The proceedings contain 133 papers. The topics discussed include: research on information integration technology of space optical remotesensing sensor;human contour segmentation algorithm for radiotherapy-assisted po...
ISBN:
(纸本)9781510680012
The proceedings contain 133 papers. The topics discussed include: research on information integration technology of space optical remotesensing sensor;human contour segmentation algorithm for radiotherapy-assisted positioning;improved design of satellite magnetic test facility;a mathematical morphology-based detector for underwater target detection using side-scan sonar images;semantic fusion block: enhanced transformer architecture for imbalanced remotesensingimage semantic segmentation;remotesensing aircraft object detection algorithm based on attention mechanism;research on remotesensing small object detection algorithm based on improved YOLOv8;and remotesensing retrieval model and analysis of sea water transparency based on quasi-analytical algorithm.
The proceedings contain 35 papers. The topics discussed include: a theoretical framework for unsupervised land cover change detection in dense satellite image time series;a class-driven hierarchical ResNet for classif...
ISBN:
(纸本)9781510666955
The proceedings contain 35 papers. The topics discussed include: a theoretical framework for unsupervised land cover change detection in dense satellite image time series;a class-driven hierarchical ResNet for classification of multispectral remotesensingimages;large-scale LOD1 building extraction from a textured 3D Mesh of a scene;enhancing land cover maps with optical time series and ambiguous loss function;deep learning methodologies for chemical dispersion map reconstruction;monitoring of renewable energy sources with remotesensing, open data and field data in Bulgaria;detection of over-ground petroleum and gas pipelines from optical remotesensingimages;and a remotesensing satellite image compression method based on conditional generative adversarial network.
The proceedings contain 31 papers. The topics discussed include: high-performance embedded system for onboard object detection in hyperspectral images;advanced building detection in VHR satellite imagery: a comprehens...
ISBN:
(纸本)9781510681002
The proceedings contain 31 papers. The topics discussed include: high-performance embedded system for onboard object detection in hyperspectral images;advanced building detection in VHR satellite imagery: a comprehensive study using different mask R-CNN approaches;attention-based 3D convolutional neural network for crop boundary detection in high-resolution satellite image time series;one-shot gas detection with transformer paired neural networks in mako collected longwave infrared hyperspectral imagery;efficient semantic segmentation of radar sounder data;unsupervised sparse convolutional autoencoder for multi-class change detection in hyperspectral images;SAR-optical deep UNet matching with Gabor jet model;and improvement of ALB data analysis method using machine learning for rescuer search in water rescue.
Adverse weather conditions consistently compromise the quality of remotesensingimages and hinder downstream vision-based tasks. Recent progress in remotesensingimage restoration has been driven by Convolutional Ne...
详细信息
Adverse weather conditions consistently compromise the quality of remotesensingimages and hinder downstream vision-based tasks. Recent progress in remotesensingimage restoration has been driven by Convolutional Neural Networks and Transformers. Nonetheless, these approaches face challenges such as constrained receptive fields or high computational costs with quadratic complexity, resulting in a trade-off between performance and efficiency. In this paper, we propose an effective multi-scale vision Mamba for remotesensingimage restoration by modeling long-range pixel dependencies with linear complexity. Specifically, we develop a bidirectional Mamba network architecture that effectively explores intra-scale and inter-scale information interactions. In addition, we design an efficient multi-scale 2D scanning mechanism to better facilitate image restoration across different scales. Extensive experiments show that the proposed method performs favorably against state-of-the-art models.
Few-shot learning has been extensively applied in current remotesensingimage classification, enabling rapid identification of new classes by leveraging prior knowledge effectively. However, current methods mainly re...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Few-shot learning has been extensively applied in current remotesensingimage classification, enabling rapid identification of new classes by leveraging prior knowledge effectively. However, current methods mainly rely on image modality to address the issue of low intra-class similarity and high interclass similarity, while the utilization of multimodal methods in remotesensing tasks remains largely unexplored. Therefore, we propose a novel framework for few-shot remotesensingimage classification, named multi-view image-text perception (MVITP). Specifically, it leverages maximum mutual information across multiple views to train an image encoder and generate image features. A text encoder is employed to generate text features. Next, we introduce a multimodal fusion encoder to capture the similarity between image features and text features. Finally, class predictions are further made by computing the similarity between the support set and the query set. We conduct experiments on three remotesensing datasets, demonstrating the outstanding performance of MVITP.
In recent years, although transformer technology has been widely used in the field of image super-resolution, it still has some limitations in handling low-frequency information and local features of images, especiall...
