Morphological Attribute Profiles for the Analysis of Very High Resolution Images

By M. Dalla Mura, Jon Atli Benediktsson, Björn Waske, Lorenzo Bruzzone. IEEE Transactions on Geoscience and Remote Sensing, 2010

730 citations recorded by the source corpus.

Subfields: Atmospheric Science, Global and Planetary Change, Media Technology

View Paper: https://www.semanticscholar.org/paper/41a0270bdd5b79c58340007f67876b38cf914ae6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Global and Planetary Change

In Media Technology

Citations in the corpus

SVM-Based Fuzzy Decision Trees for Classification of High Spatial Resolution Remote Sensing Images (2012, background): “More recent and effective proposals are the morphological and differential morphological profiles [4]– [7], the structural feature (SF) set suggested in [8], and the pixel shape index [9].”
A Novel Framework for the Design of Change-Detection Systems for Very-High-Resolution Remote Sensing Images (2013, methodology): “Spatial-context information can be modeled by: fixed-shape neighborhood systems for texture information extraction [65], [66], [67], applying Markov Random Fields theory [31], [35] or using morphological filters [32], [68].”
Classification of Hyperspectral Images by Using Extended Morphological Attribute Profiles and Independent Component Analysis (2011, positive): “To avoid this limitation, the use of morphological attribute filters instead of the conventional operators based on the geodesic reconstruction was proposed [5].”
Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods (2013, methodology): “A significant improvement in terms of classification accuracies with respect to the spectral SVM was achieved by applying the EMAP with four different attributes on the image (area and diagonal of the bounding box of connected components, moment of inertia and standard deviation, see [26]).”
Generalized Composite Kernel Framework for Hyperspectral Image Classification (2013, methodology): “3) Finally, the proposed approach models the spatial information using extended multiattribute morphological profiles (MPs) [23], defined as a generalization of the well-known MPs [24], [25] that provide a multilevel characterization of an image created by the sequential application of morphological”
SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH AN ENSEMBLE OF CNNS (2016, background): “Consequently, much of the literature has concentrated on feature extraction from a pixel’s spatial neighborhood [Herold et al., 2003, Dalla Mura et al., 2010, Tokarczyk et al., 2015].”
A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results (2013, methodology): “In particular, the so-called PANTEX image feature [23] derived from anisotropic rotation-invariant grey level co-occurrence matrix (GLCM) textural contrast measurements and the characteristic-saliency-level (CSL) featuremodel [20] based on Differential Morphological Profiles (DMP) [24] and derived m”
Automatic Feature Learning for Spatio-Spectral Image Classification With Sparse SVM (2014, neutral): “logical [16], [17], [21]–[24], Gabor [25], [26], wavelets [27],”
Remote Sensing Image Retrieval With Global Morphological Texture Descriptors (2014, background): “, differential [32], extended [33], attribute based [3], [34]) have become one of the most suc-”
Deep learning for remote sensing image classification: A survey (2018, methodology): “This is because it can significantly improve the performance of the final classifier as empirically proven (Nogueira et al., 2016). We can pretrain a network on the natural image data set first, and then fine-tune the network using a smaller group of labeled aerial images. Specifically, fine-tuning ”
Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas (2016, background): “Currently, hundreds of features are computed (Dalla Mura et al., 2010; Huang and Zhang, 2013), and then the best subset is selected (Gressin et al., 2013; Paget et al., 2015).”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, methodology): “The successful use of RF or SVM, coupled with a feature extraction approach to model a machine learning framework has been demonstrated intensively in the literature [145], [146].”
Graph Convolutional Networks for Hyperspectral Image Classification (2020, background): “feature representations, including attribute profiles (APs) [19] and invariant APs [20], [21].”
Hyperspectral Anomaly Detection With Attribute and Edge-Preserving Filters (2017, methodology): “For a complete description of the morphological attribute filter and its applications in hyperspectral image classification, we refer the reader to [19].”
Tensor Discriminative Locality Alignment for Hyperspectral Image Spectral–Spatial Feature Extraction (2013, background): “, the morphological feature [61], texture feature [62], and polarimetric feature [63], which may further improve the HSI classification performance.”