Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-1-2024
Matthias Arnold, Sina Keller
Abstract. This study introduces a novel data-driven approach for classifying and estimating the number of vehicles crossing a bridge solely on non-invasive ground-based radar time series data (GBR data). GBR is used to measure the bridge displacement remotely. It has recently been investigated for remote bridge weigh-in-motion (BWIM). BWIM mainly focuses on single-vehicle events. However, events with several vehicles should be exploited to increase the amount of data. Therefore, extracting the number of involved vehicles in the first step would be beneficial. Acquiring such information from global bridge responses such as displacement can be challenging. This study indicates that a data-driven machine learning approach can extract the vehicle count from GBR time series data. When classifying events according to the number of vehicles, we achieve a balanced accuracy of up to 80 % on an imbalanced dataset. We also try to estimate the number of cars and trucks separately via regression and acquire a R2 of 0.8. Finally, we show the impact of the data augmentation methods we apply to the GBR data to tackle the skew in the dataset using the feature importance of Random Forests.
{"title":"Machine Learning Approaches for Vehicle Counting on Bridges Based on Global Ground-Based Radar Data","authors":"Matthias Arnold, Sina Keller","doi":"10.5194/isprs-annals-x-2-2024-1-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-1-2024","url":null,"abstract":"Abstract. This study introduces a novel data-driven approach for classifying and estimating the number of vehicles crossing a bridge solely on non-invasive ground-based radar time series data (GBR data). GBR is used to measure the bridge displacement remotely. It has recently been investigated for remote bridge weigh-in-motion (BWIM). BWIM mainly focuses on single-vehicle events. However, events with several vehicles should be exploited to increase the amount of data. Therefore, extracting the number of involved vehicles in the first step would be beneficial. Acquiring such information from global bridge responses such as displacement can be challenging. This study indicates that a data-driven machine learning approach can extract the vehicle count from GBR time series data. When classifying events according to the number of vehicles, we achieve a balanced accuracy of up to 80 % on an imbalanced dataset. We also try to estimate the number of cars and trucks separately via regression and acquire a R2 of 0.8. Finally, we show the impact of the data augmentation methods we apply to the GBR data to tackle the skew in the dataset using the feature importance of Random Forests.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"110 49","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141361074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-25-2024
A. Calantropio, F. Chiabrando, F. Menna, E. Nocerino
Abstract. Underwater photogrammetry is often hampered by chromatic aberration, leading to degraded 2D and 3D products. This study investigates the effectiveness of various color enhancement methods in addressing these challenges.Theoretical considerations indicate that light penetration depth varies inversely with wavelength, causing underwater images to exhibit a blue or green cast with increasing depth. Color enhancement techniques can restore natural colors by compensating for this spectral attenuation. Additionally, scattering, caused by light reflected by particles in the water, can introduce haze into underwater images. Color enhancement can mitigate scatter and improve image clarity. In this contribution, to quantitatively evaluate color enhancement methods, we compare original images with images processed using gray-world assumption methods and physical methods that account for the physical properties of light underwater. Using artificial intelligence (AI) for underwater image color enhancement, a data-driven approach was also employed. These methods were applied to a case study concerning a Roman Navis Lapidaria shipwreck carrying five monumental cipollino marble columns at a depth of 4.5 meters in the Porto Cesareo Marine Protected Area (Italy). These methods were compared quantitatively and qualitatively, and the results are presented and discussed.