详细信息
In recent years, although transformer technology has been widely used in the field of image super-resolution, it still has some limitations in handling low-frequency information and local features of images, especially when facing the challenges posed by the complex backgrounds and diverse surface features of remotesensingimages. In this paper, a new image super-resolution algorithm based on the Swin Transformer, called SwinFR, is proposed. The core innovation lies in the design of the Residual Swin Transformer Fourier Block (RSTFB), which combines the residual Swin Transformer layer with the fast Swin Transformer Fourier Block. This combination improves the model's ability to capture low-frequency information and preserve image structural details. The module also enhances deep feature extraction and inter-layer information flow by integrating convolution and residual concatenation, which improves the model's feature integration capability and its ability to handle complex background information in remotesensingimages. In addition, this paper introduces the Multi-Scale Feature Learning (MSFL) module, which further enhances the processing of local and global information and enables high-quality image reconstruction. Experimental results show that SwinFR outperforms existing methods in key metrics such as visualization, PSNR, SSIM, and MOS on both the UCMLU and SIRI-WHU datasets, effectively demonstrating its superiority and practicality.
Multi-image Super-Resolution (MISR) reconstructs high-resolution images from multiple satellite-acquired low-resolution images, emerging as a key technique in remotesensing. However, image sequences collected by sate...
详细信息
Multi-image Super-Resolution (MISR) reconstructs high-resolution images from multiple satellite-acquired low-resolution images, emerging as a key technique in remotesensing. However, image sequences collected by satellites usually have diverse views and extended time spans, making the integration of multiple low-resolution images into a single high-resolution image with intricate details a challenging problem. In this paper, we propose AttMISR, an attention-based multi-image super-resolution network for remotesensing. AttMISR is composed of three key modules: a feature extraction module utilizing residual dynamic convolution blocks, a hybrid non-local feature fusion module, and a multi-attention-based image reconstruction module. The feature extraction module integrates the residual structure with dynamic convolution to efficiently capture complex features and textures in remotesensingimages, while the hybrid non-local feature fusion module optimizes feature aggregation across multiple remotesensingimages by calculating both cross-correlation and non-cross-correlation features. Moreover, a coordinate-window attention mechanism is proposed to construct the multi-attention-based image reconstruction module, enabling more precise reconstruction. Comprehensive experiments conducted on PROBA-V Kelvin dataset demonstrate the superiority of the proposed method.
Restoring a high-resolution (HR) image from a low-resolution (LR) image using deep learning (DL) techniques is becoming a popular restoration approach in the remotesensingimage super-resolution (SR). However, blurry...
详细信息
Restoring a high-resolution (HR) image from a low-resolution (LR) image using deep learning (DL) techniques is becoming a popular restoration approach in the remotesensingimage super-resolution (SR). However, blurry object edges, artifacts, memory usage, and computational burdens are still challenges in remotesensingimage SR. To overcome these challenges, a lightweight Multiwavelet-based Multiscale Dilated Attention Network (MMDAN) for remote-sensingimage SR is proposed. The main aim of the proposed work is to reconstruct the HR image in the multiwavelet domain. The SR scheme based on the multiwavelets is proposed under a DL framework to exploit the contextual information from sixteen subbands of multiwavelets. A multiscale dilated convolution, along with a nested attention module, is employed as a deep feature extraction function to enhance the image restoration of the proposed model. Experiments on remotesensing and natural image datasets show the superiority of the proposed model in resolution enhancement.
Multi-source remotesensingimage matching is crucial for remotesensing technology applications. However, the variations in factors such as grayscale, perspective, and sensors between multi-source images present cert...
详细信息
ISBN:
(数字)9798350350920
ISBN:
(纸本)9798350350920
Multi-source remotesensingimage matching is crucial for remotesensing technology applications. However, the variations in factors such as grayscale, perspective, and sensors between multi-source images present certain challenges for image matching. In response to the challenges in matching multi-source remotesensingimages, a matching method based on texture-enhanced region features is proposed. Initially, Gabor filters and the gray-level co-occurrence matrix (GLCM) are used to obtain the texture energy maps, followed by the extraction of maximally stable extremal regions (MSER) on the texture energy maps to acquire region features. Subsequently, the contour descriptors of the features are computed using Fourier descriptors. Finally, feature matching and refinement of the matching results are conducted in conjunction with the fast sample consensus (FSC). We conducted experimental region feature matching on multiple pairs of multi-source remotesensingimages, and the results validate the effectiveness of our method.
暂无评论