An Adaptive GIS Tool for Image Characterisation

(1)

Characterisation

Georgios Sakellariou

Department of Computing, Imperial College London georgios.sakellariou@gmail.com

Abstract. GIS systems often rely on low-level, pixel-based representations of satellite scenes. The purpose of this paper is to show the advantages of using an intermediate representation incorporating multiple criteria in scene characterisation, as well as a framework for monitoring changes over time based on features of interest. A Conceptual Spaces framework, in conjunction with navigation-based skeletonisation are employed for this purpose. We evaluate our system on satellite images of rivers and lakes.

1 Introduction

The problem of identification of important features with remote sensing methods is a very active research field, with applications ranging from cartography and oceanography to the identification of military targets. This application lies in the general field of Geographical Information Science [11]. It goes one step further than being merely a data collection system, since it employs artificial intelligence techniques to represent and characterise the scene. At the same time, the approach followed does not aim to create or use a symbolic representation and ontology of geographical information. The major reason for selecting this application is the quantity of visual information that is included in satellite images, as well as the fact that the depicted objects are all natural. The aim of the system is to collect visual topological and morphological information about river segments, and create an intermediate graph representation containing this information. This graph representation can then be utilised for further high- level processing, such as formal concept analysis [19]. The dataset is deliberately restricted to segmented satellite images, in order to avoid the process of seg- mentation of complex scenes. The system can be used in conjunction with a supervised or unsupervised GIS scene classification algorithm [17] to identify river segments automatically. The developed system aims to provide a generic and modular visual characterisation platform for inland water features. In this sense, it forms a GIS spatial analysis tool. However, contrary to traditional spatial analysis approaches, spatial information is represented in a sub-symbolic intermediate representation. This contrasts the tendency to merely be limited to image coordinates signifying areas or attributes of interest. This distinctive feature enables the reusability of the data produced. The simplification of information exchange is a major issue when attempting to combine collected data

(2)

from several geographical information systems. Thus, a sub-symbolic representation would provide a platform encouraging GISinteroperability. At the same time, this approach does not suffer from the pitfalls of ontology-driven GIS applications. A major potential use of the monitoring of inland water features is the fluctuation of water levels and the erosion of the coastline occurring over a period of time. A direct application of this monitoring is the measurement of the effects of global warming in specific areas of interest. The correlation between descriptive attributes (pollution levels, etc) and position (skeleton of river) is the key to successfully characterising a river [3]. Effective river segment characterisation is the first step to their categorisation and identification. The collection of several descriptive attributes concerning their shape facilitates this categorisation process. Common examples are pollution levels and the development of river bank deterioration. In addition, a structural representation of a river within an image can further facilitate the enrichment of this representation with attributes specific to the application. The proposed graph representation as applied to river networks combines the advantages of both vector and polygon representations in terms of the included spatial information. The method employed in this paper has the potential of acting as a representation framework for such information.

2 Characterisation as Navigation

In [18], the need for a new technique of computing the skeleton of an object is examined. The tight coupling between the generation of the skeletal points and the higher-level representation of the skeletal line is proposed. A novel skeletonisation algorithm is presented that draws on techniques developed for mobile robot mapping and navigation and offers a number of advantages over existing skeletonisation methods. First, because the algorithm works by hopping from one landmark position in the image to another, it has to visit far fewer pixels to find a skeleton compared to conventional algorithms. Second, unlike other techniques, the exploratory nature of the algorithm allows it to identify junctions and end- points on the fly, which facilitates later high-level symbolic processing. Finally, the method is more generic than others, in the sense that it can be adjusted to compute skeletons containing a variety of different sorts of morphological information. Although much effort has been put into developing skeletonisation algorithms, no attempt up to now has been made to treat skeletonisation as a problem of navigation. However, it turns out that methods for mobile robot mapping and navigation, such as those presented in [10, 9, 8], can be transferred to skeletonisation. The conceptual challenge here is to think of a robot’s environment as analogous to an object in a segmented image, with the robot itself located at a pixel inside that object. The problem of skeletonisation is then analogous to that of exploring and mapping the environment by navigating inside it while remaining on the skeletal line. These features of the algorithm make it particularly suitable to object characterisation, based on features or attributes of interest.

(3)

2.1 Including Morphological and Structural Information

Skeletonisation on its own is not sufficient to describe a shape in a satisfactory way. The reason for this is that similar shapes can have very different skeletons, while very different shapes can have similar skeletons. Hence, additional information is included, with the intention of capturing the morphology of the object contour. Various techniques have been proposed for accomplishing this.

