Topographical contextual grouping
Aspects described herein provide a computer-implemented method and system for grouping topographic data based on the context of said data without the operator needing to make any assumptions. For each vector feature, its context, that is, information about the adjacent features, is incorporated in to the associated attribution data. In doing this, the system is able to characterise all of the vector features in a geographical area based on its context, from which patterns emerge. These patterns indicate features that have similar contexts, enabling the system to group the vector features according to their contexts based on their characteristics and attributes. Conversely, features that are anomalous within the region, that is, they do not fit the pattern of the surrounding features, are also identified. This is particularly important for identifying and resolving errors in the underlying topographic data.
1. A computer implemented method comprising:
obtaining topographic data relating to a geographic area, the topographic data comprising a plurality of features having one or more attributes associated therewith;
generating adjacency data for the plurality of features, wherein the adjacency data of a feature comprises information relating to at least one attribute associated with at least one spatially adjacent feature;
identifying at least one group of features in dependence on the adjacency data, wherein the adjacency data of a feature is encoded based on the attributes associated with the at least one spatially adjacent feature; and
identifying one or more anomalous features having adjacency data different from the adjacency data of the at least one group based at least in part on the encoded adjacency data, wherein features having encoded adjacency data below a predefined level of similarity to the at least one group are identified as anomalous.
2. A method according to claim 1 , wherein the identifying at least one group comprises grouping features based at least in part on the similarity of the encoded adjacency data, wherein features having encoded adjacency data above a predefined level of similarity are grouped together.
3. A method according to claim 1 , wherein the encoding the adjacency data comprises generating a point location in an n-dimensional attribute space defined by a number, n, of attributes associated with the plurality of features.
4. A method according to claim 1 , wherein the identifying at least one group further comprises clustering the encoded adjacency data.
5. A method according to claim 4 , wherein identifying one or more anomalous features comprises identifying one or more features at a predefined distance from the at least one group identified from the clustered adjacency data.
6. A method according to claim 1 , wherein the one or more attributes comprise one or more of: type, size, shape, characteristic and manifestation.
7. A method according to claim 1 , further comprising:
determining at least one new attribute based on the at least one group; and
assigning the at least one new attribute to the features of the at least one group.
8. A method according to claim 1 , further comprising:
identifying an error in the topographic data based on the one or more anomalous features; and
modifying the topographic data to correct the identified error.
9. A method according to claim 1 , further comprising:
determining at least one new attribute based on the one or more anomalous features; and
assigning the at least one new attribute to the one or more anomalous features.
10. A method according to claim 1 , wherein the adjacency data of the plurality of features further comprises information relating to at least one attribute associated with a feature that is spatially adjacent to the at least one spatially adjacent feature.
11. A method according to claim 1 , further comprising:
generating a map image comprising a visual representation of the at least one group and/or one or more anomalous features.
12. A system comprising:
a processor; and
a computer readable medium storing one or more instruction(s) arranged such that when executed the processor is caused to:
obtain topographic data relating to a geographic area, the topographic data comprising a plurality of features having one or more attributes associated therewith;
generate adjacency data for the plurality of features, wherein the adjacency data of a feature comprises information relating to at least one attribute associated with at least one spatially adjacent feature;
identify at least one group of features in dependence on the adjacency data wherein the adjacency data of a feature is encoded based on the attributes associated with the at least one spatially adjacent feature; and
identify one or more anomalous features having adjacency data different from the adjacency data of the at least one group based at least in part on the encoded adjacency data, wherein features having encoded adjacency data below a predefined level of similarity to the at least one group are identified as anomalous.
13. A system according to claim 12 , wherein the processor is further caused to generate a map image comprising a visual representation of the at least one group and/or one or more anomalous features.
14. A system according to claim 13 , wherein the processor is caused to output the map image to a display device.
15. A system according to claim 12 , wherein the processor is further caused to:
identify an error in the topographic data based on the one or more anomalous features; and
modify the topographic data to correct the identified error.
16. A computer implemented method of identifying anomalies in a topographic dataset, the method comprising:
obtaining topographic data relating to a geographic area, the topographic data comprising a plurality of features having one or more attributes associated therewith;
generating adjacency data for the plurality of features, wherein the adjacency data of a feature comprises information relating to at least one attribute associated with at least one spatially adjacent feature;
identifying at least one group of features in dependence on the adjacency data, wherein the adjacency data of a feature is encoded based on the attributes associated with the at least one spatially adjacent feature, wherein encoding the adjacency data comprises generating a point location in an n-dimensional attribute space defined by a number, n, of attributes associated with the plurality of features; and
identifying one or more anomalous features having adjacency data different from the adjacency data of the at least one group based at least in part on the encoded adjacency data, wherein features having a distance in attribute space above a predetermined number of attributes between said features and the at least one group are identified as anomalous.
17. A system comprising:
a processor; and
a computer readable medium storing one or more instruction(s) arranged such that when executed the processor is caused to:
obtain topographic data relating to a geographic area, the topographic data comprising a plurality of features having one or more attributes associated therewith;
generate adjacency data for the plurality of features, wherein the adjacency data of a feature comprises information relating to at least one attribute associated with at least one spatially adjacent feature;
identify at least one group of features in dependence on the adjacency data, wherein the adjacency data of a feature is encoded based on the attributes associated with the at least one spatially adjacent feature, wherein the adjacency data is encoded by generating a point location in an n-dimensional attribute space defined by a number, n, of attributes associated with the plurality of features; and
identify one or more anomalous features having adjacency data different from the adjacency data of the at least one group based at least in part on the encoded adjacency data, wherein features having a distance in attribute space above a predetermined number of attributes between said features and the at least one group are identified as anomalous.