Multilevel Structure Extraction-Based Multi-Sensor Data Fusion
11
TL;DR: A novel multilevel structure extraction method is proposed to fuse multi-sensor data and can produce promising performance with regard to both subjective and objective qualities.
read more
Abstract: Multi-sensor data on the same area provide complementary information, which is helpful for improving the discrimination capability of classifiers. In this work, a novel multilevel structure extraction method is proposed to fuse multi-sensor data. This method is comprised of three steps: First, multilevel structure extraction is constructed by cascading morphological profiles and structure features, and is utilized to extract spatial information from multiple original images. Then, a low-rank model is adopted to integrate the extracted spatial information. Finally, a spectral classifier is employed to calculate class probabilities, and a maximum posteriori estimation model is used to decide the final labels. Experiments tested on three datasets including rural and urban scenes validate that the proposed approach can produce promising performance with regard to both subjective and objective qualities.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
NCGLF<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e636" altimg="si6.svg"><mml:msup><mml:mrow /><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>: Network combining global and local features for fusion of multisource remote sensing data
Bing Tu,Qi Ren,Jun Li,Zhaolou Cao,Yunyun Chen,Antonio Plaza +5 more
TL;DR: This paper proposes NCGLF2, a fusion network combining global and local features from multisource remote sensing data, leveraging CNNs for high-frequency features and transformers for low-frequency information, achieving state-of-the-art performance on three benchmark datasets.
33
A dual-stream high resolution network: Deep fusion of GF-2 and GF-3 data for land cover classification
TL;DR: In this article , a dual-stream deep high-resolution network (DDHRNet) is proposed to integrate SAR and optical data at the feature level in every branch, and a multi-modal squeeze-and-excitation module is also utilized to fuse the features.
33
The Potential of Machine Learning for a More Responsible Sourcing of Critical Raw Materials
Pedram Ghamisi,Kasra Rafiezadeh Shahi,Puhong Duan,Behnood Rasti,Sandra Lorenz,René Booysen,Samuel T. Thiele,Isabel Cecilia Contreras,Moritz Kirsch,Richard Gloaguen +9 more
TL;DR: In this article, the authors assess the relevant recent developments of machine learning for the processing of imaging sensor data and provide a list of available resources, codes and libraries for researchers at different levels, from students to senior researchers, willing to explore novel methodologies on the challenging topics of raw material extraction, classification, and process automatization.
Multi-view Feature Learning and Multi-level Information Fusion for Joint Classification of Hyperspectral and LiDAR Data
Jia Feng,Junping Zhang,Ye Zhang +2 more
TL;DR: This article proposes a novel HSI-LiDAR classification method based on multiview feature learning (MVFL) and multilevel information fusion (MLIF), which consists of aMultiview data representation (MvDR) strategy, a multibranch dual-channel graph convolutional networks (MB-DCGCNs) model, and a progressively high-confidence label assignment (PHCLA) scheme.
8
Vibration-based monitoring and dynamic properties identification via sensor fusion strategy
Mohammad S. Miah,Werner Lienhart +1 more
- 18 Apr 2022
TL;DR: This study focuses into identification & monitoring strategy by deploying a multi-sensor approach on a laboratory scale prototype bridge to deal with various uncertainties (i.e., noise, resolution, measurement error) of the sensors.
References
The Split Bregman Method for L1-Regularized Problems
Tom Goldstein,Stanley Osher +1 more
TL;DR: This paper proposes a “split Bregman” method, which can solve a very broad class of L1-regularized problems, and applies this technique to the Rudin-Osher-Fatemi functional for image denoising and to a compressed sensing problem that arises in magnetic resonance imaging.
Kernel Principal Component Analysis
Bernhard Schölkopf,Alexander J. Smola,Klaus-Robert Müller +2 more
- 08 Oct 1997
TL;DR: A new method for performing a nonlinear form of Principal Component Analysis by the use of integral operator kernel functions is proposed and experimental results on polynomial feature extraction for pattern recognition are presented.
2.6K
Four-component scattering model for polarimetric SAR image decomposition
TL;DR: A four-component scattering model is proposed to decompose polarimetric synthetic aperture radar (SAR) images and the covariance matrix approach is used to deal with the nonreflection symmetric scattering case.
1.2K
Structure extraction from texture via relative total variation
Li Xu,Qiong Yan,Yang Xia,Jiaya Jia +3 more
- 01 Nov 2012
TL;DR: This work proposes new inherent variation and relative total variation measures, which capture the essential difference of these two types of visual forms, and develops an efficient optimization system to extract main structures.
Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning
TL;DR: The proposed approach can provide classification accuracies that are similar or higher than those achieved by other supervised methods for the considered scenes, and indicates that the use of a spatial prior can greatly improve the final results with respect to a case in which only the learned class densities are considered.