A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images

By Lorenzo Bruzzone, Lorenzo Carlin. IEEE Transactions on Geoscience and Remote Sensing, 2006

409 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/7a7cf891db710dda08cdff0b0f60d32fb563889c

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

Texture and Scale in Object-Based Analysis of Subdecimeter Resolution Unmanned Aerial Vehicle (UAV) Imagery (2009, methodology): “In [27], the authors used a hierarchical segmentation as a preprocessing tool for improving the subsequent feature extraction process, which was driven by relationships of objects at multiple scales.”
A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results (2013, methodology): “The OBIA paradigm instead takes the classification decision typically at the level of the single object/region that is more risky from the statistical point of view: potential errors made at this point are thus directly propagated in the subsequent inferential steps.”
Unsupervised Feature Learning for Aerial Scene Classification (2014, background): “[13] L. Bruzzone and L. Carlin, “A multilevel context-based system for classification of very high spatial resolution images,” IEEE Trans.”
Land-cover classification with high-resolution remote sensing images using transferable deep models (2018, background): “However, the rich details of objects emerging in HRRS images, such as the geometrical shape and structural content of objects, bring more challenges to land-cover classification (Bruzzone and Carlin, 2006).”
Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint (2013, background): “Many works have been done for automatically adding a semantic label to an image according to its content, such as satellite image classification based on support vector machine (SVM) [2]–[4] or two-layer sparse coding (TSC) [6], and semantic annotation using latent Dirichlet allocation (LDA) [9].”
An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery (2013, background): “On the one hand, the classification of hyperspectral images is subject to the so-called Hughes phenomenon, or the curse of dimensionality problem, due to the small ratio between the number of training samples and the number of features [2].”
Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation (2011, background): “State of the art as it is, modern machine learning algorithms (e.g., support vector machine (SVM), boosting, etc.) [3], [4] are incapable of scaling up to thousands of categories as they require a sophisticated learned model for each category.”
Evaluation of Morphological Texture Features for Mangrove Forest Mapping and Species Discrimination Using Multispectral IKONOS Imagery (2009, methodology): “In experiments, all the feature sets are classified using SVM with the radial basis function due to its effectiveness in many classification problems [10].”
Scene classification using multi-scale deeply described visual words (2016, background): “Recently, intensive studies have been conducted in remote-sensing image classi ﬁ cation and interpretation (Bellens et al. 2008; Blaschke 2010; Bruzzone and Carlin 2006; Shackelford and Davis 2003).”
A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification (2016, background): “The obvious limitations of these approaches are the fixed regular shape and choice of the analysis window size [21].”
A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification (2009, background): “In the literature, shadow is generally dealt with as an additional class (Benediktsson et al., 2005; Bruzzone and Carlin, 2006 ).”
Bag of Lines (BoL) for Improved Aerial Scene Representation (2015, background): “Earlier studies often focused on extracting and classifying features associated with a single pixel or a group of homogeneous pixels (often referred to as objects) [1].”
Batch-Mode Active-Learning Methods for the Interactive Classification of Remote Sensing Images (2011, methodology): “[38] for more details on this data set.”
Semisupervised Classification of Remote Sensing Images With Active Queries (2012, methodology): “In [23], the concept of hierarchical segments was used to retrieve features at different scales for supervised classification.”
Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory (2009, background): “Bruzzone and Carlin [3] proposed a pixel-based system to classify VHR satellite images.”
A review on particle swarm optimization algorithm and its variants to clustering high-dimensional data (2013, background): “Yang and Du (2011) proposed a particle swarm optimization (PSO)-based dimensionality reduction approach to improve support vector machine (SVM)-based classification for high-resolution hyperspectral imagery (Bruzzone and Carlin 2006).”