ISPRS Journal of Photogrammetry and Remote Sensing最新文献

{"title":"Few-shot Remote Sensing Scene Classification via Parameter-free Attention and Region Matching","authors":"Yuyu Jia ,&nbsp;Chenchen Sun ,&nbsp;Junyu Gao,&nbsp;Qi Wang","doi":"10.1016/j.isprsjprs.2025.05.026","DOIUrl":"10.1016/j.isprsjprs.2025.05.026","url":null,"abstract":"<div><div>Few-shot remote sensing scene classification, a pivotal task in geospatial scene understanding, has drawn considerable attention as a means to address annotation scarcity in Earth observation. While recent advancements exploit metric-based learning, conventional methods that rely on global feature aggregation, <em>e.g.,</em> prototype networks, often entangle target objects with cluttered backgrounds—an inherent limitation given the heterogeneous land-cover elements in remote sensing imagery. Although parametric attention mechanisms partially alleviate this issue, they tend to overfit base-class patterns, limiting adaptability to novel categories with diverse intra-class variations. To tackle these challenges, we propose the Parameter-free Attention with Selective Region Matching (PA-SRM) framework, which integrates two cascaded components: a parameter-free region attention module and a local description classifier. The former dynamically emphasizes discriminative regions by jointly assessing semantic similarity and spatial coherence. At the same time, the latter explicitly employs entropy-aware multi-region voting to suppress residual background interference in queries. Extensive experiments on NWPU-RESISC45, WHU-RS19, UCM, and AID datasets validate the superiority of PRA-SRM and the effectiveness of its components.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 265-275"},"PeriodicalIF":10.6,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322226","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":"Mitigating NDVI saturation in imagery of dense and healthy vegetation","authors":"Zezhong Tian ,&nbsp;Jiahao Fan ,&nbsp;Tong Yu ,&nbsp;Natalia de Leon ,&nbsp;Shawn M. Kaeppler ,&nbsp;Zhou Zhang","doi":"10.1016/j.isprsjprs.2025.06.013","DOIUrl":"10.1016/j.isprsjprs.2025.06.013","url":null,"abstract":"<div><div>The Normalized Difference Vegetation Index (NDVI) is a widely used tool for assessing vegetation in remote sensing. However, its non-linear response to increasing vegetation vigor, especially in dense and healthy canopies, often leads to inaccurate estimations of vegetation status — a phenomenon known as NDVI saturation. This study investigates the underlying causes of NDVI saturation and proposes a two-stage saturation mechanism. In contrast to the first-stage optical saturation caused by biophysical constraints, we demonstrate that second-stage mathematical saturation can be mitigated through functional optimization. To address this issue, we introduce a new vegetation index (VI), Saturation Mitigated NDVI (NDVIsm), which modifies the NDVI structure by integrating an anti-saturation module. This modification enhances the index’s sensitivity to changes in vegetation vigor dynamics by amplifying variation among high NDVI values, thereby mitigating saturation effects. The performance of NDVIsm was validated across multiple remote sensing platforms and land cover types. NDVIsm eliminated saturation (defined as areas where more than 80% of pixels fall within less than 20% of the index range) and exhibited a more dispersed distribution with a pronounced right tail in the histogram. The effectiveness of NDVIsm in mitigating saturation was further confirmed by improved Pearson correlations (<em>r</em>) with canopy structure (0.3010 increase in Leaf Area Index (LAI) and 0.2452 increase in Leaf Structure Parameters (N)) and vegetation vigor (0.5575 increase in Chlorophyll Content (Cab)), as well as enhanced performance in machine learning (ML)-based yield prediction models when combined with non-optical and spatial features. Overall, NDVIsm demonstrates improved sensitivity in detecting subtle variations in dense and healthy vegetation and offers a promising solution to the saturation problem in environmental remote sensing.