A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES
An automatic classification approach is performed to classify major crop types cultivated in Karacabey Plain, Bursa, through multi-temporal Kompsat-2 and Envisat ASAR data. First, the single-date pancromatic and multispectral Kompsat-2 images are fused with an appropriate image fusion method and 1m...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Turkish Air Force Academy
2013-01-01
|
| Series: | Havacılık ve Uzay Teknolojileri Dergisi |
| Subjects: | |
| Online Access: | http://www.jast.hho.edu.tr/JAST/index.php/JAST/article/view/226/214 |
| _version_ | 1797922270800248832 |
|---|---|
| author | Aslı Özdarıcı Ok Zuhal Akyürek |
| author_facet | Aslı Özdarıcı Ok Zuhal Akyürek |
| author_sort | Aslı Özdarıcı Ok |
| collection | DOAJ |
| description | An automatic classification approach is performed to classify major crop types cultivated in Karacabey Plain, Bursa, through multi-temporal Kompsat-2 and Envisat ASAR data. First, the single-date pancromatic and multispectral Kompsat-2 images are fused with an appropriate image fusion method and 1m colour Kompsat-2 images are generated. Next, different parameter combinations are applied on the fused images in spatial and colour space to find out the optimum segmentation results. The optimum segments are then evaluated using multiple evaluation criteria. Two different classification approaches, pixel-based and segment-based, are tested in this study. First, Image classification are performed on the multispectral Kompsat-2 images. Then the Kompsat-2 images (4m) are classified with Envisat ASAR data. In this way contribution of the Envisat ASAR images to the classification accuracy are tested. Next, distance maps are produced for each thematic map to combine the information of multi-temporal images.The produced thematic maps are evaluated based on pixel-based and segment-based manner using confusion matrices. Results indicate that Envisat ASAR data improve the accuracy of thematic maps. The highest accuracies are obtained for the combined thematic maps of June-August and June-July-August (%88.71 overall accuracy and 0.86 kappa) computed for the segment-based approach. |
| first_indexed | 2024-04-10T14:28:48Z |
| format | Article |
| id | doaj.art-b8250766411145c0951b22cfb36965ef |
| institution | Directory Open Access Journal |
| issn | 1304-0448 1304-0448 |
| language | English |
| last_indexed | 2024-04-10T14:28:48Z |
| publishDate | 2013-01-01 |
| publisher | Turkish Air Force Academy |
| record_format | Article |
| series | Havacılık ve Uzay Teknolojileri Dergisi |
| spelling | doaj.art-b8250766411145c0951b22cfb36965ef2023-02-15T16:08:57ZengTurkish Air Force AcademyHavacılık ve Uzay Teknolojileri Dergisi1304-04481304-04482013-01-01613143A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGESAslı Özdarıcı Ok0Zuhal Akyürek1VAN YÜZÜNCÜ YIL UNIVERSITYMiddle East Technical UniversityAn automatic classification approach is performed to classify major crop types cultivated in Karacabey Plain, Bursa, through multi-temporal Kompsat-2 and Envisat ASAR data. First, the single-date pancromatic and multispectral Kompsat-2 images are fused with an appropriate image fusion method and 1m colour Kompsat-2 images are generated. Next, different parameter combinations are applied on the fused images in spatial and colour space to find out the optimum segmentation results. The optimum segments are then evaluated using multiple evaluation criteria. Two different classification approaches, pixel-based and segment-based, are tested in this study. First, Image classification are performed on the multispectral Kompsat-2 images. Then the Kompsat-2 images (4m) are classified with Envisat ASAR data. In this way contribution of the Envisat ASAR images to the classification accuracy are tested. Next, distance maps are produced for each thematic map to combine the information of multi-temporal images.The produced thematic maps are evaluated based on pixel-based and segment-based manner using confusion matrices. Results indicate that Envisat ASAR data improve the accuracy of thematic maps. The highest accuracies are obtained for the combined thematic maps of June-August and June-July-August (%88.71 overall accuracy and 0.86 kappa) computed for the segment-based approach.http://www.jast.hho.edu.tr/JAST/index.php/JAST/article/view/226/214AgricultureMulti-Temporal Image ClassificationSegment-Based ApproachKompsat-2Envisat ASAR |
| spellingShingle | Aslı Özdarıcı Ok Zuhal Akyürek A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES Havacılık ve Uzay Teknolojileri Dergisi Agriculture Multi-Temporal Image Classification Segment-Based Approach Kompsat-2 Envisat ASAR |
| title | A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES |
| title_full | A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES |
| title_fullStr | A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES |
| title_full_unstemmed | A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES |
| title_short | A SEGMENT-BASED APPROACH TO CLASSIFY CROP TYPES IN AGRICULTURAL LANDS BY USING MULTI-TEMPORAL OPTICAL AND MICROWAVE IMAGES |
| title_sort | segment based approach to classify crop types in agricultural lands by using multi temporal optical and microwave images |
| topic | Agriculture Multi-Temporal Image Classification Segment-Based Approach Kompsat-2 Envisat ASAR |
| url | http://www.jast.hho.edu.tr/JAST/index.php/JAST/article/view/226/214 |
| work_keys_str_mv | AT aslıozdarıcıok asegmentbasedapproachtoclassifycroptypesinagriculturallandsbyusingmultitemporalopticalandmicrowaveimages AT zuhalakyurek asegmentbasedapproachtoclassifycroptypesinagriculturallandsbyusingmultitemporalopticalandmicrowaveimages AT aslıozdarıcıok segmentbasedapproachtoclassifycroptypesinagriculturallandsbyusingmultitemporalopticalandmicrowaveimages AT zuhalakyurek segmentbasedapproachtoclassifycroptypesinagriculturallandsbyusingmultitemporalopticalandmicrowaveimages |