Remote Sensing Image Classification Research Articles

Exploring Hybrid Contrastive Learning and Scene-to-Label Information for Multilabel Remote Sensing Image Classification

Exploring Hybrid Contrastive Learning and Scene-to-Label Information for Multilabel Remote Sensing Image Classification

Multiloss Adversarial Attacks for Multimodal Remote Sensing Image Classification

Multiloss Adversarial Attacks for Multimodal Remote Sensing Image Classification

A Novel Deep Learning Framework With Meta-Heuristic Feature Selection for Enhanced Remote Sensing Image Classification

A Novel Deep Learning Framework With Meta-Heuristic Feature Selection for Enhanced Remote Sensing Image Classification

Intra- and Intersource Interactive Representation Learning Network for Remote Sensing Images Classification

Intra- and Intersource Interactive Representation Learning Network for Remote Sensing Images Classification

GrI-CNN: Granulated Deep Learning Model With Interpretable Architecture for Remote Sensing Image Classification

GrI-CNN: Granulated Deep Learning Model With Interpretable Architecture for Remote Sensing Image Classification

Attention-Based Contrastive Learning for Few-Shot Remote Sensing Image Classification

Attention-Based Contrastive Learning for Few-Shot Remote Sensing Image Classification

Multi-view Graph Convolutional Network with Spectral Component Decompose for Remote Sensing Images Classification

Automatic land cover classification from high-resolution remote sensing (RS) images remains challenging due to the complex composition of classes. Given the potential of a graph to simulate latent class composition, the latest development of graph convolutional network (GCN) has received increasing attention. However, most existing methods only use a single perspective graph structure, which largely limits their ability to capture the complementary features that would better represent the underlying data structure of images. Therefore, this paper proposes a novel multi-view GCN-based representation learning network(MvRLNet) for RS image classification. First, a superpixel-based spectral component decomposes module(SSCDM) is designed to enhance the uniqueness and homogeneity of graph nodes because the mixed superpixels may lead to miscellaneous information on graph aggregations. Second, a multi-view graph learning module(MGLM) is proposed to integrate topology and spectral graph information into a unified network with an effective feature learning strategy. Finally, the effectiveness of the proposed MvRLNet is validated on a variety datasets with different resolutions. The experimental results show that the proposed MvRLNet performs better than state-of-the-art techniques.

Comparison and Analysis of Several Remote Sensing Image Classification Methods

Comparison and Analysis of Several Remote Sensing Image Classification Methods

Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification

Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification

Application of Convolutional Neural Networks in High Score Remote Sensing Image Classification

Application of Convolutional Neural Networks in High Score Remote Sensing Image Classification

A Spatial-Spectral Relation-Guided Fusion Network for Multisource Optical RS Image Classification.

Multisource optical remote sensing (RS) image classification has obtained extensive research interest with demonstrated superiority. Existing approaches mainly improve classification performance by exploiting complementary information from multisource data. However, these approaches are insufficient in effectively extracting data features and utilizing correlations of multisource optical RS images. For this purpose, this article proposes a generalized spatial-spectral relation-guided fusion network ( S2 RGF-Net) for multisource optical RS image classification. First, we elaborate on spatial-and spectral-domain-specific feature encoders based on data characteristics to explore the rich feature information of optical RS data deeply. Subsequently, two relation-guided fusion strategies are proposed at the dual-level (intradomain and interdomain) to integrate multisource image information effectively. In the intradomain feature fusion, an adaptive de-redundancy fusion module (ADRF) is introduced to eliminate redundancy so that the spatial and spectral features are complete and compact, respectively. In interdomain feature fusion, we construct a spatial-spectral joint attention module (SSJA) based on interdomain relationships to sufficiently enhance the complementary features, so as to facilitate later fusion. Experiments on various multisource optical RS datasets demonstrate that S2 RGF-Net outperforms other state-of-the-art (SOTA) methods.

Representation-Enhanced Status Replay Network for Multisource Remote-Sensing Image Classification.

