Pub Date : 2023-10-01DOI: 10.14358/pers.23-00007r3
Yanis Marchand, Laurent Caraffa, Raphael Sulzer, Emmanuel Clédat, Bruno Vallet
Surface reconstruction has been studied thoroughly, but very little work has been done to address its evaluation. In this article, we propose new visibility-based metrics to assess the completeness and accuracy of three-dimensional meshes based on a point cloud of higher accuracy than the one from which the reconstruction has been computed. We use the position from which each high-quality point has been acquired to compute the corresponding ray of free space. Based on the intersections between each ray and the reconstructed surface, our metrics allow evaluating both the global coherency of the reconstruction and the accuracy at close range. We validate this evaluation protocol by surveying several open-source algorithms as well as a piece of licensed software on three data sets. The results confirm the relevance of assessi ng local and global accuracy separately since algorithms sometimes fail at guaranteeing both simultaneously. In addition, algorithms making use of sensor positions perform better than the ones relying only on points and normals, indicating a potentially significant added value of this piece of information. Our implementation is available at https://github.com/umrlastig/SurfaceReconEval.
{"title":"Evaluating Surface Mesh Reconstruction Using Real Data","authors":"Yanis Marchand, Laurent Caraffa, Raphael Sulzer, Emmanuel Clédat, Bruno Vallet","doi":"10.14358/pers.23-00007r3","DOIUrl":"https://doi.org/10.14358/pers.23-00007r3","url":null,"abstract":"Surface reconstruction has been studied thoroughly, but very little work has been done to address its evaluation. In this article, we propose new visibility-based metrics to assess the completeness and accuracy of three-dimensional meshes based on a point cloud of higher accuracy than the one from which the reconstruction has been computed. We use the position from which each high-quality point has been acquired to compute the corresponding ray of free space. Based on the intersections between each ray and the reconstructed surface, our metrics allow evaluating both the global coherency of the reconstruction and the accuracy at close range. We validate this evaluation protocol by surveying several open-source algorithms as well as a piece of licensed software on three data sets. The results confirm the relevance of assessi ng local and global accuracy separately since algorithms sometimes fail at guaranteeing both simultaneously. In addition, algorithms making use of sensor positions perform better than the ones relying only on points and normals, indicating a potentially significant added value of this piece of information. Our implementation is available at https://github.com/umrlastig/SurfaceReconEval.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135367685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.14358/pers.23-00026r2
Nahed Osama, Zhenfeng Shao, Mohamed Freeshah
Many remote sensing and geoscience applications require a high-precision terrain model. In 2022, the Forest And Buildings removed Copernicus digital elevation model (FABDEM) was released, in which trees and buildings were removed at a 30 m resolution. Therefore, it was necessary to make a comprehensive evaluation of this model. This research aims to perform a qualitative and quantitative analysis of fabdem in comparison with the commonly used global dems. We investigated the effect of the terrain slope, aspect, roughness, and land cover types in causing errors in the topographic representation of all dems. The fabdem had the highest overall vertical accuracy of 5.56 m. It was the best dem in representing the terrain roughness. The fabdem and Copernicus dem were equally influenced by the slopes more than the other models and had the worst accuracy of slope representation. In the tree, built, and flooded vegetation areas of the fabdem, the mean errors in elevation have been reduced by approximately 3.34 m, 1.26 m and 1.55 m, respectively. Based on Welch's t-test, there was no significant difference between fabdem and Copernicus dem elevations. However, the slight improvements in the fabdem make it the best filtered dem to represent the terrain heights over different land cover types.
{"title":"The FABDEM Outperforms the Global DEMs in Representing Bare Terrain Heights","authors":"Nahed Osama, Zhenfeng Shao, Mohamed Freeshah","doi":"10.14358/pers.23-00026r2","DOIUrl":"https://doi.org/10.14358/pers.23-00026r2","url":null,"abstract":"Many remote sensing and geoscience applications require a high-precision terrain model. In 2022, the Forest And Buildings removed Copernicus digital elevation model (FABDEM) was released, in which trees and buildings were removed at a 30 m resolution. Therefore, it was necessary to make a comprehensive evaluation of this model. This research aims to perform a qualitative and quantitative analysis of fabdem in comparison with the commonly used global dems. We investigated the effect of the terrain slope, aspect, roughness, and land cover types in causing errors in the topographic representation of all dems. The fabdem had the highest overall vertical accuracy of 5.56 m. It was the best dem in representing the terrain roughness. The fabdem and Copernicus dem were equally influenced by the slopes more than the other models and had the worst accuracy of slope representation. In the tree, built, and flooded vegetation areas of the fabdem, the mean errors in elevation have been reduced by approximately 3.34 m, 1.26 m and 1.55 m, respectively. Based on Welch's t-test, there was no significant difference between fabdem and Copernicus dem elevations. However, the slight improvements in the fabdem make it the best filtered dem to represent the terrain heights over different land cover types.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135367684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.14358/pers.23-00005r3
Zhang Chenguang, Teng Guifa
This study aims at applying the improved You Only Look Once V5s model for the assessment of regional poverty using remote sensing image target detection. The model was improved from structure, algorithm, and components. Objects in the remote sensing images were used to identify poverty, and the poverty alleviation situation could be predicted according to the existing detection results. The results showed that the values of Precision, Recall, mean Average Precision (mAP)@0.5, and mAP@0.5:0.95 of the model increased 7.3%, 0.7%, 1%, and 7.2%, respectively on the Common Objects in Context data set in the detection stage; the four values increased 3.1%, 2.2%, 1.3%, and 5.7%, respectively on the custom remote sensing image data set in the verification stage. The loss values decreased 2.6% and 37.4%, respectively, on the two data sets. Hence, the application of the improved model led to the more accurate detection of the targets. Compared with the other papers, the improved model in this paper proved to be better. Artificial poverty alleviation can be replaced by remote sensing image processing because it is inexpensive, efficient, accurate, objective, does not require data, and has the same evaluation effect. The proposed model can be considered as a promising approach in the assessment of regional poverty.
