A Theoretical Framework for Unsupervised Change Detection Based on Change Vector Analysis in the Polar Domain

By Francesca Bovolo, Lorenzo Bruzzone. IEEE Transactions on Geoscience and Remote Sensing, 2007

643 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/8a19b5623717dd9f5a0ffd2007b454474553c997

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 Ecology

In Media Technology

Citations in the corpus

Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery (2018, background): “Bovolo and Bruzzone [7] propose a formal deﬁnition and a theoretical study to of CVA in the polar domain.”
Self-Supervised Representation Learning for Remote Sensing Image Change Detection Based on Temporal Prediction (2020, background): “It obtains magnitude and direction of changed information by subtraction of corresponding spectral bands [14].”
Unsupervised Deep Change Vector Analysis for Multiple-Change Detection in VHR Images (2019, background): “In addition, a direction variable can be obtained from the multispectral difference image which is used to distinguish different kinds of change [12]–[14].”
Kernel-Based Framework for Multitemporal and Multisource Remote Sensing Data Classification and Change Detection (2008, methodology): “In remote sensing, change identification traditionally subtracts the subsequent images and then applies a threshold that is tuned either heuristically or under other more sophisticated criteria [5], [20], [21], [23].”
A Review of Change Detection in Multitemporal Hyperspectral Images: Current Techniques, Applications, and Challenges (2019, methodology): “For generating the binary change index images, we considered the ED magnitude (ED-Mag) [31], IR-MAD magnitude (IRMAD-Mag) [59], and SAM similarity image (SAM-SI) [77].”
A Novel Approach to Unsupervised Change Detection Based on a Semisupervised SVM and a Similarity Measure (2008, methodology): “Usually, the desired change-detection map is obtained by thresholding the magnitude of SCVs [3], [8], [9].”
Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection (2016, methodology): “Among them, image differencing (subtraction rule) is a robust and efficient method for detecting changes, and Change Vector Analysis (CVA) [8] represents its conceptual extension with an integrated theoretical framework, therein providing good performance.”
A critical synthesis of remotely sensed optical image change detection techniques (2015, methodology): “361 More recently, there has been some interesting research describing how n dimensional change directional 362 information can be conveyed in a CVA.”
Multitask learning for large-scale semantic change detection (2018, positive): “A well established family of change detection methods is change vector analysis (CVA), considering the multispectral difference vector in polar or hyperspherical coordinates and attempting to characterise the changes based on the associated vectors at each pixel (Lambin and Strahlers, 1994; Bovolo a”
A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images (2018, methodology): “For homogeneous images, it is easy to derive a difference map by the direct computation of pixelwise difference [18]–[20].”
A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images (2012, methodology): “Following an approach similar to the one in [17], the properties of the two features defined according to (3) and (6) can”
A Novel Framework for the Design of Change-Detection Systems for Very-High-Resolution Remote Sensing Images (2013, methodology): “Concerning radiometric corrections, we simply normalized the images by subtracting from each spectral channel of the two images its mean value [14], [27].”
Self-Supervised Change Detection in Multiview Remote Sensing Images (2021, background): “In the past decades, many researchers developed techniques that directly compare pixels values of multi-temporal images to get the change maps from coarse resolution images [1]– [3], assuming that the spectral information of each pixel can completely characterize various underlying land-cover types.”