Deep-learning-based methods are widely used in multisource remote-sensing image classification, and the improvement in their performance confirms the effectiveness of deep learning for classification tasks. However, the inherent underlying problems of deep-learning models still hinder the further improvement of classification accuracy. For example, after multiple rounds of optimization learning, representation bias and classifier bias are accumulated, which prevents the further optimization of network performance. In addition, the imbalance of fusion information among multisource images also leads to insufficient information interaction throughout the fusion process, thus making it difficult to fully utilize the complementary information of multisource data. To address these issues, a Representation-enhanced Status Replay Network (RSRNet) is proposed. First, a dual augmentation including modal augmentation and semantic augmentation is proposed to enhance the transferability and discreteness of feature representation, to reduce the impact of representation bias in the feature extractor. Then, to alleviate the classifier bias and maintain the stability of the decision boundary, a status replay strategy (SRS) is built to regulate the learning and optimization of the classifier. Finally, aiming to improve the interactivity of modal fusion, a novel cross-modal interactive fusion (CMIF) method is employed to jointly optimize the parameters of different branches by combining multisource information. Quantitative and qualitative results on three datasets demonstrate the superiority of RSRNet in multisource remote-sensing image classification, and its outperformance compared with other state-of-the-art methods.

Retracted: I3D: An Improved Three-Dimensional CNN Model on Hyperspectral Remote Sensing Image Classification

Retracted: I3D: An Improved Three-Dimensional CNN Model on Hyperspectral Remote Sensing Image Classification

A New Remote Sensing Desert Vegetation Detection Index

Land desertification is a key environmental problem in China, especially in Northwest China, where it seriously affects the sustainable development of natural resources. In this paper, we combine high-resolution satellite remote sensing images and UAV (unmanned aerial vehicle) visible light images to extract desert vegetation data and quickly locate and accurately monitor land desertification in relevant areas according to changes in vegetation coverage. Due to the strong light and dry climate of deserts in Northwest China, which results in deeper vegetation shadow texture and mostly dry shrubs with fewer stems and leaves, the accuracy of the vegetation index commonly used in visible remote sensing image classification is not able to meet the requirements for monitoring and evaluating land desertification. For this reason, in this paper, we took the Hangjin Banner in Bayannur as an example and constructed a new vegetation index, the HSVGVI (hue–saturation–value green enhancement vegetation index), based on the HSV (hue–saturation–value) color space using channel enhancement that can improve the extraction accuracy of desert vegetation and reduce misclassification. In addition, in order to further test the extraction accuracy, samples of densely vegetated and multi-shaded areas were divided in the study area according to the accuracy-influencing factors. At the same time, the HSVGVI was compared with the vegetation indices EXG (excess green index), RGBVI (red–green–blue vegetation index), MGRVI (modified green–red vegetation index), NGBDI (normalized green–red discrepancy index), and VDVI (visible-band discrepancy vegetation index) constructed based on the RGB (red–green–blue) color space. The experimental results show that the extraction accuracy of the EXG and other vegetation indices constructed in RGB color space can only reach 70%, while the extraction accuracy of the HSVGVI can reach more than 95%. In summary, the HSVGVI proposed in this paper can better realize the extraction of desert vegetation data and can provide a reliable technical tool for monitoring and evaluating land desertification.

Efficient knowledge distillation for remote sensing image classification: a CNN-based approach

PurposeThe paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.Design/methodology/approachThis study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.FindingsThis study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.Originality/valueThis study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

SEMANTIC KNOWLEDGE EMBEDDING DEEP LEARNING NETWORK FOR LAND COVER CLASSIFICATION

Abstract. Land cover classification is essential basic information and key parameters for environmental change research, geographical and national monitoring, and sustainable development planning. Deep learning can automatically and multi-level extract the features of complex features, which has been proven to be an effective method for information extraction. However, one of the major challenges of deep learning is its poor interpret-ability, which makes it difficult to understand and explain the reasoning behind its classification results. This paper proposes a deep cross-modal coupling model (CMCM) for integrating semantic features and visual features. The representation of knowledge map is indicatively introduced into remote sensing image classification. Compared to previous studies, the proposed method provides accurate descriptions of the complex semantic objects within a complex land cover environment. The results showed that the integration of semantic knowledge improved the accuracy and interpret-ability of land cover classification.

