ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"MOSAIC-Tracker: Mutual-enhanced Occlusion-aware Spatiotemporal Adaptive Identity Consistency network for aerial multi-object tracking","authors":"Jian Zou ,&nbsp;Wei Zhang ,&nbsp;Qiang Li ,&nbsp;Qi Wang","doi":"10.1016/j.isprsjprs.2025.08.013","DOIUrl":"10.1016/j.isprsjprs.2025.08.013","url":null,"abstract":"<div><div>Multi-Object Tracking (MOT) in aerial imagery remains challenging due to small object sizes, occlusions, and dynamic environments. Existing approaches predominantly rely on high precision detection and Re ID matching but neglect spatiotemporal cues and global temporal modeling of occlusion. Their static confidence weighting during association cannot adapt to real time detector confidence fluctuations, resulting in mismatches and ID switches. To alleviate these limitations, we propose MOSAIC-Tracker, a Mutual-enhanced Occlusion-aware Spatiotemporal Adaptive Identity Conservation Network with three key dimensions. First, a Spatiotemporal Occlusion Enhancement (STOE) module integrates multi-frame temporal dependencies to model global motion patterns and local dynamic features, mitigating identity switches during occlusions. Then, an Adaptive Multi-scale Feature Enhancement (AMFE) mechanism combines a Local Enhancement Mechanism with multi-scale feature aggregation to improve small object discrimination. Finally, a Dynamic Confidence Matrix Adjustment (DCMA) strategy adaptively weights detection confidence in trajectory matching to minimize association errors. Together, the three modules reduce occlusion-induced identity switches. Extensive evaluations on UAVDT and VisDrone2019 datasets demonstrate advanced performance. The code is released at: <span><span>https://github.com/aJanm/MOSAIC-Tracker</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 138-154"},"PeriodicalIF":12.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903651","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":"Unveiling diurnal aerosol layer height variability from space using deep learning","authors":"Yulong Fan ,&nbsp;Lin Sun ,&nbsp;Zhihui Wang ,&nbsp;Shulin Pang ,&nbsp;Jing Wei","doi":"10.1016/j.isprsjprs.2025.08.021","DOIUrl":"10.1016/j.isprsjprs.2025.08.021","url":null,"abstract":"<div><div>The vertical distribution of aerosols is crucial for extensive climate and environment studies but is severely constrained by the limited availability of ground-based observations and the low spatiotemporal resolutions of Lidar satellite measurements. Multi-spectral passive satellites offer the potential to address these gaps by providing large-scale, high-temporal-resolution observations, making them a promising tool for enhancing current aerosol vertical distribution data. However, traditional methods, which rely heavily on physical assumptions and prior knowledge, often struggle to deliver robust and accurate aerosol vertical profiles. Thus, we develop a novel retrieval framework that combines two advanced deep-learning models, locally-feature-focused Transformer and globally-feature-focused Fully Connected Neural Network (FCNN), referred to as TF-FCNN, to estimate hourly aerosol distributions at different heights (i.e., 0.01–1 km, 1–2 km, and 2–3 km) with 2-km spatial resolution, using multi-source satellite data, including Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO), Himawari-8 and Moderate Resolution Imaging Spectroradiometer (MODIS). This hybrid framework is thoroughly analyzed using an eXplainable Artificial Intelligence (XAI)-based SHapley Additive exPlanations (SHAP) approach, which reveals that shortwave bands and brightness temperature are the most influential features, contributing approximately 63 % to the model predictions. Validation results demonstrate that the model provides reliable hourly aerosol vertical distributions across different heights in Australia, achieving high overall sample-based cross-validation coefficients of determination (CV-R²) ranging from 0.81 to 0.90 (average = 0.88). Our hourly retrievals indicate higher aerosol loadings at lower altitudes (0.01–1 km) than higher ones (1–2 km and 2–3 km) in most areas, likely due to significant anthropogenic and natural emissions from the ground. Furthermore, we observe substantial increases in aerosol concentrations over time and enhanced diurnal variations across altitudes during highly polluted cases, including urban haze and wildfires. These unique insights into the spatial distribution of aerosol vertical layers are crucial for effective air pollution control and management.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 211-222"},"PeriodicalIF":12.