ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"Efficient large-scale vegetation mapping at the formation level using multi-source data: A case study in Beijing, China","authors":"Jiachen Xu ,&nbsp;Yongmei Huang ,&nbsp;Kai Cheng ,&nbsp;Yi Wang ,&nbsp;Tianyu Hu ,&nbsp;Hongcan Guan ,&nbsp;Yuling Chen ,&nbsp;Yu Ren ,&nbsp;Mengxi Chen ,&nbsp;Zekun Yang ,&nbsp;Jiarui Wang ,&nbsp;Qinghua Guo","doi":"10.1016/j.isprsjprs.2025.04.021","DOIUrl":"10.1016/j.isprsjprs.2025.04.021","url":null,"abstract":"<div><div>Formation-level vegetation mapping is pivotal for understanding ecological processes and mechanisms, as it reveals the distribution of dominant species that shape ecosystem structure and dynamics. However, fast and accurate formation-level mapping over large geographic areas is often hindered by the lack of robust mapping frameworks, limited field survey data, and unscientific or inefficient division of vegetation patches. To address these challenges, we proposed an automated mapping framework that integrates multi-source data for formation-level vegetation mapping. Our approach introduced an innovative strategy for automatically delineating vegetation patches based on slope units, improving mapping efficiency and ensuring results align more closely with actual vegetation distribution. Additionally, we developed a crowdsource-based vegetation survey system that aggregates data from diverse sensors, significantly increasing the sample size and diversity of vegetation formations. Using this framework, we successfully mapped 16 formations in Beijing with an overall accuracy of 65.7%, achieving F-scores exceeding 60% for major formations. The result indicates that Beijing’s vegetation is dominated by forests and shrublands, with the largest vegetation formation being <em>Vitex negundo</em> (deciduous broadleaf shrubland), covering 20% of the city in the southwestern mountains, followed by <em>Quercus mongolica</em> (deciduous broadleaf forest), occupying 10% in the northwestern mountains. This study provides a solid foundation for understanding Beijing’s vegetation distribution and its ecological functions. By integrating remote sensing and crowdsourced data, it demonstrates an effective approach for precise, large-scale formation-level vegetation mapping, offering valuable support for refined ecological management and interdisciplinary research.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"225 ","pages":"Pages 36-51"},"PeriodicalIF":10.6,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AWDA: Adversarial and Weighted Domain Adaptation for cross-dataset change detection","authors":"Xueting Zhang,&nbsp;Xin Huang,&nbsp;Jiayi Li","doi":"10.1016/j.isprsjprs.2025.04.008","DOIUrl":"10.1016/j.isprsjprs.2025.04.008","url":null,"abstract":"<div><div>Recent advancements in change detection (CD) using fully-supervised methods have been significant; however, effectively applying CD in scenarios where labels are unavailable remains a challenge. To address this, our study introduces a new task, domain adaptive change detection (DACD), which transfers change knowledge from a labeled CD dataset (source domain) to an unlabeled CD dataset (target domain). In practice, two challenges hinder change knowledge transfer across domains: domain shifts, such as resolution differences and change semantic discrepancies, and imbalanced distribution between the minority change class and the dominant no-change class. To tackle these issues, we propose a novel Adversarial and Weighted Domain Adaptation (AWDA) framework for DACD. AWDA employs a Siamese encoder–decoder network shared between source and target domains to extract features and make predictions from bi-temporal remote sensing images. Moreover, AWDA incorporates three cross-domain learning strategies for learning domain-invariant CD representations: (1) supervised learning, which uses all the labeled data of the source domain to train the model to obtain initial CD capability, (2) domain adversarial training, which aligns the features between the source and target domains adversarially, and (3) class-weighted self-training, which dynamically computes and assigns class weights for the self-training on the unlabeled data of the target domain. The proposed AWDA effectively mitigates cross-domain shifts and preserves the integrity of the minor change class during knowledge transfer. To evaluate our method’s effectiveness, we conducted comprehensive experiments across four cross-domain CD scenarios using three well-known building CD datasets. The results demonstrate AWDA substantially enhances CD performance in the target domain, achieving IoU increase ranging from 13.64 to 34.73, and significantly surpassing several competing domain adaptation methods. Our code will be available at <span><span>https://github.com/zxt9/AWDA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 398-409"},"PeriodicalIF":10.6,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From