An approach for correcting inhomogeneous atmospheric effects in remote sensing images
Two contextual-based approaches for correcting first order atmospheric effects due to atmospheric inhomogeneity and adjacency effect are described. The first method is a modification of the restoration method for the adjacency effect suggested by Richter. The second method is an adaptation of Stenbe...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Taylor & Francis LTD
2004
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/2185/1/IJRS_Atmos_15276038.pdf http://eprints.utm.my/2185/ http://dx.doi.org/10.1080/01431160410001712971 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1845470632715747328 |
|---|---|
| author | Hashim, Mazlan Watson, A. I. Thomas, M. |
| author_facet | Hashim, Mazlan Watson, A. I. Thomas, M. |
| author_sort | Hashim, Mazlan |
| building | UTM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Malaysia |
| content_source | UTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Two contextual-based approaches for correcting first order atmospheric effects due to atmospheric inhomogeneity and adjacency effect are described. The first method is a modification of the restoration method for the adjacency effect suggested by Richter. The second method is an adaptation of Stenberg’s rolling ball algorithm using the mathematical morphology transformation. Evaluation of the proposed method was carried out by noting classification accuracy on the basis that an increase in classification accuracy reflects in improved image quality. Results show that the average accuracy of classification of a scene from Malaysia, with 13 ground truth classes was as follows: (a) uncorrected—86%, (b) adjacency correction—86%, and (c) rolling ball correction—89%. It is clear from the results that the rolling ball method of correction does yield an increase in accuracy although not as substantial as in this case, and there is no reason to doubt that this method could be used to correct a wide variety of images that are affected by inhomogeneity of the atmosphere. |
| format | Article |
| id | my.utm.eprints-2185 |
| institution | Universiti Teknologi Malaysia |
| language | en |
| publishDate | 2004 |
| publisher | Taylor & Francis LTD |
| record_format | eprints |
| spelling | my.utm.eprints-21852017-05-14T07:16:34Z http://eprints.utm.my/2185/ An approach for correcting inhomogeneous atmospheric effects in remote sensing images Hashim, Mazlan Watson, A. I. Thomas, M. Q Science (General) QC Physics Two contextual-based approaches for correcting first order atmospheric effects due to atmospheric inhomogeneity and adjacency effect are described. The first method is a modification of the restoration method for the adjacency effect suggested by Richter. The second method is an adaptation of Stenberg’s rolling ball algorithm using the mathematical morphology transformation. Evaluation of the proposed method was carried out by noting classification accuracy on the basis that an increase in classification accuracy reflects in improved image quality. Results show that the average accuracy of classification of a scene from Malaysia, with 13 ground truth classes was as follows: (a) uncorrected—86%, (b) adjacency correction—86%, and (c) rolling ball correction—89%. It is clear from the results that the rolling ball method of correction does yield an increase in accuracy although not as substantial as in this case, and there is no reason to doubt that this method could be used to correct a wide variety of images that are affected by inhomogeneity of the atmosphere. Taylor & Francis LTD 2004-11-20 Article PeerReviewed application/pdf en http://eprints.utm.my/2185/1/IJRS_Atmos_15276038.pdf Hashim, Mazlan and Watson, A. I. and Thomas, M. (2004) An approach for correcting inhomogeneous atmospheric effects in remote sensing images. International Journal of remote sensing, 25 (22). pp. 5131-5141. ISSN 01431161 http://dx.doi.org/10.1080/01431160410001712971 10.1080/01431160410001712971 |
| spellingShingle | Q Science (General) QC Physics Hashim, Mazlan Watson, A. I. Thomas, M. An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title | An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title_full | An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title_fullStr | An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title_full_unstemmed | An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title_short | An approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| title_sort | approach for correcting inhomogeneous atmospheric effects in remote sensing images |
| topic | Q Science (General) QC Physics |
| url | http://eprints.utm.my/2185/1/IJRS_Atmos_15276038.pdf http://eprints.utm.my/2185/ http://dx.doi.org/10.1080/01431160410001712971 |
| url_provider | http://eprints.utm.my/ |