ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"First high temporal resolution retrievals of AOD over shallow and turbid coastal waters for Himawari-8","authors":"Yi Wang ,&nbsp;Zibo You ,&nbsp;Lunche Wang ,&nbsp;Jun Wang ,&nbsp;Meng Zhou ,&nbsp;Minghui Tao ,&nbsp;Jhoon Kim","doi":"10.1016/j.isprsjprs.2025.07.027","DOIUrl":"10.1016/j.isprsjprs.2025.07.027","url":null,"abstract":"<div><div>Although the operational Himawar-8 Aerosol Retrieval Product (ARP) can resolve diurnal variation of aerosol loading, the ARP Aerosol Optical Depth (AOD) retrievals are significantly overestimated over Shallow and Turbid Coastal Waters (STCW) as water-leaving radiance is not explicitly considered in the retrieval process. Taking the advantage that 2.3 μm water-leaving radiance from STCW is insignificant, we developed a Himawari-8 Coastal Water AOD retrieval approach (CW) by using 2.3 μm Top of Atmosphere (TOA) reflectance and the aerosol properties of the nearest open ocean pixel. Unlike the abnormally large ARP AOD retrievals over STCW, the CW algorithm yields a smooth transition among land, coast, and open ocean over Asia and increases the number of AOD retrievals by more than 10 %, depending on the variation of coastal regions. Validation against Marine Aerosol Network measurements over STCW show that 65.5 % of CW retrievals are within the expected error envelope (± (0.05 + 15 %AOD)), compared with 56.5 % for ARP, and this improvement is independent of observational geometry and terrain. Moreover, CW AOD retrievals over STCW can well capture the diurnal variation observed by Aerosol Robotic Network while ARP cannot. As to seasonal variation, CW AOD over the STCW of East China increases in spring and peaks in June, while the coverage of abnormally large ARP AOD follows the temporal change of turbid coastal waters area with a maximum occurring in winter.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 603-612"},"PeriodicalIF":12.2,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738782","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":"Enhancing LiDAR place recognition in challenging environments using Retrieval-Trigger-Reranking paradigm","authors":"Zhenghua Zhang ,&nbsp;Zhihua Xu ,&nbsp;Hu Liu ,&nbsp;Xuan Wang ,&nbsp;Qipeng Li ,&nbsp;Xiaoxiang Cao ,&nbsp;Guoliang Chen","doi":"10.1016/j.isprsjprs.2025.07.036","DOIUrl":"10.1016/j.isprsjprs.2025.07.036","url":null,"abstract":"<div><div>LiDAR place recognition (LPR) plays a critical role in simultaneous localization and mapping (SLAM) and autonomous driving systems. However, the common separation between offline database construction and online localization introduces challenges such as rotational variance, sensor discrepancies, and long-term environmental changes. Existing methods relying on fixed-length global descriptors often struggle in such scenarios due to their inherently limited capacity to encode comprehensive environmental information. To address these challenges, we propose RTR-Net, a novel framework based on Retrieval-Trigger-Reranking paradigm, to enhance LPR performance in challenging environments. The framework operates in three phases: (1) Retrieval, where a lightweight backbone generates global descriptors and local regional features for initial candidate selection; (2) Trigger, a training-free module that assesses spatial consistency between query and candidates to activate reranking only when necessary; and (3) Reranking, which refines rankings by fusing local features, global descriptors, and spatial consistency scores via spatial and channel attention mechanisms. Additionally, a regional sampling method is proposed to mitigate field-of-view (FoV) discrepancies across heterogeneous LiDAR sensors. Comprehensive evaluations on four large-scale datasets (Oxford RobotCar, NUS Inhouse, HeLiPR, MulRan) demonstrate that RTR-Net not only achieves state-of-the-art results but also stands out as a versatile, plug-and-play module. It is compatible with existing LPR methods—whether region-based or sparse voxelization-based—enhancing their localization accuracy in challenging conditions without requiring structural modifications or retraining. Further experiments on heterogeneous LPR and long-term environmental variations validate RTR-Net’s robustness, achieving leading performance across sensor types and temporal shifts. The proposed regional sampling method effectively alleviates FoV disparities, demonstrating broad applicability within current LPR frameworks.