Digitaalinen kuvankäsittely kaukokartoituksessa
Digital Image Processing in Remote Sensing

- Markus Törmä, puh. (90) 451 3896, TKK/Fotogrammetria, Otakaari 1, 02150 Espoo, Internet: Markus.Torma@hut.fi


Research project "Digital Image Processing in Remote Sensing" was started 1986 and the aim of the project is to develop and apply different digital image processing, image analysis and pattern recognition methods to photogrammetry and remote sensing. The area of the project is wide, so the research subjects have been quite diverse. During these years, research subjects like digital orthophoto, digital image measurement, image segmentation, statistical classification, error analysis etc. have been treated.

During the last few years the main target of the research has been neural networks, especially self-organizing neural networks. The aim of this stage is to study the applicability of different self-organizing neural networks to different pattern recognition problems. These problems are like feature extraction and supervised and unsupervised classification. The purpose is to find data processing methods which could perform well without any assumptions or statistical models concerning processed data.

Some publications:

Törmä, Markus: Determination of tree species using ranging scatterometer data. Int. Geoscience & Remote Sensing Symposium Florenz, Italy. IGARSS95, Vol. I-III, pp. 2038-2040. Firenze, 1995.

Törmä, Markus: Neural Network Based Clustering Algorithm. Suomalais-venäläinen kaukokartoitusseminaari (Finnish-Russian Remote Sensing Seminar), Helsinki 29.08.-01.09.1994, Prof. Risto Kuittinen, Editor, Publications of Geodetic Institute, 8 p, Helsinki 1995.

Törmä, Markus: Kohonen Self-organizing Feature Map and Its Use in Clustering. International Archives of Photogrammetry and Remote Sensing, Vol. 30, Part 3/2, (ISPRS Commission III Symposium on Spatial Information from Digital Photogrammetry and Computer Vision), H. Ebner, C. Heipke, K. Eder, Editors, p. 830-835, Munich, 1994.

Törmä, Markus: Comparison Between Three Different Clustering Algorithms, Photogrammetric Journal of Finland, Vol. 13, No. 2, p. 85-95, Espoo, 1993.

Hautakoski, Markku: Area-Based Segmentation. The Photogrammetric Journal of Finland, Vol. 12, 1990, No. 1, pp. 126-132.

Heikkilä, Jan: Estimation of Classifier's Performance with Error Counting, ISPRS Congress, Washington, D.C., 02.-14.08.1992. Int. Archives of Photogrammetry and Remote Sensing, Vol. 29, Part B3 (1992), pp. 325-334, 1992.

Kilpelä, Einari: Comparison of Some Texture Classifiers. Proceedings of the ISPRS Commission VII Symposium on "Global and Environmental Monitoring-Techniques and Impacts", Victoria, Canada, 1990, 7 p.

Törmä, Markus: Introduction to Neural Networks and Their Use in Remote Sensing, The Photogrammetric Journal of Finland, Vol. 13, No. 1, pp. 87-102, 1992.

Heikkilä, J., Laiho, A., Kilpelä, E.: Digital Image Processing in Remote Sensing - Performance Estimation of Classifiers. Proc. of COSPAR-Meeting of the Finnish Space Scientists, pp 32-33, Jyväskylä, Finland, 1991, (in Finnish).

Paluu sivulle: Ajankohtaisia tutkimushankkeita TKK:n fotogrammetrian ja kaukokartoituksen laboratoriossa
Return to the home page of HUT Institute of Photogrammetry and Remote Sensing