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908140","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-modal 2D-3D feature matching: simultaneous local feature description and detection across images and point clouds","authors":"Wei Ma ,&nbsp;Yucheng Huang ,&nbsp;Shengjun Tang ,&nbsp;Xianwei Zheng ,&nbsp;Zhen Dong ,&nbsp;Liang Ge ,&nbsp;Jianping Pan ,&nbsp;Qingquan Li ,&nbsp;Bing Wang","doi":"10.1016/j.isprsjprs.2025.08.016","DOIUrl":"10.1016/j.isprsjprs.2025.08.016","url":null,"abstract":"<div><div>Establishing correspondences between 2D images and 3D models is essential for precise 3D modeling and accurate positioning. However, widely adopted techniques for aligning 2D images with 3D features heavily depend on dense 3D reconstructions, which not only incur significant computational demands but also tend to exhibit reduced accuracy in texture-poor environments. In this study, we propose a novel method that combines local feature description and detection to enable direct and automatic alignment of 2D images with 3D models. Our approach utilizes a twin convolutional network architecture to process images and 3D data, generating respective feature maps. To address the non-uniform distribution of pixel and spatial point densities, we introduce an ultra-wide perception mechanism to expand the receptive field of image convolution kernels. Next, we apply a non-local maximum suppression criterion to concurrently evaluate the salience of pixels and 3D points. Additionally, we design an adaptive weight optimization loss function that dynamically guides learning objectives toward sample similarity. We rigorously validate our approach on multiple datasets, and our findings demonstrate successful co-extraction of cross-modal feature points. Through comprehensive 2D-3D feature matching experiments, we benchmark our method against several state-of-the-art techniques from recent literature. The results show that our method outperforms nearly all evaluated metrics, underscoring its effectiveness.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 155-169"},"PeriodicalIF":12.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903652","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":"Research on adaptive ocean remote sensing target detection framework: An efficient solution based on the broad learning system","authors":"Guangxi Cui ,&nbsp;Ka-Veng Yuen ,&nbsp;Zhongya Cai ,&nbsp;Zhiqiang Liu ,&nbsp;Guangtao Zhang","doi":"10.1016/j.isprsjprs.2025.08.020","DOIUrl":"10.1016/j.isprsjprs.2025.08.020","url":null,"abstract":"<div><div>With the rapid advancement of ocean satellite remote sensing technology and the growing availability of ocean observation data, the demand for efficient and highly adaptable target detection techniques has become increasingly urgent. To address this challenge, this study introduced an adaptive ocean remote sensing target detection framework based on the Broad Learning System (BLS), characterized by its shallow architecture and rapid incremental learning capabilities. The framework, named Auto-Features-BLS (AF-BLS), automatically and efficiently selects the optimal combination of pretrained feature extractors from diverse machine learning models via the Hyperopt library and processes them using BLS to detect ocean targets. The AF-BLS model was evaluated on 12 types of ocean targets, including internal waves, ships, rain cells, and ocean fronts. Experimental results demonstrate that AF-BLS exhibits strong robustness and flexibility in detecting these targets, outperforming traditional models with an average Accuracy of 99.19%, an average Precision of 98.51%, an average Recall of 98.15%, an average F1-Scores of 98.33%, and an average Matthews Correlation Coefficient (MCC) of 96.33% on the testing set. Furthermore, the AF-BLS model trained on CPU significantly improves overall efficiency, with training speed nearly five times faster and inference speed more than three times faster than conventional GPU-based models, highlighting its practicality for deployment in resource-constrained or real-time scenarios. Additionally, the study used internal waves as an example to validate the model’s generalization performance across untrained sensors and global applications. The proposed AF-BLS model offers an efficient and highly adaptable solution for ocean remote sensing target detection.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 188-210"},"PeriodicalIF":12.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908139","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":"An automated method for estimating fractional vegetation cover from camera-based field measurements: Saturation-adaptive threshold for ExG (SATE)","authors":"Xuemiao Ye ,&nbsp;Wenquan Zhu ,&nbsp;Ruoyang Liu ,&nbsp;Bangke He ,&nbsp;Xinyi Yang ,&nbsp;Cenliang Zhao","doi":"10.1016/j.isprsjprs.2025.08.017","DOIUrl":"10.1016/j.isprsjprs.2025.08.017","url":null,"abstract":"<div><div>Fractional vegetation cover (FVC) is a crucial metric for assessing vegetation cover on the Earth’s surface. The excess green index (ExG), derived from visible true-color RGB images, is widely recognized as a reliable metric for identifying green vegetation. However, the threshold to distinguish