{"title":"Spectral–Spatial Feature Extraction Network With SSM–CNN for Hyperspectral–Multispectral Image Collaborative Classification","authors":"Qingwang Wang;Xingxing Fan;Jiangbo Huang;Shuai Li;Tao Shen","doi":"10.1109/JSTARS.2024.3464681","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3464681","url":null,"abstract":"Multisource remote sensing (RS) image classification is a significant research area in Earth observation, aiming to achieve more comprehensive and accurate classification of land cover by integrating data from different sensors. Due to differences in imaging mechanisms and information imbalance between multisource data, multisource RS image classification faces two major challenges as follows. 1) Synergistically capturing features from different modalities to fully exploit complementary information. 2) Adaptively fusing multisource features to overcome the imbalance between modalities and avoid redundant information. This article proposes a spectral–spatial feature extraction network with SSM–CNN (SSFNet) for the collaborative classification of hyperspectral images (HSI) and multispectral images (MSI). Specifically, SSFNet captures long-range spectral correlations in HSI through a bidirectional state–space model (SSM) and learns local correlations between adjacent channels through spectral grouping, achieving global–local spectral information mining in HSI. Simultaneously, joint spatial feature extraction for HSI and MSI data is performed using embedded weight-shared residual feature extractor based on convolutional neural network. This process involves adaptively identifying the importance of features through privatized factors in batch normalization and accurately replacing redundant features. In addition, a spatial attention module is used to further enhance spatial feature representation. Finally, to better accommodate feature distributions and enhance classification outcomes, the extracted spectral–spatial features are combined using weighted fusion, allowing for dynamic integration. Experimental results on two datasets demonstrate that the proposed SSFNet significantly outperforms other competing methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10684557","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zixu Huang;Erwei Zhao;Wei Zheng;Xiaodong Peng;Wenlong Niu;Zhen Yang
{"title":"Infrared Small Target Detection via Two-Stage Feature Complementary Improved Tensor Low-Rank Sparse Decomposition","authors":"Zixu Huang;Erwei Zhao;Wei Zheng;Xiaodong Peng;Wenlong Niu;Zhen Yang","doi":"10.1109/JSTARS.2024.3463017","DOIUrl":"10.1109/JSTARS.2024.3463017","url":null,"abstract":"Infrared small target detection has been widely used in military and civil fields. However, due to the insufficient feature integration capabilities of existing methods, effectively separating strong background clutter and targets in complex scenes remains difficult. To address this issue, we propose a two-stage feature complementary improved tensor low-rank sparse decomposition (TLRSD) method. The detection process is divided into two stages: tensor initialization and tensor decomposition, effectively integrating local and nonlocal features. In the tensor initialization stage, inspired by the local saliency of the target and the local consistency of the background, we design a three-layer directional filtering (TLDF) operator for preliminary clutter suppression and target enhancement. Then, to promote the complementary advantages of local and nonlocal features, we refer to the TLDF and the original image to provide a targeted initialization strategy for the TLRSD model. In the tensor decomposition stage, we develop a robust partial sum of the tubal nuclear norm as a nonconvex approximation of tensor rank, which can adaptively adjust the singular value distribution, thus adapting to diversity scenes. Meanwhile, we finely adjust the balance between low-rank and sparse components in the model-solving process through a nonlinear reweighting strategy, accelerating the optimization convergence speed and improving the model's background recovery ability. Extensive experiments on five practical datasets demonstrate that the proposed method is more effective and robust compared to ten state-of-the-art approaches.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10682794","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhidan Cai, Ming Fang, Zhe Li, Jinyi Ming, Huimin Wang
{"title":"Blind Remote Sensing Image Deblurring Based on Local Maximum High Frequency Coefficient Prior and Graph Regularization","authors":"Zhidan Cai, Ming Fang, Zhe Li, Jinyi Ming, Huimin Wang","doi":"10.1109/jstars.2024.3461171","DOIUrl":"https://doi.org/10.1109/jstars.2024.3461171","url":null,"abstract":"","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hristina Hristova;Arnadi Murtiyoso;Daniel Kükenbrink;Mauro Marty;Meinrad Abegg;Christoph Fischer;Verena C. Griess;Nataliia Rehush
{"title":"Viewing the Forest in 3-D: How Spherical Stereo Videos Enable Low-Cost Reconstruction of Forest Plots","authors":"Hristina Hristova;Arnadi Murtiyoso;Daniel Kükenbrink;Mauro Marty;Meinrad Abegg;Christoph Fischer;Verena C. Griess;Nataliia Rehush","doi":"10.1109/JSTARS.2024.3462999","DOIUrl":"10.1109/JSTARS.2024.3462999","url":null,"abstract":"Understanding and monitoring the surrounding environment increasingly rely on its 3-D representations. However, the often high costs of 3-D data equipment limit its wide usage, and low-cost solutions are in demand. Here, we propose a novel approach based on spherical stereo videos captured with a known baseline (distance between the cameras) for a low-cost and efficient 3-D point cloud reconstruction. In a forest environment, we evaluated 1) the influence of baseline length on point cloud quality and 2) the suitability of the generated point clouds for extracting primary forest attributes (tree position and diameter). Our results show that the proposed approach allows for feasible 3-D reconstruction of complex forest plots. The highest point cloud quality was achieved with a baseline of 60 cm. This setup enabled the correct detection of more than 65% of the trees within the forest plots, producing an average tree position error between 30 and 50 cm and clearly outperforming other setups. A multiscale model-to-model cloud comparison analysis showed signed distances between the generated point cloud and the reference data with zero mean and 1 m standard deviation. We demonstrate that the proposed approach can be a valuable low-cost solution for 3-D point cloud reconstruction, facilitating forest assessment and monitoring.