Field-based sub-boundary extraction from remote sensing imagery using perceptual grouping

详细信息    查看全文

• 作者：Mustafa Turker^a ; ^{mturker@hacettepe.edu.tr} ; Emre Hamit Kok^b ; ^{emrehkok@gmail.com}
• 关键词：Field-based ; Boundary detection ; Perceptual-grouping ; Agriculture ; SPOT imagery
• 刊名：ISPRS Journal of Photogrammetry and Remote Sensing
• 出版年：2013
• 出版时间：May, 2013
• 年：2013
• 卷：79
• 期：Complete
• 页码：106-121
• 全文大小：3228 K

文摘

This study presents an approach for the automatic extraction of dynamic sub-boundaries within existing agricultural fields from remote sensing imagery using perceptual grouping. We define sub-boundaries as boundaries, where a change in crop type takes a place within the fixed geometry of an agricultural field. To perform field-based processing and analysis operations, the field boundary data and satellite imagery are integrated. The edge pixels are detected using the Canny edge detector. The edge pixels are then analyzed to find the connected edge chains and from these chains the line segments are detected using the graph-based vectorization method. The spurious line segments are eliminated through a line simplification process. The perceptual grouping of the line segments is employed for detecting sub-boundaries and constructing sub-fields within the fixed geometry of agricultural fields. Our strategy for perceptual grouping involves the Gestalt laws of proximity, continuation, symmetry and closure. The processing and analysis operations are carried out on field-by-field basis. For each field, the geometries of sub-boundaries are determined through analyzing the line segments that fall within the field and the extracted sub-boundaries are integrated with the fixed geometry of the field.

The experimental validation of the approach was carried out on the SPOT4 multispectral (XS) and SPOT5 XS images that cover an agricultural area located in the north-west section of Turkey. The overall matching percentages between the reference data and the automatically extracted sub-boundaries were computed to be 82.6 % and 76.2 % for the SPOT5 and SPOT4 images respectively. The higher matching percentage of the SPOT5 image is due to the fact that some of the boundaries present in the SPOT5 image were not detected in the coarser resolution SPOT4 image. For the SPOT5 image, of the total 292 fields processed, 177 showed a total agreement between the detected segments and the reference data. For the SPOT4 image, 154 fields showed a total agreement between the detected segments and the reference data.