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 613-629"},"PeriodicalIF":12.2,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738715","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":"PhenoSR: Enhancing organ-level phenotyping with super-resolution RGB UAV imagery for large-scale field experiments","authors":"Ruinan Zhang ,&nbsp;Shichao Jin ,&nbsp;Yi Wang ,&nbsp;Jingrong Zang ,&nbsp;Yu Wang ,&nbsp;Ruofan Zhao ,&nbsp;Yanjun Su ,&nbsp;Jin Wu ,&nbsp;Xiao Wang ,&nbsp;Dong Jiang","doi":"10.1016/j.isprsjprs.2025.07.025","DOIUrl":"10.1016/j.isprsjprs.2025.07.025","url":null,"abstract":"<div><div>Organ-level phenotyping is critical for crop breeding and precision farming by providing information directly associated with yield and quality. Unmanned aerial vehicles (UAVs) are widely utilized in large-scale field experiments for their versatile image collection capabilities. However, RGB images captured at high altitudes often lack the resolution for accurate organ-level phenotyping, as collection efficiency is prioritized. Deep learning-based image super-resolution (SR) methods can enhance image resolution, but they usually fail to address the challenge of obtaining paired low-resolution (LR) and high-resolution (HR) data for training under field conditions. Moreover, the varying significance of organ-level phenotyping across different regions in UAV images is often neglected, slowing down reconstruction. To overcome these challenges, a degradation model and a multiscale scaling strategy were proposed to generate paired datasets. Then, a semantic score was introduced to identify the significance of image regions for organ-level phenotyping. Finally, an SR algorithm (PhenoSR) based on a coarse-refined architecture was proposed to recover organ textures. PhenoSR recovered wheat organ textures in UAV images collected at flight heights ranging from 10 to 40 m. Compared to LR images, the natural image quality evaluator (NIQE) and Fréchet inception distance (FID) metrics decreased by 71.37 % and 21.53 %, respectively, while improving hyperIQA by 39.36 %. PhenoSR outperformed eight SR algorithms, achieving a 12.31 % reduction in FID and a 25.53 % improvement in hyperIQA on average. Moreover, PhenoSR enhanced organ-level wheat phenotyping tasks, such as plot segmentation, spike counting, flowering spike detection, and awn morphology identification, and can be extended to other crops and multispectral imagery. This study presents an innovative and universal technology for enhancing organ-level phenotyping accuracy and efficiency with UAV platforms, thereby accelerating the identification and utilization of crop germplasm resources.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 582-602"},"PeriodicalIF":12.2,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722949","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":"Cross-sensor adaptive semantic segmentation for mobile laser scanning point clouds based on continuous potential scene surface reconstruction","authors":"Haifeng Luo ,&nbsp;Ziyi Chen ,&nbsp;Feng Ye ,&nbsp;Tianqiang Huang ,&nbsp;Hanxian He ,&nbsp;Wenyan Hu","doi":"10.1016/j.isprsjprs.2025.07.021","DOIUrl":"10.1016/j.isprsjprs.2025.07.021","url":null,"abstract":"<div><div>Semantic segmentation is a fundamental task for extracting road information from mobile laser scanning (MLS) point clouds. Recently, deep learning-based methods have shown superior performance in MLS point cloud semantic segmentation. However, MLS is usually equipped with different LiDAR sensors, which leads to point-level distribution differences in point clouds. Therefore, a deep network trained on the source domain point clouds often performs poorly on the target domain point clouds. In this paper, we propose a new cross-sensor adaptive semantic segmentation for MLS point clouds based on continuous potential scene surface reconstruction. Firstly, an implicit neural representation framework is introduced to reconstruct the continuous potential scene surface for MLS point clouds. Then, the source and target domain MLS point clouds are both transformed into a canonical domain based on the continuous potential scene surfaces to achieve point-level distribution alignment. Next, an adaptive neighbor vote strategy is designed to map the source domain training label to the canonical domain and map the canonical domain semantic segmentation results to the target domain. Three MLS point cloud datasets were used to evaluate the performance of the proposed method. The experimental results indicated that our approach can effectively achieve cross-sensor adaptive semantic segmentation for MLS point clouds. An implementation of the proposed method is available at: <span><span>https://github.com/PCsFJNU/CrossSensorAdaptiveSemanticSeg</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 