vegetation from background via ExG is highly sensitive to variations in illumination, limiting its robustness in real-world applications. Traditional thresholding methods, such as the bimodal thresholding method, maximum entropy thresholding method, and Otsu’s method, perform well under uniform illumination conditions but often fail to achieve high vegetation identification accuracy in scenarios with uneven illumination. Previous studies have shown that saturation (S) is strongly correlated with illumination intensity and can serve as an effective indicator of illumination variations. Specifically, under strong illumination conditions, both vegetation and non-vegetation appear more vivid, resulting in higher S values. For vegetation, the green-band digital number (DN) value increases more sharply than that of the red and blue bands, resulting in a notable rise in ExG. In comparison, non-vegetation like soil shows only a slight green-band increase, producing a smaller ExG gain. This contrast in ExG between the two surfaces becomes more distinct, so a higher segmentation threshold is required. Conversely, weak illumination conditions lead to lower S values and more uniform DN reductions across surface types, which diminishes ExG contrast and necessitates a lower threshold. Building upon this insight, this study introduced a novel method for automated vegetation coverage extraction: the saturation-adaptive threshold for ExG (SATE). SATE dynamically determines the optimal segmentation threshold for ExG on a pixel-by-pixel basis on the S value, then identifies vegetation pixels by comparing the ExG value of each pixel with its corresponding threshold, and finally calculates the FVC, thereby enhancing the adaptability to diverse illumination conditions. To validate its effectiveness, SATE was tested using 100 high-resolution unmanned aerial vehicle (UAV) red‒green-blue (RGB) images collected from five diverse regions across China, covering a range of illumination conditions, vegetation types, and complex land cover scenarios. The experimental results demonstrated that SATE can effectively address the challenges posed by uneven illumination, achieving an average vegetation recognition accuracy of 91–94 %. For vegetation identification, the performance of SATE combined with ExG surpassed that of traditional thresholding methods, including the bimodal thresholding method (86.4 %), maximum entropy thresholding method (67.0 %), and Otsu’s method (66.5 %). Moreover, SATE combined with ExG achieved an accuracy comparable to that of the manual thresholding method (95 %) while eliminating the need for subjective intervention, thus enhancing the automation and ","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 170-187"},"PeriodicalIF":12.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904138","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":"Scale-aware co-visible region detection for image matching","authors":"Xu Pan ,&nbsp;Zimin Xia ,&nbsp;Xianwei Zheng","doi":"10.1016/j.isprsjprs.2025.08.015","DOIUrl":"10.1016/j.isprsjprs.2025.08.015","url":null,"abstract":"<div><div>Matching images with significant scale differences remains a persistent challenge in photogrammetry and remote sensing. The scale discrepancy often degrades appearance consistency and introduces uncertainty in keypoint localization. While existing methods address scale variation through scale pyramids or scale-aware training, matching under significant scale differences remains an open challenge. To overcome this, we address the scale difference issue by detecting co-visible regions between image pairs and propose <strong>SCoDe</strong> (<strong>S</strong>cale-aware <strong>Co</strong>-visible region <strong>De</strong>tector), which both identifies co-visible regions and aligns their scales for highly robust, hierarchical point correspondence matching. Specifically, SCoDe employs a novel Scale Head Attention mechanism to map and correlate features across multiple scale subspaces, and uses a learnable query to aggregate scale-aware information of both images for co-visible region detection. In this way, correspondences can be established in a coarse-to-fine hierarchy, thereby mitigating semantic and localization uncertainties. Extensive experiments on three challenging datasets demonstrate that SCoDe outperforms state-of-the-art methods, improving the precision of a modern local feature matcher by 8.41%. Notably, SCoDe shows a clear advantage when handling images with drastic scale variations. Code is publicly available at <span><span>github.com/Geo-Tell/SCoDe</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 122-137"},"PeriodicalIF":12.