rice planting area mapping to rice agricultural system mapping: A holistic remote sensing framework for understanding China's complex rice systems","authors":"Zizhang Zhao ,&nbsp;Jinwei Dong ,&nbsp;Jilin Yang ,&nbsp;Luo Liu ,&nbsp;Nanshan You ,&nbsp;Xiangming Xiao ,&nbsp;Geli Zhang","doi":"10.1016/j.isprsjprs.2025.03.026","DOIUrl":"10.1016/j.isprsjprs.2025.03.026","url":null,"abstract":"<div><div>Information on the rice agricultural system, including not only planting area but also phenology and cropping intensity, is critical for advancing our understanding of food and water security, methane emissions, carbon and nitrogen cycles, and avian influenza transmission. However, existing efforts primarily focus on mapping planting area and lack a comprehensive picture of the rice agricultural system. To address this gap, we propose a remote sensing-based comprehensive framework for mapping the rice agricultural system in China: First, we identified valid growth cycles of crop by using 30-m Sentinel-2 and Landsat fused data; Second, we applied a well-established phenology-based algorithm to map rice planting areas, by extracting the flooding and rapid growth signals in the transplanting and rapid growth temporal windows; Third, the rice-specific phenology phases (i.e., transplanting, tillering, heading, and mature) were identified using a phenology extraction method tailored to the physiological characteristics of rice; Finally, rice cropping intensity was determined based on detailed phenological phases and planting area data. Due to the accurate identification of crop cycles and pixel-level temporal windows at the national scale, the generated rice planting area maps exhibit a high accuracy across China, with both overall accuracy and F1 scores exceeding 0.8, based on validation with over 13,000 field samples. Improvements in the extraction method have addressed the lag in phenology detection caused by rice’s flooded environment, leading to more accurate phenological information. As a result, the phenological data shows reliable accuracy (<em>R²</em> of 0.6–0.8 and <em>RMSE</em> of 8–15 days), facilitated by the mutual enhancement of rice planting area and phenology mapping. The resultant rice phenology and cropping intensity maps are the first of their kind with 30 m resolution. Together, the resultant rice planting area, rice phenology, and cropping intensity maps provide, for the first time, a comprehensive picture of China's rice agricultural system, better supporting multiple targets related to Sustainable Development Goals.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 382-397"},"PeriodicalIF":10.6,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New maps of mafic mineral abundances in global mare units on the Moon","authors":"Yuzhen Wang ,&nbsp;Haijun Cao ,&nbsp;Jian Chen ,&nbsp;Changqing Liu ,&nbsp;Xuejin Lu ,&nbsp;Chengxiang Yin ,&nbsp;Xiaohui Fu ,&nbsp;Le Qiao ,&nbsp;Guang Zhang ,&nbsp;Chengbao Liu ,&nbsp;Peng Zhang ,&nbsp;Zongcheng Ling","doi":"10.1016/j.isprsjprs.2025.04.010","DOIUrl":"10.1016/j.isprsjprs.2025.04.010","url":null,"abstract":"<div><div>Lunar surface mineralogy plays a crucial role in characterizing the distribution and abundance of silicate minerals, providing pivotal insights into the geological evolution of the Moon. Existing lunar mineral distribution maps are primarily derived from the calibration of Apollo and Luna sample datasets, which are predominantly older than 3.0 Ga. However, these maps lack critical constraints from younger mare basalt samples, limiting their ability to fully represent the mineralogical diversity of lunar mare units. In this work, we present updated global mineral abundance maps for olivine (OLV), high-Ca pyroxene (HCP), and low-Ca pyroxene (LCP) on the global mare units using the partial least squares regression (PLS) algorithm applied to Moon Mineralogy Mapper data, incorporated the distinctive 2.0-Ga Chang’e-5 lunar samples as a new calibration reference. The revised maps indicate mean HCP, LCP, and OLV abundances of 48.4 wt%, 38.2 wt%, and 13.2 wt%, respectively, among global mare units. Our results reveal a systematic trend of HCP enrichment and OLV depletion in younger mare basalts, which correlates with variations in TiO₂ content and model ages. HCP abundance follows a Gaussian distribution, increasing from low-Ti to high-Ti units, whereas LCP exhibits an inverse trend. OLV abundance only shows a slightly decrease from medium-Ti to low-Ti units. From a geochemical perspective, mare units become progressively enriched in HCP with increasing FeO content and decreasing Mg#, while less evolved mare units, characterized by higher LCP abundances, retain higher Mg# and lower FeO content. In the new maps, the localized variations in mineral abundances are possibly related to subsurface materials excavated by impact events, highland ejecta deposits, and space weathering.