Results 31 to 40 of about 417 (152)

SGML: A Symmetric Graph Metric Learning Framework for Efficient Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
Recently, the semi-supervised graph convolutional network (SSGCN) has been verified effective for hyperspectral image (HSI) classification. However, constrained by the limited training data and spectral uncertainty, the classification performance is ...
Yunsong Li, Bobo Xi, Jiaojiao Li, Rui Song, Yuchao Xiao, Jocelyn Chanussot   +5 more
doaj   +1 more source

Efficient Multiscale Object-based Superpixel Framework

Journal of the Brazilian Computer Society
Superpixel segmentation can be used as an intermediary step in many applications, often to improve object delineation and reduce computer workload. However, classical methods do not incorporate information about the desired object. Deep-learning-based approaches consider object information, but their delineation performance depends on data annotation ...
Felipe C. Belém, Benjamin Perret, Jean Cousty, Silvio J. F. Guimarães, Alexandre X. Falcão   +4 more
openaire   +2 more sources

Multiscale Adjacent Superpixel-Based Extended Multi-Attribute Profiles Embedded Multiple Kernel Learning Method for Hyperspectral Classification

Remote Sensing, 2020
In this paper, superpixel features and extended multi-attribute profiles (EMAPs) are embedded in a multiple kernel learning framework to simultaneously exploit the local and multiscale information in both spatial and spectral dimensions for hyperspectral
Lei Pan, Chengxun He, Yang Xiang, Le Sun
doaj   +1 more source

Multiscale Pixel-Level and Superpixel-Level Method for Hyperspectral Image Classification: Adaptive Attention and Parallel Multi-Hop Graph Convolution

Remote Sensing, 2023
Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have led to promising advancements in hyperspectral image (HSI) classification; however, traditional CNNs with fixed square convolution kernels are insufficiently flexible to ...
Junru Yin, Xuan Liu, Ruixia Hou, Qiqiang Chen, Wei Huang, Aiguang Li, Peng Wang   +6 more
doaj   +1 more source

Adjacent Superpixel-Based Multiscale Spatial-Spectral Kernel for Hyperspectral Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
The kernel-based spatial-spectral approach has been widely used for hyperspectral image (HSI) classification in recent years, where composite kernel (CK) and spatial-spectral kernel (SSK) are the most representative methods. Unlike CK, SSK measures the similarity of two clusters in kernel space to capture the hidden manifold in HSI, which has proven to
Le Sun 0002, Chenyang Ma, Yunjie Chen, Hiuk Jae Shim, Zebin Wu 0001, Byeungwoo Jeon   +5 more
openaire   +1 more source

Retinal Vessel Segmentation: A Comprehensive Review From Classical Methods to Deep Learning Advances (1982–2025)

Advanced Intelligent Systems, Volume 8, Issue 7, July 2026.
Four decades of retinal vessel segmentation research (1982–2025) are synthesized, spanning classical image processing, machine learning, and deep learning paradigms. A meta‐analysis of 428 studies establishes a unified taxonomy and highlights performance trends, generalization capabilities, and clinical relevance.
Avinash Bansal, Jan Kubíček, Jana Bahrová, Alice Varyšová, Martin Augustýnek, Marek Penhaker, Juraj Timkovič   +6 more
wiley   +1 more source

Building Extraction from UAV Images Jointly Using 6D-SLIC and Multiscale Siamese Convolutional Networks

Remote Sensing, 2019
Automatic building extraction using a single data type, either 2D remotely-sensed images or light detection and ranging 3D point clouds, remains insufficient to accurately delineate building outlines for automatic mapping, despite active research in this
Haiqing He, Junchao Zhou, Min Chen, Ting Chen, Dajun Li, Penggen Cheng   +5 more
doaj   +1 more source

MSG-SR-Net: A Weakly Supervised Network Integrating Multiscale Generation and Superpixel Refinement for Building Extraction From High-Resolution Remotely Sensed Imageries

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
Weakly supervised semantic segmentation (WSSS) methods based on image-level labels can relieve the tedious pixel-level annotation burden, and these methods are mainly based on class activation maps (CAMs).
Xin Yan, Li Shen, Jicheng Wang, Xu Deng, Zhilin Li   +4 more
doaj   +1 more source

A Bridge Transformer Network With Deep Graph Convolution for Hyperspectral Image Classification

CAAI Transactions on Intelligence Technology, Volume 11, Issue 2, Page 464-482, April 2026.
ABSTRACT Transformers have been widely applied to hyperspectral image classification, leveraging their self‐attention mechanism for powerful global modelling. However, two key challenges remain as follows: excessive memory and computational costs from calculating correlations between all tokens (especially as image size or spectral bands increase) and ...
Yuquan Gan, Siyu Wu, Chang Su, Nan Xiang, Zhijie Xu, Yushan Pan   +5 more
wiley   +1 more source

Stereoscopic Saliency Detection for Rail Surface Defects via Global Low‐Rank Reconstruction and Depth Outlier Fusion

Electronics Letters, Volume 62, Issue 1, January/December 2026.
This letter presents an unsupervised stereoscopic saliency detection method for rail surface defects that integrates global low‐rank reconstruction with depth outlier analysis. A binocular line‐scanning system simultaneously acquires RGB images and depth maps, with a Global Low‐Rank Nonnegative Reconstruction (GLRNNR) algorithm extracting 2D saliency ...
Zhiwen Xiong, Yuanchun Li
wiley   +1 more source