The two most important influences on the author’s work have been Blum’s Me- dial Axis Transform [2] and the Shock Graph [22]. In [2], the shortest distance from every point belonging to the skeleton to the object contour is encoded.

The reconstruction of the original shape from its skeleton is possible in this manner. Shock graphs [22] go one step further and keep a record of the rate of change of the minimum distance to the contour along the skeleton. In this fashion, each segment of the skeleton is assigned a status. By creating these categories, a symbolic representation of the shape can be formed. The development of the algorithm took place with the aim of using the data it yields for high-level representation. In pursuit of this, it features two major advantages. First, the navigation process is not continuous. It consists of hops from one skeletal point to another. The data produced will therefore be more easily processed by high- level representation frameworks, such as those proposed in [20, 5, 13]. Second, this technique allows for the computation of any kind of morphological information, including those presented in [2, 22], since the data encoded on the skeletal points is being added on the fly. Finally, unlike other related work [24], structural information of vital importance for logical reasoning in object recognition, such as junctions and end points, is extracted with no post-processing.

2.2 The Algorithm in Detail

As mentioned in Section 2, the crucial issue is to think of an analogy between the movement of a pixel inside an object with the motion of a robot inside a room. The aim for the pixel is to explore and navigate inside the object whilst staying on a path corresponding to the skeletal line. In order to achieve this, the pixel-robot has virtual sensors, which yield information about the distance to the boundaries. The sensors are emulated by checking a circular area around the pixel-robot for points that belong to the boundary. In this way, touch-points on the boundary can be extracted. The aim of the pixel-robot is to maintain a path along which there are only two touch-points. If there are fewer than two, the robot adjusts its position, the radius of the circular area, or both. If there are more than two touch-points, that means there is a junction and the robot explores all the possible branches. The real-world equivalent of this topic has already been studied in the context of Kuipers’Spatial Semantic Hierarchy [8].

What is more, the close connection between mapping and the skeleton has been explored in [10, 9]. In the present author’s work, an attempt is made to adapt these ideas to the context of a digitised image. The roaming pixel checks a circle around it for touch points with the contour. If two touch points are found, then the pixel jumps a distance equal to the normal distance between the current

(4)

Fig. 1.Divergence-based skeleton Fig. 2.Navigation-based skeleton

centre and the cord connecting those two touch points. For object segments whose width remains constant, the algorithm performs no hops and the output is similar to that of standard skeletonisation algorithms. However, the more the object’s width varies along the skeletal line, the greater these hops will be. Hence, the algorithm is better suited to naturalistic shapes. Special mention should be made of the sub-cases of the two touch-point case. At every stage, the algorithm retains a memory of the last skeletal pixel traversed, and calculates the angle formed by that pixel, the current pixel, and the next pixel. This in turn affects the decision of whether the pixel-robot is going to move forwards or backwards.

There is also a special provision for the cases where the movement of the pixel- robot makes the sensors lose touch with one of the surfaces, and confuse it with a newly seen surface. This would clearly yield an incorrect skeleton, since only two of the total of three touch points would be sensed.

A very common problem among skeletonisation algorithms, and one that is not straightforwardly overcome, is the generation of many spurious branches.

Moreover, small variations in the contour of an object can have rather drastic consequences in the shape of its skeleton. Consequently, branch pruning is often used as a method of deleting these branches [4]. The advantage of navigation- based skeletonisation is that by adjusting sensitivity parameters these spurious branches can be limited to a minimum, or completely eliminated. In effect, this feature of the algorithm renders it more suitable for the skeletonisation of complex shapes, where these branches become a source of great confusion and usually have no structural significance. This comparative advantage is illustrated in figures 1 and 2. The navigation-based skeleton (figure 2) produces no spurious branches at all. In contrast, the divergence-based thinning algorithm [4]

generates several of them (figure 1).

3 Characterising River Networks

Characterisation involves monitoring specific characteristics of the scene that are important to the user. In the particular case of river characterisation [23, 16], both structure and shape are indispensable elements in the description of different river segments. Rivers are structured shapes, with branches and forks, but nonetheless exhibit considerable variation in the morphology of different segments. For this work, the Conceptual Spaces framework [5] is used. A Con-

(5)

ceptual Space is ametric space in which entities are characterised by a number of quality dimensions. Quality dimensions can be closely tied to the raw input or defined in more abstract terms. In this respect, the goal of our system is to not just consider a single descriptor, but several of them.