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 348-360"},"PeriodicalIF":10.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A robust framework for mapping complex cropping patterns: The first national-scale 10 m map with 10 crops in China using Sentinel 1/2 images","authors":"Bingwen Qiu ,&nbsp;Fangzheng Wu ,&nbsp;Xiang Hu ,&nbsp;Peng Yang ,&nbsp;Wenbin Wu ,&nbsp;Jin Chen ,&nbsp;Xuehong Chen ,&nbsp;Liyin He ,&nbsp;Berry Joe ,&nbsp;Francesco N. Tubiello ,&nbsp;Jianping Qian ,&nbsp;Laigang Wang","doi":"10.1016/j.isprsjprs.2025.04.012","DOIUrl":"10.1016/j.isprsjprs.2025.04.012","url":null,"abstract":"<div><div>Complex cropping patterns with crop diversity are an underexploited treasure for global food security. However, significant methodological and dataset gaps in fully characterizing cropland cultivated with multiple crops and rotation sequences hinder our ability to understand and promote sustainable agricultural systems. Existing crop mapping models are challenged by the deficiency of ground reference data and the limited transferability capabilities across large spatial domains. This study aimed to fill these gaps by proposing a robust Complex Cropping Pattern Mapping framework (CCPM) capable of national-scale automatic applications using the Sentinel-1 SAR and Sentinel-2 MSI time series datasets. The CCPM framework addresses these challenges by integrating knowledge-based approaches &amp; data-driven algorithms (Dual-driven model) and Phenological Normalization. The CCPM framework was implemented over conterminous China with complex cropping systems dominated by smallholder farms, and the first national-scale 10-m Cropping pattern map with descriptions of cropping intensity and 10 crops in China (ChinaCP-T10) in 2020 was produced. The efficiency of the CCPM framework was validated when evaluated by 18,706 ground-truth reference datasets, with an overall accuracy of 91.47 %. Comparisons with existing crop data products revealed that the ChinaCP-T10 offered more comprehensive and consistent information on diverse cropping patterns. Dominant cropping patterns diversified from single maize in northern China, winter wheat-maize in North China Plain, single oilseeds in Western China, to single rice or double rice in Southern China. The key cropping patterns changed from double-grain cropping, single grain to single cash cropping with increasing altitudes. There were 151,744 km² planted areas of double grain cropping patterns in China, and multiple cropping accounted for 36.1 % of grain cultivated area nationally. Over 80 % of grain production was mainly implemented at lower altitudes as the Non-Grain Production (NGP) ratio enhanced from 32 % within elevations below 200 m to over 70 % among elevations above 700 m. Consistent datasets on complex cropping patterns are essential, given the significant roles of diversification and crop rotations in sustainable agriculture and the frequently observed inconsistencies in existing crop data products based on thematic mapping.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 361-381"},"PeriodicalIF":10.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the consistency and stability of vegetation biophysical variables retrievals from Landsat-8/9 and Sentinel-2","authors":"Najib Djamai ,&nbsp;Richard Fernandes ,&nbsp;Lixin Sun ,&nbsp;Gang Hong ,&nbsp;Luke A. Brown ,&nbsp;Harry Morris ,&nbsp;Jadu Dash","doi":"10.1016/j.isprsjprs.2025.04.006","DOIUrl":"10.1016/j.isprsjprs.2025.04.006","url":null,"abstract":"<div><div>Systematic decametric resolution global mapping of vegetation biophysical variables, including fraction of absorbed photosynthetically active radiation (fAPAR), fraction of vegetation cover (fCOVER), and leaf area index (LAI), is required to support various activities, including climate adaptation, crop management, biodiversity monitoring, and ecosystem assessments. The Canada Centre for Remote Sensing (CCRS) version of the Simplified Level 2 Prototype Processor (SL2P-CCRS) enables global mapping of these variables using freely available medium resolution multispectral satellite data from Sentinel-2 (S2) and Landsat-8/9 (LS) data. In this study, fiducial reference measurements (RMs) from the National Ecological Observatory Network (NEON) supplemented with regional measurements from CCRS were used to evaluate the consistency between SL2P-CCRS estimates of fAPAR, fCOVER and LAI from LS and S2 data and to quantify their temporal stability. SL2P-CCRS estimates of fCOVER (Accuracy (A) ∼ 0.03, Uncertainty (U) ∼ 0.13) and fAPAR (A ∼ −0.03, U ∼ 0.13) from LS and S2 were unbiased, and generally similar between sensors, based on 6569 LS-RMs and 4932 S2-RMs matchups. However, LAI estimates, especially for woody wetlands, deciduous forest, and mixed forest, were underestimated, with better estimates obtained using S2 (A ∼ −0.33, U ∼ 0.98) than LS (A ∼ −0.43, U ∼ 1.13). For all variables, SL2P-CCRS LS estimates were highly correlated to S2 estimates overall (R2 0.80 to 0.82) but up to 35 % lower for LAI over broadleaf and mixed forests and between lower 10 % and 20 % otherwise. The inter-annual stability of SL2P-CCRS estimates from both LS and S2 fell within the Global Climate Observing System (GCOS) requirements with the mean (standard deviation) values of −0.01 yr⁻¹ (0.06 yr⁻¹) for LS LAI, 0.02 yr⁻¹ (0.09 yr⁻¹) for S2 LAI, and 0 yr⁻¹ (0.01 yr⁻¹) for fCOVER and fAPAR from both LS and S2. The stability of both S2 and LS vegetation biophysical products indicate that are well suited for quantify the physical response of vegetation to climate variability, disturbances and regeneration.