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895084","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":"CGSL: Commonality graph structure learning for unsupervised multimodal change detection","authors":"Jianjian Xu ,&nbsp;Tongfei Liu ,&nbsp;Tao Lei ,&nbsp;Hongruixuan Chen ,&nbsp;Naoto Yokoya ,&nbsp;Zhiyong Lv ,&nbsp;Maoguo Gong","doi":"10.1016/j.isprsjprs.2025.08.010","DOIUrl":"10.1016/j.isprsjprs.2025.08.010","url":null,"abstract":"<div><div>Multimodal change detection (MCD) has attracted a great deal of attention due to its significant advantages in processing heterogeneous remote sensing images (RSIs) from different sensors (e.g., optical and synthetic aperture radar). The major challenge of MCD is that it is difficult to acquire the changed areas by directly comparing heterogeneous RSIs. Although many MCD methods have made important progress, they are still insufficient in capturing the modality-independence complex structural relationships in the feature space of heterogeneous RSIs. To this end, we propose a novel commonality graph structure learning (CGSL) for unsupervised MCD, which aims to extract potential commonality graph structural features between heterogeneous RSIs and directly compare them to detect changes. In this study, heterogeneous RSIs are first segmented and constructed as superpixel-based heterogeneous graph structural data consisting of nodes and edges. Then, the heterogeneous graphs are input into the proposed CGSL to capture the commonalities of graph structural features with modality-independence. The proposed CGSL consists of a Siamese graph encoder and two graph decoders. The Siamese graph encoder maps heterogeneous graphs into a shared space and effectively extracts potential commonality in graph structural features from heterogeneous graphs. The two graph decoders reconstruct the mapped node features as original node features to maintain consistency with the original graph features. Finally, the changes between heterogeneous RSIs can be detected by measuring the differences in commonality graph structural features using the mean squared error. In addition, we design a composite loss with regularization to guide CGSL in effectively excavating the potential commonality graph structural features between heterogeneous graphs in an unsupervised learning manner. Extensive experiments on seven MCD datasets show that the proposed CGSL outperforms the existing state-of-the-art methods, demonstrating its superior performance in MCD. The code will be available at <span><span>https://github.com/TongfeiLiu/CGSL-for-MCD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 92-106"},"PeriodicalIF":12.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895082","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":"Causal learning-driven semantic segmentation for robust coral health status identification","authors":"Jiangying Qin ,&nbsp;Ming Li ,&nbsp;Deren Li ,&nbsp;Armin Gruen ,&nbsp;Jianya Gong ,&nbsp;Xuan Liao","doi":"10.1016/j.isprsjprs.2025.08.009","DOIUrl":"10.1016/j.isprsjprs.2025.08.009","url":null,"abstract":"<div><div>Global warming is accelerating the degradation of coral reef ecosystems, making accurate monitoring of coral reef health status crucial for their protection and restoration. Traditional coral reef remote sensing monitoring primarily relies on satellite or aerial observations, which provide broad spatial coverage but lack the fine-grained capability needed to capture the detailed structure and health status of individual coral colonies. In contrast, underwater photography utilizes close-range, high-resolution image-based observation, which can be considered a non-traditional form of remote sensing, to enable fine-grained assessment of corals with varying health status at pixel level. In this context, underwater image semantic segmentation plays a vital role by extracting discriminative visual features from complex underwater imaging scenes and enabling the automated classification and identification of different coral health status, based on expert-annotated labels. This semantic information can then be used to derive corresponding ecological indicators. While deep learning-based coral image segmentation methods have been proven effective for underwater coral remote sensing monitoring tasks, challenges remain regarding their generalization ability across diverse monitoring scenarios. These challenges stem from shifts in coral image data distributions and the inherent data-driven nature of deep learning models. In this study, we introduce causal learning into coral image segmentation for the first time and propose CDNet, a novel causal-driven semantic segmentation framework designed to robustly identify multiple coral health states — live, dead, and bleached — from imagery in complex and dynamic underwater environments. Specifically, we introduce a Causal Decorrelation Module to reduce spurious correlations within irrelevant features, ensuring that the network can focus on the intrinsic causal features of different coral health status. Additionally, an Enhanced Feature Aggregation Module is proposed to improve the model’s ability to capture multi-scale details and complex boundaries. Extensive