Fig. 3.Near Toronto, Canada

The local topology of a river system plays a prime role in the successful characterisation of that region. Structural information can be highly informative to the end of identifying segments and sources. Once the topology of the river network has been determined, a more detailed characterisation of the river segments can be accomplished by bringing morphology into the picture. Lastly, in addition to the morphological attributes that can potentially be recorded by navigation-based skeletonisation, graphs based on navigational skeleton representations allow for other non-morphological attributes to be considered. These could include sediment, nutrients, toxicants, and heat. Such a characterisation technique can also be used to classify water features. The most significant advantage of having an adaptable skeletonisation system is the capability to vary the collected attributes to best describe or identify a given feature. The best case scenario is where the variation of one single attribute is sufficient to distinguish between features of interest. Even though this is usually not the case, the mere fact that the attributes can be adapted facilitates the classification process. In figure 3 to figure 5, examples of the application of the algorithm to real satellite images can be seen. The topology is recorded on the fly, while morphology or additional thematic data can be included or added according to the specific application. In the skeletons extracted from these examples, nodes corresponding to junctions appear as black, while nodes corresponding to end-points appear as grey.

(6)

Fig. 4.Near Toronto, Canada

Fig. 5.Dessau, Germany

4 Monitoring Change

Measuring and quantifying changes in time series images is a topic of considerable importance in the GIS community [15, 6, 12]. The developed representation system is applied to a series of satellite images depicting the same area, taken over large time intervals. We claim that an attributed graph representation is sufficient to successfully describe the changes that have taken effect to the water features present in the images. In turn, this method can potentially be used to measure the consequences of global warming to lakes, ponds and rivers around the world. Time intervals could range from a few months or days in the case of e.g. floods, to decades in the case of the effects of global warming.

4.1 Quantifying Change

Conceptual Spaces can prove very powerful when one attempts to describe similarity [7, 1] . To each conceptual space corresponds a similarity metric. In this way, a degree of similarity can be determined when comparingknoxels- or points in the n-dimensional metric space - belonging to different objects. This metric is tailored to the nature of the conceptual space itself. Since our low-level representation yields skeletons, we selected graph matching as the similarity metric of choice. When it comes to the problem of inexact graph matching, one must ask what kind of application this matching will serve, in order to find the most suitable approach. Probably the first inexact graph matching algorihm is the one proposed by [14], an improvement of which is also used in the widely popu- lar SubDue software. In our case, theApproximate Graph Matcher [21] seemed

(7)

an appropriate choice. The original motivation for the development of the algorithm was various biology-related applications. Two features of the algorithm render it most suitable for classification in the context of conceptual spaces.

First, the matcher allows for attributes to be included in the graph representations. Since we are pursuing the comparison of attributed graphs, a matcher allowing attributes (or weights) is imperative. Second, the nature of its input enables comparisons and identifications of matches between many different graphs in one go. The graphs that need to be classified are encoded in a text file. The program then compares every graph to every other graph in the file, which effec- tively acts much like a database. Hence, even when comparing a large number of graphs, the process of classification is uncomplicated. At the same time, the fact that the software has been written in the K language, which was developed to process large amounts of data for financial applications, ensures that execution will be very fast.

4.2 Water Level Changes over Time

In contrast to sea levels, inland water levels tend to decrease as average tempera- tures rise. Evaporation is the primary cause of this phenomenon. The quantifica- tion of the effect of these changes and their consequences on the local landscape have been the motivation for being involved with satellite images in the first place. By altering the measured and compared attributes, conclusions can be drawn regarding the nature of the alterations that have taken place over a period of time. For example, the length of the branches in a drying river changes much more than the angles that are formed between these branches and the main stream. In that respect, the capability of the developed characterisation method to record multiple attributes enables a more thorough monitoring of the changes that are taking effect. Table 1 shows the quantitative measures of change to water features, as computed from images of places taken over 10 year time intervals. Snapshots of the same area taken between 1970 and 1990 (figure 6) have been used for this purpose. The framework has been used with two

0

12

3456789101112131415161718192021222324 25 26 2728293031323334353637383940414243444546474849505152535455565758

59 60616263646566676869 7071 7273747576777879808182838485868788 8990919293949596979899100101102103104105106107108109110111