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 329-347"},"PeriodicalIF":10.6,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RoIPoly: Vectorized building outline extraction using vertex and logit embeddings","authors":"Weiqin Jiao,&nbsp;Hao Cheng,&nbsp;George Vosselman,&nbsp;Claudio Persello","doi":"10.1016/j.isprsjprs.2025.03.030","DOIUrl":"10.1016/j.isprsjprs.2025.03.030","url":null,"abstract":"<div><div>Polygonal building outlines are crucial for geographic and cartographic applications. The existing approaches for outline extraction from aerial or satellite imagery are typically decomposed into subtasks, <em>e.g.,</em> building masking and vectorization, or treat this task as a sequence-to-sequence prediction of ordered vertices. The former lacks efficiency, and the latter often generates redundant vertices, both resulting in suboptimal performance. To handle these issues, we propose a novel Region-of-Interest (RoI) query-based approach called RoIPoly. Specifically, we formulate each vertex as a query and constrain the query attention on the most relevant regions of a potential building, yielding reduced computational overhead and more efficient vertex-level interaction. Moreover, we introduce a novel learnable logit embedding to facilitate vertex classification on the attention map; thus, no post-processing is needed for redundant vertex removal. We evaluated our method on the vectorized building outline extraction dataset CrowdAI and the 2D floorplan reconstruction dataset Structured3D. On the CrowdAI dataset, RoIPoly with a ResNet50 backbone outperforms existing methods with the same or better backbones on most MS-COCO metrics, especially on small buildings, and achieves competitive results in polygon quality and vertex redundancy without any post-processing. On the Structured3D dataset, our method achieves the second-best performance on most metrics among existing methods dedicated to 2D floorplan reconstruction, demonstrating our cross-domain generalization capability. The code is available at: <span><span>https://github.com/HeinzJiao/RoIPoly</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 317-328"},"PeriodicalIF":10.6,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MMFF: Multiview and multi-level feature fusion method within limited sample conditions for SAR image target recognition","authors":"Benyuan Lv ,&nbsp;Ying Luo ,&nbsp;Jiacheng Ni ,&nbsp;Siyuan Zhao ,&nbsp;Jia Liang ,&nbsp;Yingxi Liu ,&nbsp;Qun Zhang","doi":"10.1016/j.isprsjprs.2025.03.010","DOIUrl":"10.1016/j.isprsjprs.2025.03.010","url":null,"abstract":"<div><div>The fusion of SAR image features from multiple views can effectively improve the recognition performance of SAR ATR tasks. However, when the number of raw samples in SAR images is limited, multiple fusions of SAR image features from different views of the same class may result in significant feature redundancy, causing overfitting of the model. To solve those problems, we propose a multiview and multi-level feature fusion (MMFF) method that can extract richer features from extremely limited raw data. Firstly, we design a new multiview feature fusion (NMFF) module to reduce feature redundancy generated by fusing features from the same class but from different views. This module uses multiple feature fusion methods to fuse features from different views, effectively reducing feature redundancy and alleviating model overfitting. Then, we design a multiview multi-class random feature extraction (MMRFE) module to extract inter-class separability features and intra-class similarity features and fuse them with multiview features. The MMRFE module enables the network to learn inter-class separability between different classes and intra-class similarity between the same classes, thereby improving the network’s recognition ability in extremely limited data. Finally, to further increase inter-class separability and intra-class similarity, we design a coarse classifier to perform coarse classification on inter-class separability features and intra-class similarity features. The coarse classifier increases inter-class separability and intra-class similarity by calculating classification loss to affect updating network parameters. Experimental results demonstrate that when trained with 10 SAR images per class, our algorithm achieves recognition rates of 92.53 % and 80.50 % on the MSTAR dataset and Civilian Vehicle dataset, respectively, outperforming state-of-the-art methods by at least 3.2 % and 3.94 % in classification accuracy.