experiments demonstrate that CDNet achieves consistently high segmentation performance, with an average mF1 score exceeding 60% across datasets from diverse temporal and spatial domains. Compare to state-of-the-art methods, its mIoU improves by 4.3% to 40%. Moreover, CDNet maintains accurate and consistent segmentation performance under simulated scenarios reflecting practical underwater coral remote sensing monitoring challenges (including internal geometric transformations, variations in external environments, and different contextual dependencies), as well as on diverse real-world underwater coral datasets. Our proposed method provides a reliable and scalable solution for accurate and rapid spatiotemporal monitoring of coral reefs, offering practical value for long-term conservation and climate resilience of coral reefs.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 78-91"},"PeriodicalIF":12.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895081","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":"Generalization of point-to-point matching for rigorous optimization in kinematic laser scanning","authors":"Aurélien Brun ,&nbsp;Jakub Kolecki ,&nbsp;Muyan Xiao ,&nbsp;Luca Insolia ,&nbsp;Elmar V. van der Zwan ,&nbsp;Stéphane Guerrier ,&nbsp;Jan Skaloud","doi":"10.1016/j.isprsjprs.2025.08.011","DOIUrl":"10.1016/j.isprsjprs.2025.08.011","url":null,"abstract":"<div><div>In the scope of rigorous sensor fusion in kinematic laser scanning, we present a qualitative improvement of an automated retrieval method of lidar-to-lidar 3D correspondences in terms of accuracy and speed, where correspondences are locally refined shifts derived from learning based descriptors matching. These improvements are shared through an open implementation. We evaluate their impact in three, fundamentally different laser scanning scenarios (sensors and platforms) without adaptation: airborne (helicopter), mobile (car) and handheld (without GNSS). The impact of precise correspondences improves the point cloud georeferencing/registration 2 to 10 times with respect to previously described and/or industrial standards, depending on the setup, without adaptation to a particular scenario. This represents a potential to enhance the accuracy and reliability of kinematic laser scanning in different environments, whether satellite positioning is available or not, and irrespectively of the nature of the lidars (i.e. including single-beam linear or oscillating sensors).</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 107-121"},"PeriodicalIF":12.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895083","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":"City-level aerial geo-localization based on map matching network","authors":"Yong Tang ,&nbsp;Jingyi Zhang ,&nbsp;Jianhua Gong ,&nbsp;Yi Li ,&nbsp;Banghui Yang","doi":"10.1016/j.isprsjprs.2025.08.002","DOIUrl":"10.1016/j.isprsjprs.2025.08.002","url":null,"abstract":"<div><div>Autonomous localization of aircraft relies on precise geo-localization, and under Global Navigation Satellite System (GNSS)-denied conditions, visual localization methods are among the most important techniques for aircraft autonomous localization. Global visual localization typically relies on pre-established 3D maps, which require significant storage and computational overhead, limiting the applicability of aerial visual localization. Therefore, we propose a visual localization method based on OpenStreetMap, an openly accessible 2D map. This method not only enables localization in the absence of GNSS but also has lower storage and computational requirements compared to 3D map-based visual methods. This makes our approach feasible for visual geo-localization at the urban scale. We designed a neural network model based on the Vision Transformer (ViT) to extract features from aerial images and 2D maps for fast matching and retrieval, thereby estimating the global geo-location of the aerial images. Additionally, we employ particle filtering to fuse location estimates from map retrieval, visual odometry, and GNSS, achieving higher-precision real-time localization. Moreover, we collected aerial images and map tiles covering over 1000 square kilometers from the urban and suburban areas of four large cities, creating a novel aerial image-to-map matching dataset. Experiments show that, compared to the current state-of-the-art methods, our map retrieval network achieves a higher average recall rate on the dataset. In GNSS-denied conditions, our multi-source fusion localization method can achieve real-time global geo-localization at the urban scale, and under weak GNSS signals, our method provides significantly higher localization accuracy than GNSS alone.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"229 ","pages":"Pages 65-77"},"PeriodicalIF":12.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895064","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}