Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery
Remote sensing has great potential as a source of information on tree species. The classification approaches used commonly to extract species information from remotely sensed imagery typically aim to optimize the overall accuracy of species identification, a target which need not satisfy the require...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Published: |
2005
|
| _version_ | 1797097850979483648 |
|---|---|
| author | Foody, G Atkinson, P Gething, P Ravenhill, N Kelly, C |
| author_facet | Foody, G Atkinson, P Gething, P Ravenhill, N Kelly, C |
| author_sort | Foody, G |
| collection | OXFORD |
| description | Remote sensing has great potential as a source of information on tree species. The classification approaches used commonly to extract species information from remotely sensed imagery typically aim to optimize the overall accuracy of species identification, a target which need not satisfy the requirements of a particular user. Often users are interested in a specific species or subset of species, and these may not be accurately identified in a conventional classification. Here, a two-phase classification approach was used to map specific species from aerial sensor imagery of an ancient British woodland. Particular attention was focused on the identification of sycamore since this is displacing the native ash and information on its distribution would enhance basic understanding and management activities. The results show that the classification approach can be adapted to focus on a specific species of interest and used to increase classification accuracy significantly. For example, sycamore was classified to a low accuracy when a conventional approach to classification with a neural network was used (46.6-63.6%, depending on perspective), but the adoption of the two-phase approach increased its accuracy significantly (82.3-93.3%). The results demonstrate the ability to map specific class(es) of interest accurately from remotely sensed imagery. The approach used also highlights the ability to tailor an analysis to the specific requirements of the ecological study in hand and is of broad applicability. © 2005 by the Ecological Society of America. |
| first_indexed | 2024-03-07T05:01:11Z |
| format | Journal article |
| id | oxford-uuid:d8562d08-2e2b-4f11-8dce-4fde001308a7 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T05:01:11Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | oxford-uuid:d8562d08-2e2b-4f11-8dce-4fde001308a72022-03-27T08:47:44ZIdentification of specific tree species in ancient semi-natural woodland from digital aerial sensor imageryJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:d8562d08-2e2b-4f11-8dce-4fde001308a7Symplectic Elements at Oxford2005Foody, GAtkinson, PGething, PRavenhill, NKelly, CRemote sensing has great potential as a source of information on tree species. The classification approaches used commonly to extract species information from remotely sensed imagery typically aim to optimize the overall accuracy of species identification, a target which need not satisfy the requirements of a particular user. Often users are interested in a specific species or subset of species, and these may not be accurately identified in a conventional classification. Here, a two-phase classification approach was used to map specific species from aerial sensor imagery of an ancient British woodland. Particular attention was focused on the identification of sycamore since this is displacing the native ash and information on its distribution would enhance basic understanding and management activities. The results show that the classification approach can be adapted to focus on a specific species of interest and used to increase classification accuracy significantly. For example, sycamore was classified to a low accuracy when a conventional approach to classification with a neural network was used (46.6-63.6%, depending on perspective), but the adoption of the two-phase approach increased its accuracy significantly (82.3-93.3%). The results demonstrate the ability to map specific class(es) of interest accurately from remotely sensed imagery. The approach used also highlights the ability to tailor an analysis to the specific requirements of the ecological study in hand and is of broad applicability. © 2005 by the Ecological Society of America. |
| spellingShingle | Foody, G Atkinson, P Gething, P Ravenhill, N Kelly, C Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title | Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title_full | Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title_fullStr | Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title_full_unstemmed | Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title_short | Identification of specific tree species in ancient semi-natural woodland from digital aerial sensor imagery |
| title_sort | identification of specific tree species in ancient semi natural woodland from digital aerial sensor imagery |
| work_keys_str_mv | AT foodyg identificationofspecifictreespeciesinancientseminaturalwoodlandfromdigitalaerialsensorimagery AT atkinsonp identificationofspecifictreespeciesinancientseminaturalwoodlandfromdigitalaerialsensorimagery AT gethingp identificationofspecifictreespeciesinancientseminaturalwoodlandfromdigitalaerialsensorimagery AT ravenhilln identificationofspecifictreespeciesinancientseminaturalwoodlandfromdigitalaerialsensorimagery AT kellyc identificationofspecifictreespeciesinancientseminaturalwoodlandfromdigitalaerialsensorimagery |