本研究旨在将改进的You Only Look Once V5s模型应用于基于遥感图像目标检测的区域贫困评估。从结构、算法和组件三个方面对模型进行了改进。利用遥感影像中的地物对贫困进行识别，根据已有的检测结果对扶贫情况进行预测。结果表明，在检测阶段，该模型的Precision、Recall、mean Average Precision (mAP)@0.5和mAP@0.5:0.95分别比Common Objects in Context数据集提高了7.3%、0.7%、1%和7.2%;在验证阶段的自定义遥感图像数据集上，这四个值分别增长3.1%、2.2%、1.3%和5.7%。在两个数据集上，损失值分别下降2.6%和37.4%。因此，改进模型的应用使得目标的检测更加准确。与其他文献相比，本文改进的模型效果更好。人工扶贫可以被遥感图像处理取代，因为它便宜、高效、准确、客观、不需要数据，而且具有同样的评价效果。所提出的模型可以被认为是评估区域贫困的一种很有前途的方法。
{"title":"Application of Improved YOLO V5s Model for Regional Poverty Assessment Using Remote Sensing Image Target Detection","authors":"Zhang Chenguang, Teng Guifa","doi":"10.14358/pers.23-00005r3","DOIUrl":"https://doi.org/10.14358/pers.23-00005r3","url":null,"abstract":"This study aims at applying the improved You Only Look Once V5s model for the assessment of regional poverty using remote sensing image target detection. The model was improved from structure, algorithm, and components. Objects in the remote sensing images were used to identify poverty, and the poverty alleviation situation could be predicted according to the existing detection results. The results showed that the values of Precision, Recall, mean Average Precision (mAP)@0.5, and mAP@0.5:0.95 of the model increased 7.3%, 0.7%, 1%, and 7.2%, respectively on the Common Objects in Context data set in the detection stage; the four values increased 3.1%, 2.2%, 1.3%, and 5.7%, respectively on the custom remote sensing image data set in the verification stage. The loss values decreased 2.6% and 37.4%, respectively, on the two data sets. Hence, the application of the improved model led to the more accurate detection of the targets. Compared with the other papers, the improved model in this paper proved to be better. Artificial poverty alleviation can be replaced by remote sensing image processing because it is inexpensive, efficient, accurate, objective, does not require data, and has the same evaluation effect. The proposed model can be considered as a promising approach in the assessment of regional poverty.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136161543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Grids and Datums Update: This month we look at the Republic of Botswana","authors":"C. Mugnier","doi":"10.14358/pers.88.2.87","DOIUrl":"https://doi.org/10.14358/pers.88.2.87","url":null,"abstract":"","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"156 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73731757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.14358/pers.21-00045r2
Linze Bai, Q. Cheng, Yuxuan Shu, Sihang Zhang
The aboveground biomass (AGB) of trees plays an important role in the urban ecological environment. Unlike forest biomass estimation, the estimation of AGB of urban trees is greatly influenced by human activities and has strong spatial heterogeneity. In this study, taking Hengqin, China, as an example, we extract the tree area accurately and design a collaborative scheme of optical and lidar data. Finally, five evaluation models are used, including two deep learning models (deep belief network and stacked sparse autoencoder), two machine learning models (random forest and support vector regression), and a geographically weighted regression model. The experimental results show that the deep learning model is effective. The result of the stacked sparse autoen - coder, which is the best model, is that R2 = 0.768 and root mean square error = 18.17 mg/ha. The results show that our method can be applied to estimate the AGB of urban trees, which greatly influences urban ecological construction.
