سامانه پشتیبانی خدمات اطلاعات

  اخبار و اعلانات

 آمار

تعداد نشریات158
تعداد شماره‌ها6,230
تعداد مقالات67,758
تعداد مشاهده مقاله115,125,372
تعداد دریافت فایل اصل مقاله89,893,374
Niazmardi, Saeid. (1398). A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms. , 3(2), 92-98. doi: 10.22059/eoge.2020.285999.1057
Saeid Niazmardi. "A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms". , 3, 2, 1398, 92-98. doi: 10.22059/eoge.2020.285999.1057
Niazmardi, Saeid. (1398). 'A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms', , 3(2), pp. 92-98. doi: 10.22059/eoge.2020.285999.1057
Niazmardi, Saeid. A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms. , 1398; 3(2): 92-98. doi: 10.22059/eoge.2020.285999.1057

A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms

Earth Observation and Geomatics Engineering
دوره 3، شماره 2، اسفند 2019، صفحه 92-98    اصل مقاله (1.09 M)
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22059/eoge.2020.285999.1057
نویسنده
Saeid Niazmardi*
Department of remote sensing engineering, Faculty of civil and surveying engineering, Graduate University of advanced technology, Kerman, Iran
چکیده
Extracting and modeling the spatial information content of very high resolution (VHR) images can dramatically increase the performances of urban area classification. However, extracting spatial features is a highly challenging task. During the years, several spatial feature extraction methods have been proposed, most of which are mainly designed for grayscale images. To use these methods for a multispectral image, usually, a dimensionality reduction step is required. As a result, these methods cannot optimally extract the spatial information contents of different bands of a multispectral image. To address this issue, we proposed the use of the region covariance descriptor (RCD) for spatial feature extraction from VHR images. The RCD features consider the covariance matrix of a local neighborhood of each pixel as the features. These features can model both the spatial information and the spectral relationship between bands. The RCD features lie in a Riemannian manifold, on which the common classification algorithms cannot be applied. To overcome this, we used Riemannian kernel functions. Also, we proposed a multiple kernel learning strategy for combining RCD and spectral features. The proposed strategy was evaluated for classifying a VHR image acquired over the urban area of Tehran, Iran. Furthermore, its obtained results were compared with those of ten other common spatial feature extraction methods. The results showed that the proposed classification strategy using the RCD features yielded at least 5% higher accuracies than the other feature extraction methods.
کلیدواژه‌ها
Covariance descriptors؛ Region covariance descriptors؛ Multiple kernel learning؛ High resolution؛ Urban classification
آمار
تعداد مشاهده مقاله: 231
تعداد دریافت فایل اصل مقاله: 168


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب