Balancing exploration and exploitation according to evolutionary states is crucial meta-heuristic search (M-HS) algorithms. Owing its simplicity in theory effectiveness global optimization, gravitational algorithm (GSA) has attracted increasing attention recent years. However, the tradeoff between GSA achieved mainly by adjusting size of an archive, named , which stores those superior agents after fitness sorting each iteration. Since property remains unchanged whole process, emphasizes over...

This study presents a spectral–spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel be classified. Specifically, it has two subnetworks. The spatial subnetwork introduces proposed module exploit rich patch-based contextual information center pixel. spectral correlation over features. extracted and are then fused HSI classification. Experiments conducted on four...

This study presents a deep extraction of localized spectral features and multi-scale spatial convolution (LSMSC) framework for spectral-spatial fusion based classification hyperspectral images (HSIs). First, adjacent bands are grouped on their similarity measurements, where the whole hypercube is partitioned into several sub-cubes, each corresponding to one band group. Then, proposed (LSF) strategy used extract features, which extracted from group using 1D convolutional neural network (CNN)....

Singular spectral analysis (SSA) has recently been successfully applied to feature extraction in hyperspectral image (HSI), including conventional (1-D) SSA domain and 2-D spatial domain. However, there are some drawbacks, such as sensitivity the window size, high computational complexity under a large window, failing extract joint spectral-spatial features. To tackle these issues, this article, we propose superpixelwise adaptive (SpaSSA), that is for exploiting local information of HSI. The...

As an essential reprocessing method, dimensionality reduction (DR) can reduce the data redundancy and improve performance of hyperspectral image (HSI) classification. A novel unsupervised DR framework with feature interpretability, which integrates both band selection (BS) spatial noise is proposed to extract low-dimensional spectral-spatial features HSI. We a new Neighboring Grouping Normalized Matching Filter (NGNMF) for BS, dimension whilst preserve corresponding spectral information. An...

Currently, long-range spectral and spatial dependencies have been widely demonstrated to be essential for hyperspectral image (HSI) classification. Due the transformer superior ability exploit representations, transformer-based methods exhibited enormous potential. However, existing approaches still face two crucial issues that hinder further performance promotion of HSI classification: 1) treating as 1D sequences neglects properties HSI, 2) dependence between information is not fully...

Due to the cubic structure of a hyperspectral image (HSI), how characterize its spectral and spatial properties in three dimensions is challenging. Conventional spectral-spatial methods usually extract information separately, ignoring their intrinsic correlations. Recently, some 3D feature extraction are developed for features simultaneously, although they rely on local spatial-spectral regions thus ignore global similarity consistency. Meanwhile, these contain huge model parameters which...

Extracting buildings from very high resolution (VHR) images has attracted much attention but is still challenging due to their large varieties in appearance and scale. Convolutional neural networks (CNNs) have shown effective superior performance automatically learning high-level discriminative features extracting buildings. However, the fixed receptive fields make conventional CNNs insufficient tolerate scale changes. Multiscale CNN (MCNN) a promising structure meet this challenge....

As hyperspectral imagery (HSI) contains rich spectral and spatial information, a novel principal component analysis (PCA) segmented-PCA (SPCA)-based multiscale 2-D-singular spectrum (2-D-SSA) fusion method is proposed for joint spectral–spatial HSI feature extraction classification. Considering the overall spectra adjacent band correlations of objects, PCA SPCA methods are utilized first dimension reduction, respectively. Then, 2-D-SSA applied onto dimension-reduced images to extract...

Accurately monitoring the quantity and quality of urban vegetation contributes to regional greening efforts improves understanding vegetation's impact on environment. However, factors such as building shadows synthetic materials can greatly obstruct estimates. Additionally, indices (VIs) saturate quickly in high biomass conditions, complicating assessments. To address these issues, we propose a new index, namely hyperspectral image-based index (HSVI). HSVI is built three steps: band...

Path planning is a global optimization problem aims to program the optimal flight path for Unmanned Aerial Vehicle (UAV) that has short length and suffers from low threat. In this paper, we present Mixed-Strategy based Gravitational Search Algorithm (MSGSA) planning. MSGSA, an adaptive adjustment strategy gravitational constant attenuation factor alpha ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math...

Large-scale, high-resolution and multi-temporal impervious surface maps from remote sensing are essential for socioeconomic environmental studies. However, in complex regions like subtropical China, climate terrain severely contaminate optical synthetic aperture radar (SAR) imagery, resulting relatively poor accuracy here. Therefore, this paper presents a novel network accurately extracting surfaces, which terrain-guided gated fusion module is proposed to adaptively fuse Sentinel-2...

Urbanization and climate change cause the urban ecological environment to become increasingly dependent on water. However, open water areas green spaces in cities are constantly decreasing, making resources scarce. There is an urgent need for a method that aligns with current status can quickly assess ecological–environmental quality (UEEQ). Traditional UEEQ methods have abandoned factor, neglecting influence of environment. In modern cities, water, which guarantees operation maintenance...

Soil salinization leads to dehydration of plants, which seriously threatens ecologically sustainable development and food security guarantee. In the complex diverse coastal wetland environment, impervious surface bare soil have similar spectral features with salinized soil, make it difficult for traditional satellite data algorithms accurately timely monitor small salinization. This article presents a baseline-based salinity index (BSSI) monitoring using medium-resolution data. BSSI, we...

Edge detection is one of the key issues in field computer vision and remote sensing image analysis. Although many different edge-detection methods have been proposed for gray-scale, color, multispectral images, they still face difficulties when extracting edge features from hyperspectral images (HSIs) that contain a large number bands with very narrow gap spectral domain. Inspired by clustering characteristic gravitational theory, novel algorithm HSIs presented this paper. In method, we...