摘要水下摄影测量经常受到色差的影响，导致二维和三维产品的质量下降。理论研究表明，光的穿透深度与波长成反比，导致水下图像随着深度的增加而呈现蓝色或绿色。色彩增强技术可以通过补偿这种光谱衰减来还原自然色彩。此外，水中颗粒反射的光线所产生的散射也会给水下图像带来雾度。色彩增强可以减少散射，提高图像清晰度。在本文中，为了定量评估色彩增强方法，我们将原始图像与使用灰度世界假设方法和考虑到水下光的物理特性的物理方法处理的图像进行了比较。我们还采用了人工智能（AI）进行水下图像色彩增强，这是一种数据驱动的方法。这些方法被应用于一项案例研究，该案例涉及意大利切萨雷奥 港海洋保护区 4.5 米深处的一艘罗马 Navis Lapidaria 沉船，船上载有五根具有纪念意义的 cipollino 大理石圆柱。对这些方法进行了定量和定性比较，并对结果进行了介绍和讨论。
{"title":"Quantitative Evaluation of Color Enhancement Methods for Underwater Photogrammetry in Very Shallow Water: a Case Study","authors":"A. Calantropio, F. Chiabrando, F. Menna, E. Nocerino","doi":"10.5194/isprs-annals-x-2-2024-25-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-25-2024","url":null,"abstract":"Abstract. Underwater photogrammetry is often hampered by chromatic aberration, leading to degraded 2D and 3D products. This study investigates the effectiveness of various color enhancement methods in addressing these challenges.Theoretical considerations indicate that light penetration depth varies inversely with wavelength, causing underwater images to exhibit a blue or green cast with increasing depth. Color enhancement techniques can restore natural colors by compensating for this spectral attenuation. Additionally, scattering, caused by light reflected by particles in the water, can introduce haze into underwater images. Color enhancement can mitigate scatter and improve image clarity. In this contribution, to quantitatively evaluate color enhancement methods, we compare original images with images processed using gray-world assumption methods and physical methods that account for the physical properties of light underwater. Using artificial intelligence (AI) for underwater image color enhancement, a data-driven approach was also employed. These methods were applied to a case study concerning a Roman Navis Lapidaria shipwreck carrying five monumental cipollino marble columns at a depth of 4.5 meters in the Porto Cesareo Marine Protected Area (Italy). These methods were compared quantitatively and qualitatively, and the results are presented and discussed.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 28","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141364754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-81-2024
Shengxi Gui, P. Schuegraf, K. Bittner, Rongjun Qin
Abstract. Recent advancements in deep learning have enabled the possibility to identify unit-level building sections from very high resolution satellite images. By learning from the examples, deep models can capture patterns from the low-resolution roof textures to separate building units from duplex buildings. This paper demonstrates that such unit-level segmentation can further advance level of details (LoD)2 modeling. We extend a building boundary regularization method by adapting noisy unit-level segmentation results. Specifically, we propose a novel polygon composition approach to ensure the individually segmented units within a duplex building or dense adjacent buildings are consistent in their shared boundaries. Results of the experiments show that, our unit-level LoD2 modeling has favorably outperformed the state-of-the-art LoD2 modeling results from satellite images.
{"title":"Unit-level LoD2 Building Reconstruction from Satellite-derived Digital Surface Model and Orthophoto","authors":"Shengxi Gui, P. Schuegraf, K. Bittner, Rongjun Qin","doi":"10.5194/isprs-annals-x-2-2024-81-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-81-2024","url":null,"abstract":"Abstract. Recent advancements in deep learning have enabled the possibility to identify unit-level building sections from very high resolution satellite images. By learning from the examples, deep models can capture patterns from the low-resolution roof textures to separate building units from duplex buildings. This paper demonstrates that such unit-level segmentation can further advance level of details (LoD)2 modeling. We extend a building boundary regularization method by adapting noisy unit-level segmentation results. Specifically, we propose a novel polygon composition approach to ensure the individually segmented units within a duplex building or dense adjacent buildings are consistent in their shared boundaries. Results of the experiments show that, our unit-level LoD2 modeling has favorably outperformed the state-of-the-art LoD2 modeling results from satellite images.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"108 50","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141361537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-231-2024
Hanyu Xiang, Wenyuan Niu, Xianfeng Huang, Bo Ning, Fan Zhang, Jianmin Xu
Abstract. 3D reconstruction of cultural heritage with large volume and high precision is a technical problem in the field of photogrammetry. This paper studies a high-precision digitalization method for large-volume immovable heritage assets based on photogrammetry and laser scanning. It solves the problem of large-scale aerial triangulation and ensures overall color and geometric consistency while satisfying high-precision modeling of local details. Taking the millimeter accuracy 3D reconstruction project of Cave No. 13 in Yungang Grottoes as an example, we use more than 280,000 arbitrary images to reconstruct the entire cave and verify the effectiveness of the proposed method.