537-551"},"PeriodicalIF":12.2,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720976","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":"Improved multi-source remote sensing object detection network by geometry consistency constraint and Gaussian distribution alignment","authors":"Yungang Cao,&nbsp;Haibo Cheng,&nbsp;Baikai Sui,&nbsp;Yahui Zeng","doi":"10.1016/j.isprsjprs.2025.07.037","DOIUrl":"10.1016/j.isprsjprs.2025.07.037","url":null,"abstract":"<div><div>Multi-source remote sensing object detection, by combining data from different sensors, can comprehensively improve the accuracy and robustness of object detection. However, it faces challenges such as data inconsistency, domain shift, and scarcity of labeled data. Domain adaptation methods can address these challenges by aligning features between the source and target domains, reducing domain shift, and enhancing the model’s generalization ability, thus solving the discrepancies in multi-source data. However, existing domain adaptation object detection methods insufficiently utilize shallow geometric features that are important for geometric consistency, and traditional methods that use adversarial networks for feature alignment often leading to insufficient alignment capability and training instability. To address the insufficient utilization of geometric information in existing methods and considering that shallow features contain abundant geometric information (e.g., points, lines, and surfaces), this paper proposes a shallow feature alignment method based on geometric consistency (GCFA), using shallow features as alignment cues. This method achieves effective feature alignment through partition calculation and weighted loss processing. Furthermore, to tackle the problems of insufficient alignment capability and training instability in the network, we introduce a feature alignment method based on Gaussian distribution (GDFA). This method directly aligns the feature distributions of the source and target domains by leveraging the mean and standard deviation, thereby enhancing the alignment capability of the network. And we can update the network directly through the loss function, without the need for adversarial networks or gradient reversal layers, thus avoiding potential training instability issues. In addition, we design a pseudo-labels refinement module (PLRM) that combines dynamic threshold select and pseudo-labels class weighting to enhance the constraint ability of the model’s unsupervised branch. In order to verify the effectiveness of the method proposed in this paper, we conducted extensive experiments on datasets such as DOTA, DIOR, WHU, and Levir. On the DOTA and DIOR datasets, the proposed method achieves a 3.09 % improvement in mAP50 compared to the best baseline method. On the WHU dataset, it shows a 2.30 % improvement over the best method, and on the Levir and SSDD datasets, the proposed method outperforms the best method by 2.13 %.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 566-581"},"PeriodicalIF":12.2,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720979","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-demand, semantic EO data cubes – knowledge-based, semantic querying of multimodal data for mesoscale analyses anywhere on Earth","authors":"Felix Kröber ,&nbsp;Martin Sudmanns ,&nbsp;Lorena Abad ,&nbsp;Dirk Tiede","doi":"10.1016/j.isprsjprs.2025.07.015","DOIUrl":"10.1016/j.isprsjprs.2025.07.015","url":null,"abstract":"<div><div>With the daily increasing amount of available Earth Observation (EO) data, the importance of processing frameworks that allow users to focus on the actual analysis of the data instead of the technical and conceptual complexity of data access and integration is growing. In this context, we present a Python-based implementation of ad-hoc data cubes to perform big EO data analysis in a few lines of code. In contrast to existing data cube frameworks, our semantic, knowledge-based approach enables data to be processed beyond its simple numerical representation, with structured integration and communication of expert knowledge from the relevant domains. The technical foundations for this are threefold: Firstly, on-demand fetching of data in cloud-optimized formats via SpatioTemporal Asset Catalog (STAC) standardized metadata to regularized three-dimensional data cubes. Secondly, provision of a semantic language along with an analysis structure that enables to address data and create knowledge-based models. And thirdly, chunking and parallelization mechanisms to execute the created models in a scalable and efficient manner. From the user’s point of view, big EO data archives can be analyzed both on local, commercially available devices and on cloud-based processing infrastructures without being tied to a specific platform. Visualization options for models enable effective exchange with end users and domain experts regarding the design of analyses. The concrete benefits of the presented framework are demonstrated using two application examples relevant for environmental monitoring: querying cloud-free data and analyzing the extent of forest disturbance areas.