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10682782","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmed Mohammed;Nisar Ali;Abdul Bais;Yuefeng Ruan;Richard D. Cuthbert;Jatinder S. Sangha
{"title":"From Fields to Pixels: UAV Multispectral and Field-Captured RGB Imaging for High-Throughput Wheat Spike and Kernel Counting","authors":"Ahmed Mohammed;Nisar Ali;Abdul Bais;Yuefeng Ruan;Richard D. Cuthbert;Jatinder S. Sangha","doi":"10.1109/JSTARS.2024.3463432","DOIUrl":"10.1109/JSTARS.2024.3463432","url":null,"abstract":"Wheat breeding enhances wheat crops for better environmental resistance and higher yield potential. Experimental breeding lines are evaluated based on their yield potential, where quantifying spikes per unit area and kernels per spike is crucial for assessment. This study introduces SPINEL (SPIke and kerNEL), a framework that combines unmanned aerial vehicle (UAV)-captured multispectral imaging and field-captured RGB camera imaging for spike and kernel quantification. This approach utilizes YOLOv8 models, each tailored for a specific detection task. The first model detects plots in UAV-captured multispectral images with a mean average precision (mAP) score of 95%, while the second model, trained to detect spikes in the same dataset, demonstrates an mAP score of 86%. The third model detects spikes and kernels in field-captured RGB images with an 85% mAP score. The first two models aid in estimating the spike density in each field plot. The third model provides the estimated number of kernels in spikes of each unique breeding line. Spikes per field plot and kernels per spike serve as key quantification metrics. The SPINEL framework utilizes the geolocation information of the multispectral images and associates these metrics with breeding lines at the field level. This integration provides a clear visual representation of spike count and average kernels per spike for each field plot. SPINEL offers a precise, automated solution for phenotyping in wheat breeding, promising significant advancements in crop improvement strategies.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10682791","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ConvLSTM–ViT: A Deep Neural Network for Crop Yield Prediction Using Earth Observations and Remotely Sensed Data","authors":"Seyed Mahdi Mirhoseini Nejad;Dariush Abbasi-Moghadam;Alireza Sharifi","doi":"10.1109/JSTARS.2024.3464411","DOIUrl":"10.1109/JSTARS.2024.3464411","url":null,"abstract":"This article introduces an approach for soybean yield prediction by integrating convolutional long short-term memory (ConvLSTM), three-dimensional convolutional neural network (3D-CNN), and vision transformer (ViT). By utilizing multispectral remote sensing data, our model leverages the spatial hierarchy of 3D-CNNs, the temporal sequencing capabilities of ConvLSTM, and the global context analysis of ViTs to capture complex patterns in agricultural datasets. The integration of these advanced methodologies allows for a comprehensive analysis of both spatial and temporal aspects of crop growth, enabling more accurate and robust predictions. Our experimental results demonstrate that the proposed model significantly outperforms existing methods, as evidenced by lower root mean square error and higher correlation coefficients. The 3D-CNN component effectively extracts spatial features from the multispectral images, while the ConvLSTM captures the temporal dynamics of crop development. The ViT further refines these features by focusing on the most relevant parts of the input data through self-attention mechanisms. The findings highlight the potential of this model in enhancing decision-making processes in crop management, particularly in precision agriculture. By providing more accurate yield predictions, the model can assist farmers in optimizing resource allocation, scheduling irrigation, and applying fertilizers more efficiently, thereby promoting sustainable farming practices. Furthermore, the model's robustness across various conditions underscores its applicability to different crops and geographic regions. This article contributes to the field of agricultural remote sensing by offering a robust solution to the complexities of analyzing large-scale, multispectral data. The proposed approach not only improves prediction accuracy but also provides timely and actionable insights for agricultural stakeholders.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10684164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammad Ahmad;Muhammad Hassaan Farooq Butt;Manuel Mazzara;Salvatore Distefano;Adil Mehmood Khan;Hamad Ahmed Altuwaijri
