An Object-Based Method to Integrate Remote Sensing and Geographical Information for Advanced Feature Extraction

以物件為基礎的方法整合地理資訊及遙測影像做土地使用特徵擷取與分類

10.29790/JTGIS.200504.0002

王聖銘(Sheng-Ming Wang)

地理資訊系統 ； 遙測 ； 影像分析 ； 特徵擷取 ； 土地使用分類 ； Geographical Information System ； Remote Sensing ； Image Analysis ； Feature Extraction ； Land use Classification

臺灣地理資訊學刊

2期（2005 / 04 / 01）

11 - 26

英文

本文在呈現利用以物件為基礎的方法整合地理資訊及遙測影像資料做土地使用特徵擷取與分類的研究。本研究的動機在於探討如何整合多樣性的空間資料，並轉化為物件化的知識，作為土地使用特徵擷取與分類的基礎。在本研究中所提出之以物件為基礎分析單元並結合物件內含知識推論的分析方法，比傳統的以像元或網格區域為基礎分析單元的分析方法，更接近真實世界認知與分類方法，並可獲得較好的資訊擷取與分類結果。 本研究依相關分析與設計，建構了實際應用的雛型系統－OMIRGS。並利用兩組不同年份的空間資料做案例分析。由案例分析的結果顯示，利用OMIRGS針對本研究中所設定的九種土地使用特徵擷取及分類的結果，分別有93%及94%的分類準確度。相對於傳統的單純以SMAP關聯性影像分類方法所的到的結果，其結果有顯著的改進。而由相關結果顯示，利用本研究所設計，以物件為基礎分析單元並結合物件內含知識推論的分析方法，能擷取到僅利用傳統的遙測影像分類分析方法所無法得到的分類結果。

This paper presents an object-based method to integrate remote sensing and geographical information systems for advanced feature extraction. The research was motivated by the need to integrate spatial data for feature extraction and the hypothesis that an object-based approach would lead to improved results compared to pixel and kernel-based approaches. A prototype system-OMIRGS, had been designed and implemented in this research. A case study for object land use classification and change detection within an urban-rural area has been carried out. Promising results have been obtained from the case study. The 1988 and 1990 land use maps of the case study area, with 9 classes of land use features; have been generated with an accuracy of 93% and 94%. Significant improvements have been obtained comparing the results with those generated using the SMAP contextual image classification method alone. This research concludes that the method proposed in this research can be used to extract the features, which are very difficult to derive using conventional techniques and remotely sensed data alone. The work contributes to the prioritized research area of the integration of remote sensing and geographic information systems for advanced feature extraction.

1. Aplin, P.,Atkinson, P. M.,Curran, P. J.(1997).Integrating fine spatial resolution satellite sensor imagery and digital vector data for per-field land cover mapping, RSS 97 Observations and Interactions.23rd Annual Conference and Exhibition of the Remote Sensing Society
2. Barnsley, M. J.,Barr, S. L.(1996).Inferring urban land use from satellite sensor images using kernel-bases spatial reclassification.Photogrammetric Engineering and Remote Sensing,62(8),949-958.
3. Cattell, R. G. G.(1993).Object Data Management: Object-Oriented and Extented Relational Database Systems (Reprinted and corrections).Addison-Wesley Publishing Company.
4. Date, C. J.(1990).An Introduction to Database Systems.Addison-Wesley Publishing Company.
5. Ehlers, M.,Edwards, G.,Bedard, Y.(1989).Integration of remote sensing with geographic information systems: a necessary evolution.Photogrammetric Engineering and Remote Sensing,55(11),1619-1627.
6. Estes, J. E.,Star, J. L.,Estes, J. E.,Star, J. L.,McGwire, K. C. (eds.)(1997).Integration of Geographic Information Systems and Remote Sensing.UK:Cambridge University Press.
7. Fung, T,Chan, K.(1994).Spatial composition of spectral classes: a structural approach for image analysis of heterogenenous land-use and land-cover types.Photogrammetric Engineering and Remote Sensing,60(2),173-180.
8. Green, K.,Kempka, D.,Lackey, L.(1994).Using remote sensing to detect and monitor land-cover and land-use change.Photogrammetric Engineering and Remote Sensing,60(3),331-337.
9. Harris, P. M.,Ventura, S. J.(1995).The integration of geographic data with remotely sensed imagery to improve classification in an urban area.Photogrammetric Engineering and Remote Sensing,61(8),993-998.
10. Johnsson, K.(1994).Segment-based land use classification from SPOT satellite data.Photogrammetric Engineering and Remote Sensing,60(1),47-53.
11. Smith, G. M.,Fyller, R. M.,Armable, G.,Costa, C.,Devereux, B. J.(1997).CLEVER mapping: an implementation of a per-parcel classification procedure within an integrated GIS environment, RSS 97 Observations and Interactions.23rd Annual Conference and Exhibition of the Remote Sensing Society
12. Star, J. L.,Estes, J. E.,McGwire, K. C.,Estes, J. E.,Star, J. L.,McGwire, K. C. (eds.)(1997).Integration of Geographic Information Systems and Remote Sensing.UK:Cambridge University Press.
13. Star, J. L.,Estes, J. E.,Star, J. L. (eds.)(1991).Integration of Remote Sensing and Geographic Information Systems.National Center for Geographic Information and Analysis.
14. Wang, F. J.(1993).A knowledge-based vision system for detecting land changes at urban fringes.IEEE Transactions on Geoscience and Remote Sensing,31(1),136-145.
15. Wilkinson, G. G.(1996).A review of current issue in the integration of GIS and remote sensing data.International Journal of Geographical Information System,10(1),85-101.