Extracting Citrus in Southern China (Guangxi Region) Based on the Improved DeepLabV3+ Network

China is one of the countries with the largest citrus cultivation areas, and its citrus industry has received significant attention due to its substantial economic benefits. Traditional manual forestry surveys and remote sensing image classification tasks are labor-intensive and time-consuming, resulting in low efficiency. Remote sensing technology holds great potential for obtaining spatial information on citrus orchards on a large scale. This study proposes a lightweight model for citrus plantation extraction that combines the DeepLabV3+ model with the convolutional block attention module (CBAM) attention mechanism, with a focus on the phenological growth characteristics of citrus in the Guangxi region. The objective is to address issues such as inaccurate extraction of citrus edges in high-resolution images, misclassification and omissions caused by intra-class differences, as well as the large number of network parameters and long training time found in classical semantic segmentation models. To reduce parameter count and improve training speed, the MobileNetV2 lightweight network is used as a replacement for the Xception backbone network in DeepLabV3+. Additionally, the CBAM is introduced to extract citrus features more accurately and efficiently. Moreover, in consideration of the growth characteristics of citrus, this study augments the feature input with additional channels to better capture and utilize key phenological features of citrus, thereby enhancing the accuracy of citrus recognition. The results demonstrate that the improved DeepLabV3+ model exhibits high reliability in citrus recognition and extraction, achieving an overall accuracy (OA) of 96.23%, a mean pixel accuracy (mPA) of 83.79%, and a mean intersection over union (mIoU) of 85.40%. These metrics represent an improvement of 11.16%, 14.88%, and 14.98%, respectively, compared to the original DeepLabV3+ model. Furthermore, when compared to classical semantic segmentation models, such as UNet and PSPNet, the proposed model achieves higher recognition accuracy. Additionally, the improved DeepLabV3+ model demonstrates a significant reduction in both parameters and training time. Generalization experiments conducted in Nanning, Guangxi Province, further validate the model’s strong generalization capabilities. Overall, this study emphasizes extraction accuracy, reduction in parameter count, adherence to timeliness requirements, and facilitation of rapid and accurate extraction of citrus plantation areas, presenting promising application prospects.

Remote sensing image classification using modified random forest with empirical loss function through crowd-sourced data

Remote sensing image classification using modified random forest with empirical loss function through crowd-sourced data

S2EFT: Spectral-Spatial-Elevation Fusion Transformer for hyperspectral image and LiDAR classification

With the innovation of sensors, communication, computer and other technologies, remote sensing (RS) imaging methods show a diversification trend. At present, relying on a variety of earth observation platforms, more multi-source RS data can be obtained, which overcomes the inadequacy and incompleteness of the new earth observation information of single source RS image. In this paper, a classification method of hyperspectral images (HSI) and LiDAR data based on spectral-spatial-elevation fusion Transformer (S2EFT) framework is proposed. The Transformer framework is introduced into the task of multi-source RS image classification. Two simple but effective modules, spatial information recognition module and sliding group spectral embedding module, are added to the proposed framework, and the Patch form commonly used in traditional convolutional neural networks (CNNs) is used as the input. It effectively solves the shortcomings of Transformer’s insufficient attention to local information, reduces redundant spatial information, enhances the transmission of information, and fully integrates multidimensional information of pixels in same position. Experiments on three real data sets are compared with existing methods, and the best results are obtained by the proposed methods. The source code can be downloaded from https://github.com/SYFYN0317/S2EFT.

Integrating IoT and honey badger algorithm based ensemble learning for accurate vehicle detection and classification

The fusion of Internet of Things (IoT) and deep learning (DL) methods has proven valuable in automating vehicle detection and classification tasks on remote sensing images (RSI). This technology has broad applications, including traffic monitoring, urban planning, and transportation management. Recent advancements have demonstrated the efficacy of DL models like convolutional neural networks (CNN) in RSI classification tasks. In this aspect, this study proposes a novel honey badger optimization algorithm with an ensemble learning-based vehicle detection and classification (HBOAEL-VDC) technique. The purpose of the study is to design ensemble DL models for accurate vehicle identification and classification processes. To accomplish this, the HBOAEL-VDC technique makes use of an improved RetinaNet model for the detection of objects, i.e., vehicles on the RSI. Moreover, the classification of detected vehicles takes place using the ensemble learning process, comprising three DL models, namely gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). Furthermore, the HBOA-based parameter tuning process gets carried out to adjust the hyperparameter values of the DL models and thereby improve the classification results. The simulation outcome of the HBOAEL-VDC approach is tested on benchmark RSI databases. The experimentation outcomes reported the enhanced vehicle classification performance of the HBOAEL-VDC approach over other recent DL models.