112 113 114 115116117118119

120121 122123 124125126127128129130 131132133134135136137138139140 141142143144145146147148149150151152153154155156 157 158159160161 162163164165166 167 168169170171172173174175 176177178179180181 182183184185186187188 189190191192193194195196 197198199200201202203 204205206207208209210211212 213214215216217218219220 221222223224225226227228229 230 231 232233234235236237238239240241242243244245246247248249250251252253254255256257258259260

261262

263 264 265266267268269270 271272273274275276277 278279280281282283284 285286287288289290291 292293294295296297298 299300301302303304305306 307308309310311312313314 315316317318319320321 322323324325326327328329330 331332333334335336337338 339340341342343344345346 347348349350351352353354355356357358359360361362363364365366367368 369370371372373374375376377378379380381382383384385386387388389 390391392393394395396397398399 400 401 402403404405 406407408409410 411 412413414415416417418419 420421 422423424425426427428429430431 432433434435436437438439440 441442 443444445446447448 449 450 451 452453 454455456457 458459 460461462463464465466467468469470471472473474475476477478479480481482483484485486488487 489

490491492 493494495496497498499500501502503504505506507508509510511512513514515516517518 519 520521522523 524 525 526 527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562

563 564

565566567 568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622

623 624 625 626627

628 629 630631632633634635636637 638639640641642643644645646647648649 650651652653654655656657658659660661662663664665666667668669670671672

673674675676677678679

680681682 683684685686687688689690691 692 693694

695696697698699700701702703 704705706707708709710711712713714 715716717718719720721722723724725 726727728729730731732733734735 736737738739740741

742 743744745746747748

749 750751752753754755756757758759 760761762763764765766767768769770771772773774775 776777778 779

780781 782783784785 786787788789790791792793794795796797798799 800801802803804805806807808809810811 812813814815816817818819820821822 823824825826827828829830831 832833834835836837838839 840841842843844845846847

848

849 850851852853854855856857 858859860861862863864865866867868869 870871872873874875876877878

879 880 881 882 883 884 885 886 887888 889890891892893894895 896897898899900901902903904905 906907908909910911912913914915916

917 918919920921 922923924925 926 927928929930931932933934 935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970

971972973974975976977978979980981982983984985986987988989990991992993994995996 9979989991000 1001 1002

1003 1004 1005100610071008100910101011101210131014101510161017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057

0123

45678910111213141516

171819 2021 2223

24 25 2627 28293031323334353637 3839 4041 4243444546474849505152535455565758596061626364656667686970717273 747576777879808182838485868788 89 90 9192939495 96979899 100101102103104 105106107108109110111112113114115116117118119120121122 123124125126127 128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230

231232233234235236237238239240241242243244245 246247

248249 250251

252253254 255256257258259260 261262263264265 266267268269270271272 273274275276277278 279280281282283284285286 287288289290291292293 294295296297298299 300301302303304305306 307308309310311312313 314315316317318319320 321322323324325326327328 329330331332333 334 335 336 337 338 339340 341342343344345346347348349 350351352353

354

355356357 358359 360361362363364365366367 368369370371372373374375376377378379380381382383384385 386387388389390391392393394395396397398399400 401402403404405406407408409410411412413414 415416417418419420421422423424425426 427428

429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467 468 469 470 471 472 473 474 475 476 477 478 479 480 481482483484485 486487488489490491492493494 495496497498499500501502503504 505506507508509510511512513 514515516517518519 520521522523524525526 527528529530531532 533534535536537538539540 541542543544545546547548 549550551552553554555556 557558559560561562563564565 566567568569570571572573 574575576577578579580581 582583 584 585586587588589590591592593594595596597598599 600601602603604605606607608 609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648

649 650

651652653654655656657658659660661662663664665666 667668669670671672 673674675676677678679 680681682683684685686687 688689690691692693694 695696697698699700701702703 704705706707708709710711 712713714715716717718719720 721722 723 724725726727 728729 730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771

772 773774775776777778779780781782783784785786787788 789790791792793794795796797799798

800801802803804805 806807808809810811812813814 815 816817818819820821822823824825826 827 828829830831 832 833834

835

836 837838 839840 841842843 844845 846847848849 850851 852853854855856857858859860861862863864865866867868869870871

872 873 874875876877878879880881882883884885886887888

889 890891892893894895896897898899900901

902903904905906 907908909910911912913914 915916917918919920921922923924925 926 927928929930931 932 933 934935936937 938

939 940 941 942 943 944 945946947948949950951952953954955956957958959960961962963964965966967968969970971972973 974 975 976

977978979980 981982983 984

985986987988989990991992993994995 996

997998999 10001001

1002 1003

1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015101610171018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036

