[vc_empty_space][vc_empty_space]
An evaluation of the use of integrated spectral and textural features to identify agricultural land cover types in Pangalengan, West Java, Indonesia
Wikantika K.a, Uchida S.b, Yamamoto Y.b
a Department of Geodetic Engineering, Institute of Technology Bandung, Indonesia
b Development Research Division, Japan Intl. Res. Ctr. Agric. Sci., Japan
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]The objective of the study is to evaluate the use of integration of spectral and textural features derived from IKONOS imagery to identify agricultural land cover types in a mountainous case study area in Pangalengan, West Java, Indonesia. The study includes image preprocessing, development of an image quantization method, calculation of textural measures, development of data sets and an accuracy assessment. Image preprocessing focuses on image registration and topographic normalization. Topographic normalization is conducted to minimize the effect of illumination differences on surface reflectance. In this study, two image quantization methods, i.e. image segmentation and averaging filtered were developed. The image segmentation method classifies the image into several segmentations based on a determination of the total number of pixels per class, while the averaging filtered method classifies the image based on the average of the digital number values within a window size. Four textural measures, inverse difference moment, contrast, entropy and energy, were calculated based on the gray level co-occurrence matrix (GLCM). The results indicate that a combination of spectral and textural aspects significantly improves the classification accuracy compared with classification with pure spectral features only. Image segmentation and averaging filtered methods can reveal more effectively spatial forms of agricultural land cover types than using a 256 gray-level scale. The overall accuracy increased 11.33% when using the integration of spectral and multiple textural features of inverse difference moment (5×5) and energy (9×9).[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]IKONOS,Image quantization,Land cover classification[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.6090/jarq.38.137[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]