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 552-565"},"PeriodicalIF":12.2,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720978","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 novel knowledge-based multi-modal semi-supervised framework for 3D change detection and mining volume estimation in open-pit mines using GF7 satellite images","authors":"Dehui Dong ,&nbsp;Dongping Ming ,&nbsp;Miao Li ,&nbsp;Hongzhen Xu ,&nbsp;Yanfei Wei ,&nbsp;Ming Huang","doi":"10.1016/j.isprsjprs.2025.07.034","DOIUrl":"10.1016/j.isprsjprs.2025.07.034","url":null,"abstract":"<div><div>The detection of three-dimensional (3D) terrain changes in open-pit mines is of great significance for resource management and environmental monitoring. Obtaining multi-temporal, high-quality, large-scale elevation data is very difficult, and the data used in previous studies were insufficient to support large-scale 3D change detection in mining areas. The emergence of the GF7 satellite image has resolved this issue. This paper proposes a framework for 3D change detection in large-scale, few-shot mining areas using GF7 satellite images, which simultaneously outputs the mine’s two-dimensional (2D) and 3D change detection results. From this, it can further estimate the mining volume in the mine. The framework builds a remote sensing knowledge-based multi-modal, semi-supervised mine recognition model, which fuses complementary multi-modal information of the mine from the input DSM and imagery through feature alignment and cross-modal attention mechanisms. It also employs a strong–weak consistency regularization strategy, which integrates spectral and terrain knowledge from unlabeled data to learn the feature differences between the mine and background elements and the heterogeneity of boundaries, thereby enhancing the model’s sensitivity to mine-specific features. The model’s pre- and post-temporal mine predictions are differenced and overlaid with DSM to obtain 2D and 3D change detection results. Based on this, the mining volume is estimated using the difference integration method. Multiple comparison and ablation experiments validate the accuracy of the 2D and 3D change detection, as well as its robustness in dealing with different seasonal change scenarios and severely imbalanced class distributions. The study is expected to provide a reference for monitoring the mining progress of mineral resources. The code of the HD-Net will be made available freely at <span><span>https://github.com/dongdhcugb/KMS-RNet.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 519-536"},"PeriodicalIF":12.2,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720975","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":"Leak detection using thermal imagery: Deep learning versus traditional computer vision state-of-the-art","authors":"Elena Vollmer,&nbsp;Julian Ruck,&nbsp;Rebekka Volk,&nbsp;Frank Schultmann","doi":"10.1016/j.isprsjprs.2025.06.006","DOIUrl":"10.1016/j.isprsjprs.2025.06.006","url":null,"abstract":"<div><div>As a cornerstone of climate-neutral heat supply in urban areas, district heating systems require monitoring to detect and mitigate leaks in their subterranean pipelines. Recent research has focused on an approach involving thermography, where leaks are detected as hot-spots in remote sensing imagery. To this end, various traditional computer vision algorithms have been implemented to automate anomaly detection.</div><div>This paper pursues a new approach that has so far received little attention in the context of leak detection in district heating pipelines: deep learning, specifically supervised semantic segmentation. By creating a generalisable, multi-stage training procedure to tackle the prevalent limited dataset problem, various architectures are tailored to this anomaly detection task, of which the SegFormer-B2 with Tversky loss is found to perform best. Via comprehensive quantitative, qualitative, explainable AI, and holistic evaluation, the model is assessed and compared to state-of-the-art traditional algorithmic alternatives. It is found to excel, outperforming previous intersection over union scores by almost 10<!--> <!-->%pt and maintaining a high precision with little detriment to recall and detection rate.