1037

1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 10541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076

1077 1078 1079

0

1234567 891011121314151617181920212223242526

27282930313233343536 37

38 394041 424344454647

4849 505152 53545556575859606162636465666768 6970717273747576777879808182 83848586878889 90919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134 135 136137138139140141142143 144145146147148149150151 152153154155156157158159 160161162163

164165166167168169170 171172173174175176 177178179180181182183 184185186187188189190191 192193194195196 197198199200201202203204 205206207208209 210211212213214 215216217218219220221222223224225226 227 228 229 230231 232233234235 236237 238 239

240241242243244245246247248249250251252 253254 255256257258259260261 262263264265266267268269270271 272273274275276277278279 280281282283284285286287 288289 290 291 292 293 294 295 296297 298 299 300301 302303304305306 307308309310311312313314315316 317318319320321322 323324325326 327 328329330331332333 334335336337338339340 341342343344345346 347348349350351352353354 355356357358359360361 362363364365366367368369 370371372373374375 376 377378379380381382383384385386387388389390391392393394395396397398399400401402403404405 406407408409410411412413414415416417418419420421422423424 425 426 427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463

464

465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502

503 504505 506

507508509 510 511

512 513514515516517518519520521522523524525526527528529530531532533534535536537538539

540541 542543544545546547548 549550551552553 554555 556557558559560561562563

564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640

641642 643644 645646647648649650651652653 654655656657658659660661662663664665 666667668669670671672673674 675676677678679 680 681682 683684685686687

688689690 691692693 694

695696697698699 700701702703704 705706707708709710 711712713714715716717 718719 720 721 722 723724725 726727728729730731732733734735 736

737 738

739740741742743744745746747 748 750 751 752 753754 755756757

758759760761762763764765766767768769770771 772773774775776777

778 779780781782783 784 785 786787788789790791792793794795796797798799800801 802 803 804

805806807808809810811812813814815816817818 819 820 821

822823824825826827828829830831832833834

835836

837838839840841842843 844845846847 848849850851852 853854855856857 858859860861 862863864865866 867868

Fig. 6.Change of lake water levels

(8)

Change over time(Sample 1) Dimensionaverage r angle

1970-1980 59% 28%

1980-1990 75% 84%

1970-1990 85% 87%

1970-1990 30% 13%

1970-1980 81% 80%

1980-1990 22% 13%

1970-1990 83% 81%

Table 1.Measuring change over time: 3 time series image samples

attributes, average radius along the skeleton, and branch angle. In the images depicting a lake in Kazakhstan (figure 6), we can see that the greatest structural changes have taken effect during the past 10 years. This can be corroborated by an inspection of the time series images. The recession of water levels during the decade 1980-1990 has caused greater alterations to the shape of the lake, and hence the landscape. In the case of two attributes, a two-dimensional conceptual space containing the results of table 1, can be used in conjunction with Princi- pal Components Analysis (PCA)to produce maps of change. The presented data were collected from three sets of time series images over identical time intervals.

Fig. 7.Analysis of change

Figure 7 shows what this analysis can show for the three time series, similar to the one in figure 6 depicting a lake in Kazakhstan. In figure 7 (left), points corresponding to change between 1970 to 1980 have been highlighted as grey, while the rest as black. Figure 7 (right) indicates how PCA assists in forming

(9)

groups of points (depicted as different shades of grey). In this example, three groups can be separated by the two principal components. In cases with large numbers of measured attributes, and hence many dimensions, such grouping of data can be useful in extracting patterns of change.

5 Conclusion

This paper demonstrated the applicability of the system presented in previous chapters to the challenging problem of river characterisation based on real satellite images. By providing an intermediate representation of river networks, the system contributes to the field of GIS, where lower level representations are the norm. The advantages of this higher-level representation are adaptability and interoperability. Second, the capabilities of the conceptual space framework employed in this paper are more evidently utilised by measuring and classifying changes in time series satellite images. The multi-attribute approach to river characterisation provides a platform that can successfully describe morphological as well as topological changes to river networks. Moreover, PCA is able to classify these changes and provides the user with an informative measure of mon- itored alterations. These two functions render the system a useful GIS tool that can be used to characterise river networks or classify water feature alterations over a period of time. In addition, this paper showed that the design choices made can produce an adaptable and versatile GIS tool.

References

1. Ola Ahlqvist. Using uncertain conceptual spaces to translate between land cover categories. International Journal of Geographical Information Science, 19(7):831–

857, 2005.

