Classification and feature extraction for remote sensing images from urban areas based on morphological transformations

By Jon Atli Benediktsson, Martino Pesaresi, Kolbeinn Amason. IEEE Transactions on Geoscience and Remote Sensing, 2003

821 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ed4f21d6fd4ea0cd2decba6f126cf05e9d7c1326

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 Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Hyperspectral Image Classification With Deep Feature Fusion Network (2018, methodology): “[10], [11] utilize multiple morphological operations to construct spectral–spatial features of HSIs.”
Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations (2005, methodology): “Neural-network-based approaches were then used for the classification of the resulting morphological features [21], [22].”
Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery (2006, methodology): “High spatial resolution imagery initially thrives on the application of urban-related feature extraction has been used (Jensen and Cowen, 1999; Benediktsson et al., 2003; Herold et al., 2003a), but there has not been as much work in detailed vegetation mapping using high spatial resolution imagery.”
A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification (2009, background): “Possible practical applications may be found in urban planning (Shackelford & Davis, 2003; Benediktsson et al., 2003 ), but also for crisis management or as support for civil protection activities (Pagot & Martino Pesaresi, 2008; Chini et al., 2009; Chini et al., 2008a).”
A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles (2015, background): “In [19], in order to reduce the dimensionality of data and address”
Learning multiscale and deep representations for classifying remotely sensed imagery (2016, methodology): “Rather than defining a crisp neighbor set for every pixel, morphological filters (Benediktsson et al., 2003) were used to adaptively define the neighborhoods of pixels.”
Classification of hyperspectral data from urban areas based on extended morphological profiles (2005, methodology): “In [11], Benediktsson et al. extended the method in [10] and successfully included decision boundary feature extraction to reduce the redundancy in the morphological profile.”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “Handcrafted features have proved effective and can represent a variety of spectral, textural, and geometrical attributes of the images [12], [13].”
Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory (2009, methodology): “We also compare our building-detection method with the well-known derivative morphological profiles (DMP) method [1].”
A comparative study on multivariate mathematical morphology (2007, background): “(≈78% for IRS-1C and ≈95% for IKONOS in [15]).”
Morphological Attribute Profiles for the Analysis of Very High Resolution Images (2010, methodology): “In [8], feature extraction techniques were applied to the DMP in order to reduce the dimensionality of the features considered by a neural network classifier.”
Classification of the wildland-urban interface: A comparison of pixel- and object-based classifications using high-resolution aerial photography (2008, methodology): “As we did here, most researchers use standard error matrices (Congalton & Green, 1999; Foody, 2002) to evaluate the accuracy of object-based remotely sensed map products (e.g., Bauer & Steinnocher, 2001; Herold et al., 2003; Kettig & Landgrebe, 1976).”
Recent Advances in Techniques for Hyperspectral Image Processing (2009, methodology): “In previous work, morphological processing has been used to extract information about the size, shape and the orientation of structures in single-band remote sensing images (Benediktsson et al., 2003).”
Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles (2008, methodology): “In this sense, the MP has been proposed as an alternative way to use spatial information [1], [7].”
An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery (2013, methodology): “However, it should be recognized that although various spatial features are currently available for high-resolution image processing, such as morphological features [6]–[10], [12], structural feature set [29], PSI [13], wavelet-based texture [30], object-based features [32], and GLCM [4], [33], it i”