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 505-518"},"PeriodicalIF":12.2,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721083","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":"Mapping snow-covered forest albedo via hybrid radiative transfer and machine learning across Northern Hemisphere","authors":"Siyong Chen ,&nbsp;Pengfeng Xiao ,&nbsp;Xueliang Zhang ,&nbsp;Petri Pellikka ,&nbsp;Hao Liu ,&nbsp;Yantao Liu","doi":"10.1016/j.isprsjprs.2025.07.033","DOIUrl":"10.1016/j.isprsjprs.2025.07.033","url":null,"abstract":"<div><div>Snow-covered forests are widely distributed in the Northern Hemisphere, and their albedo significantly influences forest warming effects, radiative balance, and climate change. However, estimating snow-covered forest albedo is challenging due to the complex interactions between the snow and canopy. Current algorithms often rely on snow-free forest models or linear weighting of snow and forest components. These simplified forward models result in significant errors in the bidirectional reflectance simulation of snow-covered forests. Meanwhile, the albedo retrieval process is computationally intensive, especially when lookup tables or optimization algorithms are employed. Thus, we propose a novel albedo retrieval framework that integrates the strengths of snow-covered forest radiative transfer model with the efficiency of machine learning methods. This framework achieves three key advancements: (1) the snow-covered forest bidirectional reflectance (SFBR2) model is extended to sloped terrain to reduce the reflectance simulation errors; (2) the representativeness and accuracy of training datasets are improved by combining satellite observations with SFBR2-retrieved albedo; and (3) Random Forest model is utilized on the Google Earth Engine (GEE) platform to enable rapid retrieval of snow-covered forest albedo. As a result, a snow-covered forest albedo product for the Northern Hemisphere from 2001 to 2022 is successfully generated. Validation against albedo observations from flux stations demonstrates that our retrieval framework achieves higher accuracy (R² ≥ 0.775 and RMSE ≤ 0.037) than the Moderate Resolution Imaging Spectroradiometer (MODIS) and Global LAnd Surface Satellites (GLASS) products. This highlights its potential to further enhance our understanding of radiative balance and climate change in snow-covered forests.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 489-504"},"PeriodicalIF":10.6,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714457","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":"PL4U: Automated plane-based uncertainty evaluation and reduction method for indoor Mobile Laser Scanning systems","authors":"Ziyang Xu ,&nbsp;Maximilian Hackl ,&nbsp;Christoph Holst","doi":"10.1016/j.isprsjprs.2025.07.019","DOIUrl":"10.1016/j.isprsjprs.2025.07.019","url":null,"abstract":"<div><div>Mobile Laser Scanning (MLS) systems have obtained remarkable achievements in data acquisition and various scenario applications over the past decades. However, the investigation about their uncertainty evaluation has followed a different trend, significantly lagging behind the development pace of current MLS systems. A lack of automated, reliable, cost-effective, and commonly acceptable uncertainty evaluation solutions is evident. This paper presents an automated plane-based evaluation and reduction method for trajectory estimation errors of indoor MLS systems. The complete process can be split into plane correspondence establishment, parameter estimation and uncertainty reduction. The plane correspondence is mainly established by plane extraction, plane selection, plane matching, and matching verification. Then, a data-driven plane-based continuous random sampling estimation strategy is utilized to estimate 6 DoF trajectory estimation errors. Ultimately, a frame-wise error evaluation and reduction is achieved. For validation, two independent experiments are conducted, each covering distinct indoor scenarios and point clouds exhibiting different quality characteristics. The MLS point clouds evaluated in these experiments vary significantly in terms of noise levels and the presence of outliers, thus reflecting two common scenarios encountered in practical applications. Two independent experiments demonstrate that the results estimated by our method are highly consistent with the reference value and our method outperforms existing leading methods regarding overall effectiveness and robustness.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"228 ","pages":"Pages 467-488"},"PeriodicalIF":10.6,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144712939","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}