2. Harry Blum. A Transformation for Extracting New Descriptors of Shape. In Weiant Wathen-Dunn, editor,Models for the Perception of Speech and Visual Form, pages 362–380. MIT Press, Cambridge, 1967.

3. J.B. Dalton, D.J. Bove, and C.S. Mladinich. Remote sensing characterization of the animas river watershed, southwestern colorado, by aviris imaging spectroscopy.

Scientific Investigations Report 5203, U.S. Geological Survey, 2004.

4. P. Dimitrov, C. Phillips, and K. Siddiqi. Robust and efficient skeletal graphs. pages 417–423, 2000.

5. Peter G¨ardenfors. Conceptual Spaces: The Geometry of Thought. MIT Press, Cambridge, MA, USA, 2000.

6. Rie Honda, Shuai Wang, Tokio Kikuchi, and Osamu Konishi. Mining of moving objects from time-series images and its application to satellite weather imagery.J.

Intell. Inf. Syst., 19(1):79–93, 2002.

7. Werner Kuhn and Martin Raubal. Semantic reference systems. International Journal of Geographical Information Science, 17:405–409, 2003.

8. Benjamin Kuipers. The spatial semantic hierarchy. Artificial Intelligence, 119(1- 2):191–233, 2000.

(10)

9. Benjamin Kuipers and Yung-Tai Byun. A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations.Robotics and Autonomous Systems, 8(1-2):47–63, 1991.

10. Tod S. Levitt and Benjamin Kuipers. Navigation and mapping in large scale space.

AI Magazine, 9(2):25–43, 1988.

11. Paul A. Longley, Michael F. Goodchild, David J. Maguire, and David W. Rhind.

Geographic Information Systems and Science. John Wiley & Sons Ltd., West Sussex, England, 2nd edition, 2005.

12. D. M. Mark. Geographic information science: Critical issues in an emerging cross- disciplinary research domain. Journal of the Urban and Regional Information Sys- tems Association, 12(1):45–54, 2000.

13. Richard C. Meathrel and Antony Galton. A hierarchy of boundary-based shape descriptors. InIJCAI, pages 1359–1364, 2001.

14. N. Nilsson. Principles of Artificial Intelligence. Symbolic Computation. Springer, 1982. NIL n 82:1 1.Ex.

15. S. Ogata, K. Kirimoto, and M. Ide. Time series image analysis of dalian, china by remote sensing. In SICE 2002. Proceedings of the 41st SICE Annual Conference, volume 4, pages 2099–2101, August 2002.

16. Melissa Parsons, Martin C. Thoms, and R. H. Norris. Development of a standard- ised approach to river habitat assessment in australia. Environmental Monitoring and Assessment, 98(1):109–130, 2004.

17. F.F. Sabins. Remote Sensing Principles and Interpretation. 2nd edition, 1987.

18. Georgios Sakellariou, Murray Shanahan, and Benjamin Kuipers. Skeletonisation as mobile robot navigation. InProceedings of Towards Autonomous Robotic Systems (TAROS-04), pages 149–155, September 2004.

19. Paulo Santos, Brandon Bennett, and Georgios Sakellariou. Supervaluation seman- tics for an inland water feature ontology. In Leslie Pack Kaelbling and Allessandro Saffiotti, editors, Proceedings of the 19th International Joint Conference on Arti- ficial Intelligence (IJCAI-05), pages 564–569, Edinburgh, 2005. Professional Book Center.

20. M. Shanahan. A logical account of perception incorporating feedback and expec- tation. InKR, 2002.

21. Dennis Shasha, Jason T. L. Wang, and Rosalba Giugno. Algorithmics and applications of tree and graph searching. In PODS ’02: Proceedings of the twenty-first ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, pages 39–52, New York, NY, USA, 2002. ACM Press.

22. Kaleem Siddiqi, Ali Shokoufandeh, Sven J. Dickinson, and Steven W. Zucker.

Shock graphs and shape matching. InICCV, pages 222–229, 1998.

23. J.R. Thomson, M.P. Taylor, K.A. Fryirs, and G.J. Brierley. A geomorphological framework for river characterization and habitat assessment. Aquatic Conserva- tion: Marine and Freshwater Ecosystems, 11(5):373–389, 2001.

24. S. Vidal, E. Bardinet, G. Malandain, S. Damas, and N. Capilla. Object representation and comparison inferred from its medial axis. InICPR ’00: Proceedings of the International Conference on Pattern Recognition, pages 712–715, 2000.