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 234-250"},"PeriodicalIF":10.6,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307792","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":"HDRoad: An encoder-decoder architecture with hybrid attention and directional prior for efficient road extraction from remote sensing images","authors":"Fan He ,&nbsp;Shijie Liu ,&nbsp;Sicong Liu ,&nbsp;Yanmin Jin ,&nbsp;Huan Xie ,&nbsp;Xiaohua Tong","doi":"10.1016/j.isprsjprs.2025.06.014","DOIUrl":"10.1016/j.isprsjprs.2025.06.014","url":null,"abstract":"<div><div>Road extraction from very high resolution (VHR) remote sensing images (RSIs) presents significant challenges due to the varied morphology and high semantic complexity of road structures. Many existing methods struggle to consistently perform well across diverse and complex scenarios. Additionally, balancing efficiency and performance remains an unresolved issue in prior research, particularly those employing transformers. To address these challenges, we propose HDRoad, a novel encoder-decoder architecture that improves both model performance and computational efficiency, enabling training and inference on high-resolution inputs with a single GPU. The encoder, Hybrid Attention Network (HA-Net), combines dense and sparse spatial attention to effectively distill semantic information. The decoder, Directional Augmented Road Morphology Extraction Network (DARMEN), uses morphological priors to accurately refine and reconstruct road features. The model is validated on the DeepGlobe dataset and SouthernChina12k, a newly developed road segmentation dataset comprising 11,791 images from various remote sensing sources. Experimental results demonstrate that HDRoad achieves an IoU of 75.09 % on the DeepGlobe dataset and is the only model exceeding 60 % IoU on SouthernChina12k, setting new benchmarks for state-of-the-art performance in the field.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 251-264"},"PeriodicalIF":10.6,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307793","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":"Tiny object detection with single point supervision","authors":"Haoran Zhu ,&nbsp;Chang Xu ,&nbsp;Ruixiang Zhang ,&nbsp;Fang Xu ,&nbsp;Wen Yang ,&nbsp;Haijian Zhang ,&nbsp;Gui-Song Xia","doi":"10.1016/j.isprsjprs.2025.05.006","DOIUrl":"10.1016/j.isprsjprs.2025.05.006","url":null,"abstract":"<div><div>Tiny objects, with their limited spatial resolution, often resemble point-like distributions. As a result, bounding box prediction using point-level supervision emerges as a natural and cost-effective alternative to traditional box-level supervision. However, the small scale and lack of distinctive features of tiny objects make point annotations prone to noise, posing significant hurdles for model robustness. To tackle these challenges, we propose Point Teacher—the first end-to-end point-supervised method for robust tiny object detection in aerial images. To handle label noise from scale ambiguity and location shifts in point annotations, Point Teacher employs the teacher–student architecture and decouples the learning into a two-phase denoising process. In this framework, the teacher network progressively denoises the pseudo boxes derived from noisy point annotations, guiding the student network’s learning. Specifically, in the first phase, random masking of image regions facilitates regression learning, enabling the teacher to transform noisy point annotations into coarse pseudo boxes. In the second phase, these coarse pseudo boxes are refined using dynamic multiple instance learning, which adaptively selects the most reliable instance from dynamically constructed proposal bags around the coarse pseudo boxes. Extensive experiments on three tiny object datasets (<em>i.e.</em>, AI-TOD-v2, SODA-A, and TinyPerson) and a multi-scale object dataset DOTA-v2 validate the proposed method’s effectiveness and robustness against point location shifts. Notably, relying solely on point supervision, our Point Teacher already shows comparable performance with box-supervised learning methods. Code is available at <span><span>https://github.com/ZhuHaoranEIS/Point-Teacher</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 219-233"},"PeriodicalIF":10.6,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307791","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":"Solar cities: Multiple-reflection within urban canyons","authors":"Fan Xu ,&nbsp;Man Sing Wong ,&nbsp;Rui Zhu ,&nbsp;Ying Dang","doi":"10.1016/j.isprsjprs.2025.05.031","DOIUrl":"10.1016/j.isprsjprs.2025.05.031","url":null,"abstract":"<div><div>Solar photovoltaic (PV) harvesting is a significant energy resource leading to the rapid expansion of renewable energy. To facilitate decision-making regarding the optimal location and appropriate time for harvesting solar energy, the precise estimation of solar potential distribution in a city especially in 3D context is essential. However, using constant values to represent the urban vertical façades in a city and/or ignoring the indirect