{"title":"Large Scale and Complex Structure Grotto Digitalization Using Photogrammetric Method: A Case Study of Cave No. 13 in Yungang Grottoes","authors":"Hanyu Xiang, Wenyuan Niu, Xianfeng Huang, Bo Ning, Fan Zhang, Jianmin Xu","doi":"10.5194/isprs-annals-x-2-2024-231-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-231-2024","url":null,"abstract":"Abstract. 3D reconstruction of cultural heritage with large volume and high precision is a technical problem in the field of photogrammetry. This paper studies a high-precision digitalization method for large-volume immovable heritage assets based on photogrammetry and laser scanning. It solves the problem of large-scale aerial triangulation and ensures overall color and geometric consistency while satisfying high-precision modeling of local details. Taking the millimeter accuracy 3D reconstruction project of Cave No. 13 in Yungang Grottoes as an example, we use more than 280,000 arbitrary images to reconstruct the entire cave and verify the effectiveness of the proposed method.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141366150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-49-2024
A. Elashry, C. Toth
Abstract. This research introduces a novel approach to improve vision-based positioning in the absence of GNSS signals. Specifically, we address the challenge posed by obstacles that alter image information or features, making retrieving the query image from the database difficult. While the Bag of Visual Words (BoVW) is a widely used image retrieval technique, it has a limitation in representing each image with a single histogram vector or vocabulary of visual words, i.e., the emergence of obstacles can introduce new features to the query image, resulting in different visual words. Our study overcomes this limitation by clustering the features of each image using the k-means method and generating a graph for each class. Each node or key point in the graph obtains additional information from its direct neighbors using functions employed in graph neural networks, functioning as a feedforward network with constant parameters. This process generates new embedding nodes, and eventually, global pooling is applied to produce one vector for each graph, representing each image with graph vectors based on objects or feature classes. As a result, each image is represented with graph vectors based on objects or feature classes. In the presence of obstacles covering one or more graphs, there is sufficient information from the query image to retrieve the most relevant image from the database. Our approach was applied to indoor positioning applications, with the database collected in Bolz Hall at The Ohio State University. Traditional BoVW techniques struggle to properly retrieve most query images from the database due to obstacles like humans or recently deployed objects that alter image features. In contrast, our approach has shown progress in image retrieval by representing each image with multiple graph vectors, depending on the number of objects in the image. This helps prevent or mitigate changes in image features caused by obstacles covering or adding features to the image, as demonstrated in the results.
摘要这项研究提出了一种新方法，用于在没有全球导航卫星系统信号的情况下改进基于视觉的定位。具体来说，我们要解决的挑战是，由于障碍物改变了图像信息或特征，使得从数据库中检索查询图像变得困难。虽然 "视觉词袋"（Bag of Visual Words，BoVW）是一种广泛使用的图像检索技术，但它在用单一直方图向量或视觉词词汇来表示每幅图像方面存在局限性，即障碍物的出现会给查询图像带来新的特征，从而产生不同的视觉词。我们的研究通过使用 k-means 方法对每幅图像的特征进行聚类，并为每个类别生成一个图，从而克服了这一局限性。图中的每个节点或关键点都会使用图神经网络中使用的函数从其直接相邻的节点或关键点获取额外的信息，作为具有恒定参数的前馈网络发挥作用。这一过程会生成新的嵌入节点，最终，全局池化技术会为每个图生成一个向量，用基于对象或特征类别的图向量来表示每幅图像。因此，每幅图像都是用基于物体或特征类别的图向量来表示的。在有障碍物覆盖一个或多个图的情况下，查询图像中的信息足以从数据库中检索出最相关的图像。我们的方法应用于室内定位应用，数据库收集于俄亥俄州立大学的博尔兹大厅。传统的 BoVW 技术很难从数据库中正确检索到大多数查询图像，原因是人类或最近部署的物体等障碍物会改变图像特征。相比之下，我们的方法根据图像中物体的数量，用多个图向量来表示每幅图像，从而在图像检索方面取得了进展。如结果所示，这有助于防止或减轻因障碍物覆盖或增加图像特征而导致的图像特征变化。
{"title":"A Novel Approach to Image Retrieval for Vision-Based Positioning Utilizing Graph Topology","authors":"A. Elashry, C. Toth","doi":"10.5194/isprs-annals-x-2-2024-49-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-49-2024","url":null,"abstract":"Abstract. This research introduces a novel approach to improve vision-based positioning in the absence of GNSS signals. Specifically, we address the challenge posed by obstacles that alter image information or features, making retrieving the query image from the database difficult. While the Bag of Visual Words (BoVW) is a widely used image retrieval technique, it has a limitation in representing each image with a single histogram vector or vocabulary of visual words, i.e., the emergence of obstacles can introduce new features to the query image, resulting in different visual words. Our study overcomes this limitation by clustering the features of each image using the k-means method and generating a graph for each class. Each node or key point in the graph obtains additional information from its direct neighbors using functions employed in graph neural networks, functioning as a feedforward network with constant parameters. This process generates new embedding nodes, and eventually, global pooling is applied to produce one vector for each graph, representing each image with graph vectors based on objects or feature classes. As a result, each image is represented with graph vectors based on objects or feature classes. In the presence of obstacles covering one or more graphs, there is sufficient information from the query image to retrieve the most relevant image from the database. Our approach was applied to indoor positioning applications, with the database collected in Bolz Hall at The Ohio State University. Traditional BoVW techniques struggle to properly retrieve most query images from the database due to obstacles like humans or recently deployed objects that alter image features. In contrast, our approach has shown progress in image retrieval by representing each image with multiple graph vectors, depending on the number of objects in the image. This helps prevent or mitigate changes in image features caused by obstacles covering or adding features to the image, as demonstrated in the results.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 1242","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141363827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-9-2024
R. Blaskow, Hans-Gerd Maas
Abstract. Bridge structures can be surveyed using a number of different methods. Established are image-based methods using structure from motion by an unmanned aerial vehicle (UAV), terrestrial laser scanning (TLS), or a combination of both methods. Beyond static terrestrial laser scanning, buildings can also be efficiently surveyed using personal laser scanner (PLS) systems. The advantage here is the greater flexibility and increased speed compared to the static method. On the other hand, the accuracy may be more critical, and the resulting point cloud will be more sensitive to systematic global or local deformations under unfavorable measurement conditions. For example, temporary influences can lead to local mapping errors. These include influences such as uneven measurement system motion or non-static, feature-sparse environments. This study investigates the acquisition of 3D point clouds representing the outer shell of a concrete bridge using a PLS system. We demonstrate a method for detecting possible deformations in PLS point clouds using the example of a bridge structure. For this purpose, the reference (TLS) and the PLS point clouds are segmented into individual clusters and a segment-based ICP fine registration is performed. Different RMSE values for the upper road section (0.061 m) and for the pillar segments (0.021 m) as well as different transformation parameters indicate slight displacements in the PLS point cloud. The analysis of the cloud-to-cloud distances showed that there were slight deformations in the Z direction in the area of the road surface. In the lateral direction, no significant residual deviations were found in the area of the bridge pillars.
{"title":"Structural Health Monitoring of Bridges with Personal Laser Scanning: Segment-based Analysis of systematic Point Cloud Deformations","authors":"R. Blaskow, Hans-Gerd Maas","doi":"10.5194/isprs-annals-x-2-2024-9-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-9-2024","url":null,"abstract":"Abstract. Bridge structures can be surveyed using a number of different methods. Established are image-based methods using structure from motion by an unmanned aerial vehicle (UAV), terrestrial laser scanning (TLS), or a combination of both methods. Beyond static terrestrial laser scanning, buildings can also be efficiently surveyed using personal laser scanner (PLS) systems. The advantage here is the greater flexibility and increased speed compared to the static method. On the other hand, the accuracy may be more critical, and the resulting point cloud will be more sensitive to systematic global or local deformations under unfavorable measurement conditions. For example, temporary influences can lead to local mapping errors. These include influences such as uneven measurement system motion or non-static, feature-sparse environments. This study investigates the acquisition of 3D point clouds representing the outer shell of a concrete bridge using a PLS system. We demonstrate a method for detecting possible deformations in PLS point clouds using the example of a bridge structure. For this purpose, the reference (TLS) and the PLS point clouds are segmented into individual clusters and a segment-based ICP fine registration is performed. Different RMSE values for the upper road section (0.061 m) and for the pillar segments (0.021 m) as well as different transformation parameters indicate slight displacements in the PLS point cloud. The analysis of the cloud-to-cloud distances showed that there were slight deformations in the Z direction in the area of the road surface. In the lateral direction, no significant residual deviations were found in the area of the bridge pillars.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141364964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-201-2024
Yikang Ren, Fang Liu
Abstract. The Dunhuang murals, a significant part of Chinese heritage, have suffered deterioration primarily due to environmental and chemical factors, notably salt damage. This study proposes a sophisticated method that synergizes Fractional Order Differentiation (FOD) and Partial Least Squares Regression (PLSR) to accurately invert the phosphate content in the Mural Plaster of the Dunhuang paintings. The focal points of the research include: 1) To address the issue of information loss and reduced modeling precision caused by integer order differentiation algorithms, the FOD method is employed for preprocessing hyperspectral data. This approach ensures the fine spectral differences in the phosphate content of the Mural Plaster are precisely captured, 2) Utilizing PLSR, the study models the spectral bands identified at a significance level of 0.01 with measured conductivity values, thereby enabling the precise prediction of the phosphate content in the murals. The research outcomes reveal: 1) The FOD method can elucidate the nonlinear characteristics and variation patterns of the mural samples in the hyperspectral curve.As the order increases from zero to two, the number of spectral bands meeting the 0.01 significance test initially decreases and then increases. The highest absolute value of the positive correlation coefficient is observed at 1.9 orders, corresponding to the 2077 nm band, 2) For predicting the phosphate content in the murals, the model at 1.9 orders is most suitable for inversion. This model, after cross-validation, achieves a maximum R2 value of 0.783. This study created an efficient FOD-based model for estimating phosphate in mural plasters.
{"title":"A Novel Hyperspectral Salt Assessment Model for Weathering in Architectural Ruins","authors":"Yikang Ren, Fang Liu","doi":"10.5194/isprs-annals-x-2-2024-201-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-201-2024","url":null,"abstract":"Abstract. The Dunhuang murals, a significant part of Chinese heritage, have suffered deterioration primarily due to environmental and chemical factors, notably salt damage. This study proposes a sophisticated method that synergizes Fractional Order Differentiation (FOD) and Partial Least Squares Regression (PLSR) to accurately invert the phosphate content in the Mural Plaster of the Dunhuang paintings. The focal points of the research include: 1) To address the issue of information loss and reduced modeling precision caused by integer order differentiation algorithms, the FOD method is employed for preprocessing hyperspectral data. This approach ensures the fine spectral differences in the phosphate content of the Mural Plaster are precisely captured, 2) Utilizing PLSR, the study models the spectral bands identified at a significance level of 0.01 with measured conductivity values, thereby enabling the precise prediction of the phosphate content in the murals. The research outcomes reveal: 1) The FOD method can elucidate the nonlinear characteristics and variation patterns of the mural samples in the hyperspectral curve.As the order increases from zero to two, the number of spectral bands meeting the 0.01 significance test initially decreases and then increases. The highest absolute value of the positive correlation coefficient is observed at 1.9 orders, corresponding to the 2077 nm band, 2) For predicting the phosphate content in the murals, the model at 1.9 orders is most suitable for inversion. This model, after cross-validation, achieves a maximum R2 value of 0.783. This study created an efficient FOD-based model for estimating phosphate in mural plasters.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 47","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141364975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-179-2024
C. Okolie, A. Adeleke, J. Smit, J. Mills, Caleb O. Ogbeta, I. Maduako
Abstract. Gradient-Boosted Decision Trees (GBDTs), particularly when tuned with Bayesian optimisation, are powerful machine learning techniques known for their effectiveness in handling complex, non-linear data. However, the performance of these models can be significantly influenced by the characteristics of the terrain being analysed. In this study, we assess the performance of three Bayesian-optimised GBDTs (XGBoost, LightGBM and CatBoost) using digital elevation model (DEM) error correction as a case study. The performance of the models is investigated across five landscapes in Cape Town South Africa: urban/industrial, agricultural, mountain, peninsula and grassland/shrubland. The models were trained using a selection of datasets (elevation, terrain parameters and land cover). The comparison entailed an analysis of the model execution times, regression error metrics, and level of improvement in the corrected DEMs. Generally, the optimised models performed considerably well and demonstrated excellent predictive capability. CatBoost emerged with the best results in the level of improvement recorded in the corrected DEMs, while LightGBM was the fastest of all models in the execution time for Bayesian optimisation and model training. These findings offer valuable insights for applying machine learning and hyperparameter tuning in remote sensing.
摘要梯度提升决策树（GBDTs），尤其是使用贝叶斯优化技术进行调整时，是一种强大的机器学习技术，因其在处理复杂、非线性数据方面的有效性而闻名。然而，这些模型的性能会受到所分析地形特征的显著影响。在本研究中，我们以数字高程模型（DEM）误差修正为例，评估了三种贝叶斯优化 GBDT（XGBoost、LightGBM 和 CatBoost）的性能。研究了这些模型在南非开普敦五种地貌中的表现：城市/工业地貌、农业地貌、山地地貌、半岛地貌和草地/灌木地貌。这些模型是利用精选的数据集（海拔高度、地形参数和土地覆盖）进行训练的。比较工作包括分析模型的执行时间、回归误差指标以及校正后 DEM 的改进程度。总体而言，优化模型的表现相当出色，显示出卓越的预测能力。CatBoost 在校正后的 DEM 改善水平方面取得了最佳结果，而 LightGBM 在贝叶斯优化和模型训练的执行时间方面是所有模型中最快的。这些发现为在遥感中应用机器学习和超参数调整提供了宝贵的见解。
{"title":"Performance analysis of Bayesian optimised gradient-boosted decision trees for digital elevation model (DEM) error correction: interim results","authors":"C. Okolie, A. Adeleke, J. Smit, J. Mills, Caleb O. Ogbeta, I. Maduako","doi":"10.5194/isprs-annals-x-2-2024-179-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-179-2024","url":null,"abstract":"Abstract. Gradient-Boosted Decision Trees (GBDTs), particularly when tuned with Bayesian optimisation, are powerful machine learning techniques known for their effectiveness in handling complex, non-linear data. However, the performance of these models can be significantly influenced by the characteristics of the terrain being analysed. In this study, we assess the performance of three Bayesian-optimised GBDTs (XGBoost, LightGBM and CatBoost) using digital elevation model (DEM) error correction as a case study. The performance of the models is investigated across five landscapes in Cape Town South Africa: urban/industrial, agricultural, mountain, peninsula and grassland/shrubland. The models were trained using a selection of datasets (elevation, terrain parameters and land cover). The comparison entailed an analysis of the model execution times, regression error metrics, and level of improvement in the corrected DEMs. Generally, the optimised models performed considerably well and demonstrated excellent predictive capability. CatBoost emerged with the best results in the level of improvement recorded in the corrected DEMs, while LightGBM was the fastest of all models in the execution time for Bayesian optimisation and model training. These findings offer valuable insights for applying machine learning and hyperparameter tuning in remote sensing.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"123 30","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141361760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-33-2024
A. Calantropio, F. Menna, D. Skarlatos, C. Balletti, Gottfried Mandlburger, P. Agrafiotis, F. Chiabrando, A. Lingua, Alessia Giaquinto, E. Nocerino
Abstract. Benchmark datasets have become increasingly widespread in the scientific community as a method of comparison, validation, and improvement of theories and techniques thanks to more affordable means for sharing. While this especially holds for test sites and data collected above the water, publicly accessible benchmark activities for geospatial analyses in the underwater environment are not very common. Applying geomatic techniques underwater is challenging and expensive, especially when dealing with deep water and offshore operations. Moreover, benchmarking requires ground truth data for which, in water, several open issues exist concerning geometry and radiometry. Recognizing this scientific and technological challenge, the NAUTILUS (uNder And throUgh waTer datasets for geospatIaL stUdieS) project aims to create guidelines for new multi-sensor/cross-modality benchmark datasets. The project focuses on (i) surveying the actual needs and gaps in through and under-the-water geospatial applications through a questionnaire and interviews, (ii) launching a unique publicly available database collecting already existing datasets scattered across the web and literature, (iii) designing and identifying proper test site(s) and methodologies to deliver to the extended underwater community a brand-new multi-sensor/cross-modality benchmark dataset. The project outputs are available to researchers and practitioners in underwater measurements-related domains, as they can now access a comprehensive tool providing a synthesis of open questions and data already available. In doing so, past research efforts to collect and publish datasets have received additional credit and visibility.
{"title":"Under and Through Water Datasets for Geospatial Studies: the 2023 ISPRS Scientific Initiative “NAUTILUS”","authors":"A. Calantropio, F. Menna, D. Skarlatos, C. Balletti, Gottfried Mandlburger, P. Agrafiotis, F. Chiabrando, A. Lingua, Alessia Giaquinto, E. Nocerino","doi":"10.5194/isprs-annals-x-2-2024-33-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-33-2024","url":null,"abstract":"Abstract. Benchmark datasets have become increasingly widespread in the scientific community as a method of comparison, validation, and improvement of theories and techniques thanks to more affordable means for sharing. While this especially holds for test sites and data collected above the water, publicly accessible benchmark activities for geospatial analyses in the underwater environment are not very common. Applying geomatic techniques underwater is challenging and expensive, especially when dealing with deep water and offshore operations. Moreover, benchmarking requires ground truth data for which, in water, several open issues exist concerning geometry and radiometry. Recognizing this scientific and technological challenge, the NAUTILUS (uNder And throUgh waTer datasets for geospatIaL stUdieS) project aims to create guidelines for new multi-sensor/cross-modality benchmark datasets. The project focuses on (i) surveying the actual needs and gaps in through and under-the-water geospatial applications through a questionnaire and interviews, (ii) launching a unique publicly available database collecting already existing datasets scattered across the web and literature, (iii) designing and identifying proper test site(s) and methodologies to deliver to the extended underwater community a brand-new multi-sensor/cross-modality benchmark dataset. The project outputs are available to researchers and practitioners in underwater measurements-related domains, as they can now access a comprehensive tool providing a synthesis of open questions and data already available. In doing so, past research efforts to collect and publish datasets have received additional credit and visibility.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 498","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141364353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-97-2024
D. Haitz, Max Hermann, Aglaja Solana Roth, Michael Weinmann, Martin Weinmann
Abstract. In this paper, we focus on investigating the potential of advanced Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting for 3D scene reconstruction from aerial imagery obtained via sensor platforms with an almost nadir-looking camera. Such a setting for image acquisition is convenient for capturing large-scale urban scenes, yet it poses particular challenges arising from imagery with large overlap, very short baselines, similar viewing direction and almost the same but large distance to the scene, and it therefore differs from the usual object-centric scene capture. We apply a traditional approach for image-based 3D reconstruction (COLMAP), a modern NeRF-based approach (Nerfacto) and a representative for the recently introduced 3D Gaussian Splatting approaches (Splatfacto), where the latter two are provided in the Nerfstudio framework. We analyze results achieved on the recently released UseGeo dataset both quantitatively and qualitatively. The achieved results reveal that the traditional COLMAP approach still outperforms Nerfacto and Splatfacto approaches for various scene characteristics, such as less-textured areas, areas with high vegetation, shadowed areas and areas observed from only very few views.
{"title":"The Potential of Neural Radiance Fields and 3D Gaussian Splatting for 3D Reconstruction from Aerial Imagery","authors":"D. Haitz, Max Hermann, Aglaja Solana Roth, Michael Weinmann, Martin Weinmann","doi":"10.5194/isprs-annals-x-2-2024-97-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-97-2024","url":null,"abstract":"Abstract. In this paper, we focus on investigating the potential of advanced Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting for 3D scene reconstruction from aerial imagery obtained via sensor platforms with an almost nadir-looking camera. Such a setting for image acquisition is convenient for capturing large-scale urban scenes, yet it poses particular challenges arising from imagery with large overlap, very short baselines, similar viewing direction and almost the same but large distance to the scene, and it therefore differs from the usual object-centric scene capture. We apply a traditional approach for image-based 3D reconstruction (COLMAP), a modern NeRF-based approach (Nerfacto) and a representative for the recently introduced 3D Gaussian Splatting approaches (Splatfacto), where the latter two are provided in the Nerfstudio framework. We analyze results achieved on the recently released UseGeo dataset both quantitatively and qualitatively. The achieved results reveal that the traditional COLMAP approach still outperforms Nerfacto and Splatfacto approaches for various scene characteristics, such as less-textured areas, areas with high vegetation, shadowed areas and areas observed from only very few views.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 29","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141365837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：