J H Fernyhough. Generation of qualitative spatio-temporal representations from visual input. PhD Thesis, 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....is discontinuous. 33.Exceptions to this are pointed out and considered in (Bennett 1994a) 34.We have also done some work on real time event recognition from image sequences, by means of qualitative event descriptions; our initial work in this area is reported in (Fernyhough, Cohn and Hogg 1996, Fernyhough 1997, Fernyhough, Cohn and Hogg 1997) 35.Here maximal can be stated in qualitative terms by saying that the region is not a proper part of another sea region which is also part of the convex hull of the land region. 36.E.g. one might add an order of magnitude representation such as that in (Raiman ....

Fernyhough, J. H.: 1997, Generation of qualitative spatio-temporal representations from visual input, PhD Thesis.

....Recognition from Visual Input using Qualitative Reasoning on Automatically Generated Spatio Temporal Models J Fernyhough, A G Cohn and D C Hogg School of Computer Studies, University of Leeds, LS2 9JT, UK. f agc scs.leeds.ac. ukg This work [ Fernyhough, 1997; Fernyhough et al. 1997 ] was motivated by the desire to apply qualitative spatiotemporal reasoning techniques to real world dynamic scene analysis. Such regions should be conceptually relevant to the physical structure of the domain rather than arbitrary. Our domains of interest are scenes ....

....Recognition from Visual Input using Qualitative Reasoning on Automatically Generated Spatio Temporal Models J Fernyhough, A G Cohn and D C Hogg School of Computer Studies, University of Leeds, LS2 9JT, UK. f agc scs.leeds.ac. ukg This work [ Fernyhough, 1997; Fernyhough et al. 1997 ] was motivated by the desire to apply qualitative spatiotemporal reasoning techniques to real world dynamic scene analysis. Such regions should be conceptually relevant to the physical structure of the domain rather than arbitrary. Our domains of interest are scenes where the movement of objects ....

J H Fernyhough. Generation of qualitative spatio-temporal representations from visual input. PhD Thesis, 1997.

....paper. Next we briefly describe a technique for learning semantically relevent spatio temporal regions. The main body of the paper demonstrates the effectiveness of this spatio temporal model in a qualitative event learning system supported by experimental results. Full details can be found in [ Fernyhough, 1997 ] 2 Generation of Semantic Regions In [ Fernyhough et al. 1996 ] we demonstrate how a (hierarchical) region based model of space (similar to the hand generated model of [ Howarth and Buxton, 1992a ] corresponding to the underlying structure of a domain, can be automatically constructed ....

....remaining paths stored in the database. However, some form of attentional control mechanism is often employed in visual surveillance applications to identify interesting objects. The basis of our attention control mechanism relies on extending the spatial model to incorporate temporal information [ Fernyhough, 1997 ] When we construct the database of paths used by objects travelling through the scene we also incorporate point coordinates at regular time intervals 1 that can be used later to form regions which sub divide the other composite regions within the spatial model into equi temporal regions ....

J H Fernyhough. Generation of qualitative spatio-temporal representations from visual input. PhD Thesis, submitted, 1997.

....have provided a broad outline of the research context for this paper. Next we briefly describe a technique for learning semantically relevent spatio temporal regions. The main body of the paper demonstrates the effectiveness of this spatio temporal model in a qualitative event learning system [7] supported by experimental results. 2 Generation of Semantic Regions In [6] we demonstrate how a (hierarchical) region based model of space (similar to the hand generated model of [9] corresponding to the underlying structure of a domain, can be automatically constructed from the extended ....

....remaining paths stored in the database. However, some form of attentional control mechanism is often employed in visual surveillance applications to identify interesting objects. The basis of our attention control mechanism relies on extending the spatial model to incorporate temporal information [7]. When we construct the database of paths used by objects travelling through the scene we also incorporate point coordinates at regular time intervals 1 that can be used later to form regions which sub divide the other composite regions within the spatial model into equi temporal regions ....

J H Fernyhough. Generation of qualitative spatiotemporal representations from visual input. PhD Thesis, 1997.

....we have provided a broad outline of the research context for this paper. Next, we briefly describe a technique for learning semantically relevant spatio temporal regions. The body of the paper demonstrates the effectiveness of this spatio temporal model in a qualitative event learning system [12,28] supported by experimental results. Then we will compare and contrast our approach with alternative techniques in the literature. There then follows a discussion of the underlying assumptions and of the methodology proposed. In conclusion we will discuss how the our present system might be ....

....our approach with alternative techniques in the literature. There then follows a discussion of the underlying assumptions and of the methodology proposed. In conclusion we will discuss how the our present system might be extended and further evaluated. The material in this paper is largely from [12] and has been reported on briefly previously in [13,28] 2 Generation of Semantic Regions In [13] we outlined how a (hierarchical) region based model of space corresponding to the underlying spatial structure of a domain, may be automatically constructed from the extended observation of objects ....

[Article contains additional citation context not shown here]

J H Fernyhough. Generation of qualitative spatio-temporal representations from visual input. PhD Thesis, 1997.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC