کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
4943251 | 1437624 | 2017 | 20 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
پیش نمایش صفحه اول مقاله
![عکس صفحه اول مقاله: River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation](/preview/png/4943251.png)
چکیده انگلیسی
This publication presents a computer method allowing river channels to be segmented based on SAR polarimetric images. Solutions have been proposed which are based on a morphological approach using the watershed segmentation and combining regions by maximising the average contrast. The image processing methods were developed so that their computational complexity is as low as possible, which is of particular importance in analysing high resolution SAR/polarimetric SAR images, where it has a measurable impact on the total segmentation time. What is more, compared to the existing solutions known from the literature review: (1) in the proposed approach, there is no need to execute further steps necessary to eliminate objects (i.e. background components) located outside the river channel from the image as a result of the segmentation carried out, (2) there is no need to sample the entire image and carry out a pixel-wise classification to prepare the segmentation process. If the steps listed in items (1) - (2) are performed, they can, unfortunately, extend the segmentation time. The experiments completed on images acquired from the ALOS PALSAR satellite for different regions of the world have shown a high quality of the segmentations carried out and a high computational efficiency compared to state-of-the art methods. Consequently, the proposed method can be used as a useful tool for monitoring changes in river courses and adopted in expert and intelligent systems used for analysing remote sensing data.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Expert Systems with Applications - Volume 82, 1 October 2017, Pages 196-215
Journal: Expert Systems with Applications - Volume 82, 1 October 2017, Pages 196-215
نویسندگان
Marcin Ciecholewski,