack, G., Horspool, R.: Data Compression using Dynamic Markov Modelling. Computer Journal 30 (1987) 541–550
Bell, T., Cleary, J., Witten, I.: Text Compression. Prentice Hall (1990)
Hu, J., Turin, W., Brown, M.: Language Modelling using Stochastic Automata with Variable Length Contexts. Computer Speech and Language 11 (1997) 1–16
Magee, D.: Tracking multiple vehicles using foreground, background and motion models. In: Proc. ECCV Workshop on Statistical Methods in Video Processing. (2002)
Johnson, N., Hogg, D.: Learning the Distribution of Object Trajectories for Event Recognition. Image and Vision Computing 14 (1996) 609–615
Wren, C., Azarbayejani, A., Darrell, T., Pentland, A.: Pfinder: Real-time tracking of the human body. IEEE Transactions on PAMI 19(7) (1997) 780–785
Cohn, A.G., Hazarika, S.M.: Continuous transitions in mereotopology. In: Commonsense-2001: 5th Symposium on Logical Formalizations of Commonsense Reasoning. (2001)
Hazarika, S.M., Cohn, A.G.: Abducing qualitative spatio-temporal histories from partial observations. In: Proc. 8th Int. Conf. on Knowledge Representation and Reasoning, San Mateo, Morgan Kaufmann (2002)
Randell, D., Witkowski, M., Shanahan, M.: From images to bodies: Modelling and exploiting spatial occlusion and motion parallax. In: Proc. IJCAI, Morgan Kaufmann (2001)
Freksa, C.: Using orientation information for qualitative spatial reasoning. In Frank, A.U., Campari, I., Formentini, U., eds.: Proc. Int. Conf. on Theories and Methods of Spatio-Temporal Reasoning in Geographic Space, Berlin, Springerverlag (1992)
Meathrel, R.C., Galton, A.: A hierarchy of boundary-based shape descriptors. In: Proc. IJCAI. (2001) 1359–1364
Jungert, E.: Symbolic spatial reasoning on object shapes for qualitative matching. In Frank, A.U., Campari, L., eds.: Spatial Information Theory: A Theoretical Basis for GIS. Lecture Notes in Computer Science No.716, COSIT’93, Springer-Verlag (1993) 444–462
Clementini, E., Di Felice, P.: A global framework for qualitative shape description. Geoinformatica 1 (1997) 1–17
Davis, E., Gotts, N.M., Cohn, A.G.: Constraint networks of topological relations and convexity. Constraints 4 (1999) 241–280
Kaelbling, L.P., Oates, T., Hernandez, N., Finney, S.: Learning in worlds with objects. In Cohen, P.R., Oates, T., eds.: Learning Grounded Representations. Number Technical Report SS-01-05, AAAI Press (2001) 31–36
Zacks, J., Tversky, B., Iyer, G.: Perceiving, remembering and communicating structure in events. Journal of Experimental Psychology: General 136 (2001) 29–58
Zacks, J., Tversky, B.: Event structure in perception and conception. Psychological Bulletin 127 (2001) 3–21
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cohn, A.G., Magee, D.R., Galata, A., Hogg, D.C., Hazarika, S.M. (2003). Towards an Architecture for Cognitive Vision Using Qualitative Spatio-temporal Representations and Abduction. In: Freksa, C., Brauer, W., Habel, C., Wender, K.F. (eds) Spatial Cognition III. Spatial Cognition 2002. Lecture Notes in Computer Science, vol 2685. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45004-1_14
Download citation
DOI: https://doi.org/10.1007/3-540-45004-1_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40430-9
Online ISBN: 978-3-540-45004-7
eBook Packages: Springer Book Archive