components under the estimation of received irradiation have been adopting in the current research, which may lead to inaccuracies in final results particular in complex urban environment. In this work, we propose a methodology to estimate the solar potential accurately by incorporating the façade albedo using street view images, as well as considering multiple reflection in urban canyon. Furthermore, this method is further integrated in the proposed evaluation framework to assess the impact of urban façade albedo on solar potential distribution. Compared to existing methods, the proposed framework first discusses and analyzes the importance of façade albedo and evaluates its impact quantitatively. The experimental results show that the discrepancies in albedo significantly affect the overall solar potential by 8.0% to 9.1%. If multiple reflections under urban canyon are disregarded, the impact can reach 11.9% to 17.8%.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 205-218"},"PeriodicalIF":10.6,"publicationDate":"2025-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288708","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":"DepthCD: Depth prompting in 2D remote sensing imagery change detection","authors":"Ning Zhou,&nbsp;Mingting Zhou,&nbsp;Haigang Sui","doi":"10.1016/j.isprsjprs.2025.05.020","DOIUrl":"10.1016/j.isprsjprs.2025.05.020","url":null,"abstract":"<div><div>Change detection with multi-temporal remote sensing images has wide applications in urban expansion monitoring, disaster response, and historical geographic information updating. In recent years, advancements in artificial intelligence have spurred the development of automatic remote sensing change detection methods. However, the existing change detection methods focus on variations in the spectral characteristics of objects, while ignoring the differences and variations in the Earth surface elevation of the different targets. This results in false alarms and missed detections in complex scenarios involving shadow occlusion, spectral confusion, and differences in imaging angles. In this paper, we present a depth prompting two-dimensional (2D) remote sensing change detection framework (DepthCD) that models depth/height changes automatically from 2D remote sensing images and integrates them into the change detection framework to overcome the effects of spectral confusion and shadow occlusion. During the feature extraction phase of DepthCD, we introduce a lightweight adapter to enable cost-effective fine-tuning of the large-parameter vision transformer encoder pre-trained by natural images. Inspired by domain knowledge of the dimensional correlation in land surface changes, we propose a depth change prompter to explicitly model depth/height changes at the feature, depth, and slope levels. In the change prediction phase, we introduce a binary change decoder and a semantic classification decoder that couple the depth change prompts with high-dimensional land-cover features, enabling accurate extraction of changed areas and accurate change types. Extensive experiments on six public change detection datasets validate the advantages of the DepthCD framework in binary and semantic change detection tasks. Detailed ablation studies further highlight the significance of the depth change prompts in remote sensing change detection.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 145-169"},"PeriodicalIF":10.6,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272431","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":"TAM-TR: Text-guided attention multi-modal transformer for object detection in UAV images","authors":"Jianhao Xu ,&nbsp;Xiangtao Fan ,&nbsp;Hongdeng Jian ,&nbsp;Chen Xu ,&nbsp;Weijia Bei ,&nbsp;Qifeng Ge ,&nbsp;Teng Zhao ,&nbsp;Ruijie Han","doi":"10.1016/j.isprsjprs.2025.04.027","DOIUrl":"10.1016/j.isprsjprs.2025.04.027","url":null,"abstract":"<div><div>Object detection in unmanned aerial vehicles (UAV) imagery is crucial in many fields, such as maritime search and rescue, remote sensing mapping, urban management and agricultural monitoring. The diverse perspectives and altitudes of UAV images often result in significant variations in the appearance and dimensions of objects, and occlusions are found more frequently than in general scenes. The unique bird’s-eye view of drones makes it more difficult for existing object detection models to distinguish between similar objects. A text-guided attention multi-modal transformer network named TAM-TR is proposed to address the above challenges. A Bidirectional Text–Image Attention Path Aggregation Network (BTA-PAN) is