Segmentation and classification of hyperspectral images using watershed transformation

By Yuliya Tarabalka, Jocelyn Chanussot, Jon Atli Benediktsson. Pattern Recognition, 2010

589 citations recorded by the source corpus.

Subfields: Atmospheric Science, Biomedical Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/26cbdee3e90d700748c5cacad1b8f5be9ff83492

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 Biomedical Engineering

In Media Technology

Citations in the corpus

Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, unknown): “A hyperspectral image is first segmented into different regions based on the homogeneity of either intensity or texture [27] so that all the pixels within the same region can be considered as a spatial neighborhood.”
HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images (2018, background): “In recent years, the hyperspectral image begins to be applied to various computer vision tasks, such as image segmentation, face recognition, and object tracking [31, 28, 33].”
Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “Hyperspectral imaging has been recently applied in many computer vision tasks, including the tracking [19], face recognition[20] and segmentation[28].”
Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, unknown): “Various methods [27]–[29] propose, first, segmenting the hyperspectral image and, then, aggregating the spectrum-wise features for each segmented region to enforce local consistence.”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, methodology): “Another one is the strategy adopted in [90], which combines the output of a pixel-wise SVM classifier with the morphological watershed transformation [139] in order to provide a more spatially homogeneous classification.”
Semisupervised Classification of Remote Sensing Images With Active Queries (2012, methodology): “A recent approach considers the use of a supervised classifier to initialize the markers of a segmentation algorithm [7].”
CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification (2020, unknown): “Besides, the spatial structures of HSIs have also been explored to boost the spectral–spatial feature learning, such as graph construction [17], [18], superpixel segmentation [19], and morphological segmentation [20], [21].”
Remote Sensing Image Retrieval With Global Morphological Texture Descriptors (2014, methodology): “cessful and widely used methods for remote sensing image classification, while the morphological remote sensing application extent also includes simplification [35], texture analysis [36], and segmentation [37].”
SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images (2010, background): “Approaches for deﬁning a one-band gradient from the B-band image are analyzed in [15].”
Hyperspectral Super-Resolution by Coupled Spectral Unmixing (2015, unknown): “This capability has proved useful for visual tasks such as tracking [23] and segmentation [22], in applications including face recognition [19], document analysis [18], food inspection [26] and earth observation [6].”