{"title":"Pyramid Hierarchical Spatial-Spectral Transformer for Hyperspectral Image Classification","authors":"Muhammad Ahmad;Muhammad Hassaan Farooq Butt;Manuel Mazzara;Salvatore Distefano;Adil Mehmood Khan;Hamad Ahmed Altuwaijri","doi":"10.1109/JSTARS.2024.3461851","DOIUrl":"10.1109/JSTARS.2024.3461851","url":null,"abstract":"The transformer model encounters challenges with variable-length input sequences, leading to efficiency and scalability concerns. To overcome this, we propose a pyramid-based hierarchical spatial-spectral transformer (PyFormer). This innovative approach organizes input data hierarchically into pyramid segments, each representing distinct abstraction levels, thereby enhancing processing efficiency. At each level, a dedicated transformer encoder is applied, effectively capturing both local and global context. Integration of outputs from different levels culminates in the final input representation. In short, the pyramid excels at capturing spatial features and local patterns, while the transformer effectively models spatial-spectral correlations and long-range dependencies. Experimental results underscore the superiority of the proposed method over state-of-the-art approaches, achieving overall accuracies of 96.28% for the Pavia University dataset and 97.36% for the University of Houston dataset. In addition, the incorporation of disjoint samples augments robustness and reliability, thereby highlighting the potential of PyFormer in advancing hyperspectral image classification (HSIC).","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681622","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Raja Inoubli;Daniel Enrique Constantino-Recillas;Alejandro Monsiváis-Huertero;Lilia Bennaceur Farah;Imed Riadh Farah
{"title":"Assessment of Surface Scattering Models Within the Water Cloud Model Toward Soil Moisture Retrievals Using Sentinel-1 and Sentinel-2 Images","authors":"Raja Inoubli;Daniel Enrique Constantino-Recillas;Alejandro Monsiváis-Huertero;Lilia Bennaceur Farah;Imed Riadh Farah","doi":"10.1109/JSTARS.2024.3462591","DOIUrl":"10.1109/JSTARS.2024.3462591","url":null,"abstract":"The agricultural productivity and the optimized use of water resources rely on the soil moisture (SM) retrieval to achieve some of the sustainable development goals, such as ensuring food security and monitoring climate change. One of the main aspects to provide accurate SM retrieval results is the selection of the most effective models. This study is carried out to exhibit the impact of three different soil formulations [i.e., Linear, Oh, and improved integral equation model (I2EM)] within the water cloud model (WCM). The experiments are conducted based on the combined use of Sentinel-1 and Sentinel-2 images. The in-situ measurements used in this work are collected from five different fields in Huamantla, Central Mexico. The experiments focus on the complete growing season of corn taking into consideration the soil and the vegetation contribution. The best \u0000<italic>Bias</i>\u0000 and \u0000<italic>unbiased root mean squared difference (ubRMSD)</i>\u0000 values obtained by the Oh-WCM are equal to −0.437 and 0.295 dB, respectively at VV in PX1. The I2EM-WCM achieved \u0000<italic>Bias</i>\u0000 and \u0000<italic>ubRMSD</i>\u0000 values equal to −0.760 and 0.379 dB at VV, respectively. The linear-WCM also obtained low \u0000<italic>Bias</i>\u0000 and \u0000<italic>ubRMSD</i>\u0000 values equal to −0.297 and 0.322 dB, respectively. Therefore, the combination of the Oh model within the WCM is considered as the appropriate combination for the SM retrieval due to its high achieved accuracy. The sensitivity analysis of changes in \u0000<inline-formula><tex-math>$sigma ^{0}_{pq,text{tot}}$</tex-math></inline-formula>\u0000 due to changes in SM found that it is possible to capture changes higher than 0.06 m\u0000<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>\u0000/m\u0000<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>\u0000 in SM over the complete growing season of corn using C-band backscatter observations.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681514","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weihua Gao;Wenlong Niu;Wenlong Lu;Pengcheng Wang;Zhaoyuan Qi;Xiaodong Peng;Zhen Yang
{"title":"Dim Small Target Detection and Tracking: A Novel Method Based on Temporal Energy Selective Scaling and Trajectory Association","authors":"Weihua Gao;Wenlong Niu;Wenlong Lu;Pengcheng Wang;Zhaoyuan Qi;Xiaodong Peng;Zhen Yang","doi":"10.1109/JSTARS.2024.3462514","DOIUrl":"10.1109/JSTARS.2024.3462514","url":null,"abstract":"Effective detection and tracking of dim and small targets with low SCR has become a research hotspot due to its wide range of applications. However, most of the previously proposed methods seldom utilize the abundant temporal features formed by target motion, resulting in poor detection and tracking performance for low SCR targets. In this article, we analyze the difficulty based on spatial features and the feasibility based on temporal features of realizing effective detection. According to this analysis, we use a multiframe as a detection unit and propose a detection method based on TESS. Specifically, we investigated the composition of ITPs formed by pixels on a multiframe detection unit. For the target-present pixel, the target passing through the pixel will bring a weak transient disturbance on the ITP and introduce a change in the statistical properties of ITP. We use a well-designed function to amplify the transient disturbance, suppress the background and noise components, and output the trajectory of the target. Subsequently, to solve the contradiction between the detection rate and the false alarm rate brought by the traditional threshold segmentation, we associate the temporal and spatial features of the trajectory and propose a trajectory extraction method based on the 3-D Hough transform. Finally, we propose a trajectory segments-based multitarget tracking method. Compared with the various state-of-the-art detection and tracking methods, experiments in multiple scenarios prove the superiority of our proposed methods for dim and small targets in low SCR.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":null,"pages":null},"PeriodicalIF":4.7,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681464","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142248902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}