proposed in TAM-TR. This network imitates the architecture of the classic algorithm Scale-Invariant Feature Transform (SIFT) and shows better scale adaptability. A novel Multi-modal encoder–decoder head (MEH) was proposed, which can simultaneously consider all input sequence positions to avoid the disappearance of features of occluded objects. An additional text-guided attention branch, combined with a large text model, was proposed to improve the TAM-TR’s classification accuracy. Additionally, a Rotation-invariant IOU (RIOU) loss function was proposed to eliminate the previous loss function’s rotational instability. The experiment demonstrated that the TAM-TR outperformed the baseline by 9.5% and achieves 39.7% mean Averaged Precision (mAP) on the Visdrone dataset. The code will be available at <span><span>https://github.com/Xjh-UCAS/TAM-TR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 170-184"},"PeriodicalIF":10.6,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272432","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":"Phase congruency image mosaicking approach for aerial mid-wave infrared low-overlap array scanning images","authors":"Jiani He ,&nbsp;Yueming Wang ,&nbsp;Lixia Deng ,&nbsp;Yitao Li ,&nbsp;Zhao-Liang Li","doi":"10.1016/j.isprsjprs.2025.06.007","DOIUrl":"10.1016/j.isprsjprs.2025.06.007","url":null,"abstract":"<div><div>With the rapid development of imager manufacturing technology, mid-wave infrared (MWIR) array scanning images have been widely used to embody abundant thermal radiation geographic information. Due to the limited field of view (FOV) of the MWIR imaging detector, image mosaicking is essential for combining multiple overlapping images into a larger FOV image. However, MWIR images simultaneously suffer from poor image quality and a low signal-to-noise ratio (SNR), presenting significant challenges to existing mosaicking methods, particularly under low-overlap conditions. To overcome these challenges, this study proposes a robust phase congruency (PC) image mosaicking approach for aerial MWIR array scanning images based on image positions derived from Position Orientation System (POS). First, a joint corner-edge PC (CEPC) feature detection strategy is implemented to enhance feature point detection in MWIR images. Subsequently, a fractional average PC localization and orientation histogram (FAPC-LOH) descriptor is developed to generate robust feature descriptors. Additionally, image pairs and matching correspondences within overlapping regions are filtered using the initial image positions to prevent mismatches and ensure the reliability of feature points. Valid feature points are incorporated into the global consistency rectangling alignment model based on topology analysis to obtain the rectangular mosaicking results. Finally, ground control points (GCPs) are used to correct the planar projection error of the mosaicked images. The proposed mosaicking method is rigorously evaluated on six MWIR datasets collected from three cities, encompassing diverse scenarios, flight altitudes, imaging times, and overlap rates. Results demonstrate that our PC-based approach improves the mean number of inliers (MNI) by 5–12 times, increases the rate of successful matching (RSM) by 21.2–46.93% with an average RSM of 99.74%. It also achieves an average alignment root mean square error (RMSE) of 2.11 pixels and an average geometric positioning accuracy of 1.26 m (RMSE) across six datasets. Furthermore, the alignment results outperform those of representative mosaicking algorithms and popular commercial software, achieving superior global and local alignment along with enhanced positioning accuracy.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 185-204"},"PeriodicalIF":10.6,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272328","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":"SAGRNet: A novel object-based graph convolutional neural network for diverse vegetation cover classification in remotely-sensed imagery","authors":"Baoling Gui ,&nbsp;Lydia Sam ,&nbsp;Anshuman Bhardwaj ,&nbsp;Diego Soto Gómez ,&nbsp;Félix González Peñaloza ,&nbsp;Manfred F. Buchroithner ,&nbsp;David R. Green","doi":"10.1016/j.isprsjprs.2025.06.004","DOIUrl":"10.1016/j.isprsjprs.2025.06.004","url":null,"abstract":"<div><div>Growing global population, changing climate, and shrinking land resources demand for quicker, efficient, and more accurate methods of mapping and monitoring vegetation cover in remote sensing datasets. Many deep learning-based methods have been widely applied for semantic segmentation tasks in remote sensing