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 302-316"},"PeriodicalIF":10.6,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliable-loc: Robust sequential LiDAR global localization in large-scale street scenes based on verifiable cues","authors":"Xianghong Zou ,&nbsp;Jianping Li ,&nbsp;Weitong Wu ,&nbsp;Fuxun Liang ,&nbsp;Bisheng Yang ,&nbsp;Zhen Dong","doi":"10.1016/j.isprsjprs.2025.03.029","DOIUrl":"10.1016/j.isprsjprs.2025.03.029","url":null,"abstract":"<div><div>Wearable laser scanning (WLS) system has the advantages of flexibility and portability. It can be used for determining the user’s path within a prior map, which is a huge demand for applications in pedestrian navigation, collaborative mapping, augmented reality, and emergency rescue. However, existing LiDAR-based global localization methods suffer from insufficient robustness, especially in complex large-scale outdoor scenes with insufficient features and incomplete coverage of the prior map. To address such challenges, we propose LiDAR-based reliable global localization (Reliable-loc) exploiting the verifiable cues in the sequential LiDAR data. First, we propose a Monte Carlo Localization (MCL) based on spatially verifiable cues, utilizing the rich information embedded in local features to adjust the particles’ weights hence avoiding the particles converging to erroneous regions. Second, we propose a localization status monitoring mechanism guided by the sequential pose uncertainties and adaptively switching the localization mode using the temporal verifiable cues to avoid the crash of the localization system. To validate the proposed Reliable-loc, comprehensive experiments have been conducted on a large-scale heterogeneous point cloud dataset consisting of high-precision vehicle-mounted mobile laser scanning (MLS) point clouds and helmet-mounted WLS point clouds, which cover various street scenes with a length of over 30 km. The experimental results indicate that Reliable-loc exhibits high robustness, accuracy, and efficiency in large-scale, complex street scenes, with a position accuracy of ±2.91 m, yaw accuracy of ±3.74 degrees, and achieves real-time performance. For the code and detailed experimental results, please refer to <span><span>https://github.com/zouxianghong/Reliable-loc</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 287-301"},"PeriodicalIF":10.6,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Saliency supervised masked autoencoder pretrained salient location mining network for remote sensing image salient object detection","authors":"Yuxiang Fu ,&nbsp;Wei Fang ,&nbsp;Victor S. Sheng","doi":"10.1016/j.isprsjprs.2025.03.025","DOIUrl":"10.1016/j.isprsjprs.2025.03.025","url":null,"abstract":"<div><div>Remote sensing image salient object detection (RSI-SOD), as an emerging topic in computer vision, has significant applications across various sectors, such as urban planning, environmental monitoring and disaster management, etc. In recent years, RSI-SOD has seen significant advancements, largely due to advanced representation learning methods and better architectures, such as convolutional neural networks and vision transformers. While current methods predominantly rely on supervised learning, there is potential for enhancement through self-supervised learning approaches, like masked autoencoder. However, we observed that the conventional use of masked autoencoder for pretraining encoders through masked image reconstruction yields subpar results in the context of RSI-SOD. To this end, we propose a novel approach: saliency supervised masked autoencoder (SSMAE) and a corresponding salient location mining network (SLMNet), which is pretrained by SSMAE for the task of RSI-SOD. SSMAE first uses masked autoencoder to reconstruct the masked image, and then employs SLMNet to predict saliency map from the reconstructed image, where saliency supervision is adopted to enable SLMNet to learn robust saliency prior knowledge. SLMNet has three major components: encoder, salient location mining module (SLMM) and the decoder. Specifically, SLMM employs residual multi-level fusion structure to mine the locations of salient objects from multi-scale features produced by the encoder. Later, the decoder fuses the multi-level features from SLMM and encoder to generate the prediction results. Comprehensive experiments on three public datasets demonstrate that our proposed method surpasses the state-of-the-art methods. Code is available at: <span><span>https://github.com/Voruarn/SLMNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"224 ","pages":"Pages 222-234"},"PeriodicalIF":10.6,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}