images of vegetated environments. However, most existing models are pixel-based, which introduces challenges such as high time consumption, cumbersome implementation, and limited scalability. This paper presents the SAGRNet model, a Graph Convolutional Neural Network (GCN) that incorporates sampling aggregation and self-attention mechanisms, while leveraging the ResNet residual network structure. A key innovation of SAGRNet is its ability to fuse features extracted through diverse algorithms, enabling comprehensive representation and enhanced classification performance. The SAGRNet model demonstrates superior performance over leading pixel-based neural networks, such as U-Net++ and DeepLabV3, in terms of both time efficiency and accuracy in vegetation image classification tasks. We achieved an overall mapping accuracy of ∼90 % using SAGRNet, compared to ∼87% and ∼85% from U-Net++ and DeepLabV3, respectively. Additionally, it offers more convenience in data processing. Furthermore, the model significantly outperforms cutting-edge graph-based convolutional networks, including Graph U-Net (achieved overall accuracy ∼65%) and TGNN (achieved overall accuracy ∼75%), showcasing exceptional generalization capability and classification accuracy. This paper provides a comprehensive analysis of the various processing aspects of this object-based GCN for vegetation mapping and emphasizes its significant potential for practical use. The model’s versatility can also be expanded to other image processing domains, offering unprecedented possibilities of information extraction from satellite imagery. The code for practical application experiment is available at <span><span>https://github.com/baoling123/GCN-remote-sensing-classification.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 99-124"},"PeriodicalIF":10.6,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272330","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":"Registration of close-range, multi-lens multispectral imagery by retrieving the scene 3D structure","authors":"Sylvain Jay ,&nbsp;Frédéric Baret ,&nbsp;Samuel Thomas ,&nbsp;Marie Weiss","doi":"10.1016/j.isprsjprs.2025.06.001","DOIUrl":"10.1016/j.isprsjprs.2025.06.001","url":null,"abstract":"<div><div>Multispectral, multi-lens cameras, which acquire spectal images from different individual cameras equipped with different optical filters, are among the most widely used multispectral cameras available on the market. However, their use for close-range sensing is limited by the lack of registration algorithms capable of handling the strong parallax effects observed on scenes with non-negligible relief. In this paper, we propose a method based on stereo camera calibration and disparity estimation to register a close-range multispectral image while retrieving the corresponding 3D point cloud. The method takes advantage of the rigidity of these cameras and the synchronized capture of multispectral bands, both of which are thus compulsory. The algorithm is three-fold. First, the optimal combination of band pair alignments is found. Then, the semi-global matching stereovision algorithm combined with a robust matching cost function are used to align these band pairs and to compute the point cloud. Finally, a pixel filling step that exploits the spectral covariances of the different classes of materials in the image is implemented to limit the number of missing pixels, e.g., due to occlusions.</div><div>The method was tested on Airphen multispectral images of four plant crops (wheat, sunflower, cover crops and maize) acquired at a distance to the ground ranging from 1.5 to 3 m, thus encompassing a large variability in 3D structure and parallax effects. The results demonstrate that the proposed method achieves better registration performance than six state-of-the-art existing methods, while maintaining a reasonable processing time. Further, the point cloud provides accurate information on the 3D structure of the imaged scene, as shown by the centimetric plant height estimation accuracy. As the point cloud is aligned with the registered multispectral bands, the method provides a 4D (spectral and spatial) description of the scene with a single image, i.e., a multispectral point cloud. This opens up interesting prospects for several applications in close-range sensing including, but not restricted to, vegetation characterization.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"227 ","pages":"Pages 125-144"},"PeriodicalIF":10.6,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272329","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}