{"title":"Estimating the Aboveground Biomass of Urban Trees by Combining Optical and Lidar Data: A Case Study of Hengqin, Zhuhai, China","authors":"Linze Bai, Q. Cheng, Yuxuan Shu, Sihang Zhang","doi":"10.14358/pers.21-00045r2","DOIUrl":"https://doi.org/10.14358/pers.21-00045r2","url":null,"abstract":"The aboveground biomass (AGB) of trees plays an important role in the urban ecological environment. Unlike forest biomass estimation, the estimation of AGB of urban trees is greatly influenced by human activities and has strong spatial heterogeneity. In this study, taking Hengqin, China,\u0000 as an example, we extract the tree area accurately and design a collaborative scheme of optical and lidar data. Finally, five evaluation models are used, including two deep learning models (deep belief network and stacked sparse autoencoder), two machine learning models (random forest and\u0000 support vector regression), and a geographically weighted regression model. The experimental results show that the deep learning model is effective. The result of the stacked sparse autoen - coder, which is the best model, is that R2 = 0.768 and root mean square error = 18.17\u0000 mg/ha. The results show that our method can be applied to estimate the AGB of urban trees, which greatly influences urban ecological construction.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"76 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83863857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"GIS Tips & Tricks—Sometimes You Need to Turn the World Upside-Down","authors":"Alma M. Karlin","doi":"10.14358/pers.88.2.83","DOIUrl":"https://doi.org/10.14358/pers.88.2.83","url":null,"abstract":"","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"206 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76064637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.14358/pers.21-00023r2
Xuehan Wang, Z. Shao, Xiao Huang, D. Li
High-spatiotemporal-resolution land surface temperature (LST) images are essential in various fields of study. However, due to technical constraints, sensing systems have difficulty in providing LSTs with both high spatial and high temporal resolution. In this study, we propose a multi-scale spatiotemporal temperature-image fusion network (MSTTIFN) to generate high-spatial-resolution LST products. The MSTTIFN builds nonlinear mappings between the input Moderate Resolution Imaging Spectroradiometer (MODIS) LSTs and the out- put Landsat LSTs at the target date with two pairs of references and therefore enhances the resolution of time-series LSTs. We conduct experiments on the actual Landsat and MODIS data in two study areas (Beijing and Shandong) and compare our proposed MSTTIFN with four competing methods: the Spatial and Temporal Adaptive Reflectance Fusion Model, the Flexible Spatiotemporal Data Fusion Model, a two-stream convolutional neural network (StfNet), and a deep learning-based spatiotemporal temperature-fusion network. Results reveal that the MSTTIFN achieves the best and most stable performance.
{"title":"Spatiotemporal Temperature Fusion Based on a Deep Convolutional Network","authors":"Xuehan Wang, Z. Shao, Xiao Huang, D. Li","doi":"10.14358/pers.21-00023r2","DOIUrl":"https://doi.org/10.14358/pers.21-00023r2","url":null,"abstract":"High-spatiotemporal-resolution land surface temperature (LST) images are essential in various fields of study. However, due to technical constraints, sensing systems have difficulty in providing LSTs with both high spatial and high temporal resolution. In this study, we propose a multi-scale spatiotemporal temperature-image fusion network (MSTTIFN) to generate high-spatial-resolution LST products. The MSTTIFN builds nonlinear mappings between the input Moderate Resolution Imaging Spectroradiometer (MODIS) LSTs and the out- put Landsat LSTs at the target date with two pairs of references and therefore enhances the resolution of time-series LSTs. We conduct experiments on the actual Landsat and MODIS data in two study areas (Beijing and Shandong) and compare our proposed MSTTIFN with four competing methods: the Spatial and Temporal Adaptive Reflectance Fusion Model, the Flexible Spatiotemporal Data Fusion Model, a two-stream convolutional neural network (StfNet), and a deep learning-based spatiotemporal temperature-fusion network. Results reveal that the MSTTIFN achieves the best and most stable performance.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"1 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87543077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Postearthquake building damage assessment requires professional judgment; however, there are factors such as high workload and human error. Making use of Terrestrial Laser Scanning data, this paper presents a method for seismic damage information extraction. This new method is based on principal component analysis calculating the local surface curvature of each point in the point cloud. Then use the nearest point angle algorithm, combined with the data features of the actual measured value to identify point cloud seismic information, and filter the points that tend to the plane by setting the threshold value. Based on the statistical analysis of the normal vector, the raw point cloud data are deplanarized to obtain the preliminary results of seismic damage information. The density clustering algorithm is used to denoise the initially extracted seismic damage information. Ultimately, we can obtain the distribution patterns and characteristics of cracks in the walls of the building. The extraction result of the seismic damage information point cloud data is compared with the photos collected at the site, showing that the algorithm steps successfully identify the crack and shed wall skin information recorded in the site photos (identification rate: 95%). Point cloud distribution maps of cracked and shed siding areas determine quantitative information on seismic damage, providing a higher level of performance and detail than direct contact measurements.
{"title":"Three-Dimensional Point Cloud Analysis for Building Seismic Damage Information","authors":"Fan Yang, Zhiwei Fan, Chao Wen, Xiaoshan Wang, Xiaoli Li, Zhiqiang Li, Xintao Wen, Zhanyu Wei","doi":"10.14358/pers.21-00019r3","DOIUrl":"https://doi.org/10.14358/pers.21-00019r3","url":null,"abstract":"Postearthquake building damage assessment requires professional judgment; however, there are factors such as high workload and human error. Making use of Terrestrial Laser Scanning data, this paper presents a method for seismic damage information extraction. This new method is based\u0000 on principal component analysis calculating the local surface curvature of each point in the point cloud. Then use the nearest point angle algorithm, combined with the data features of the actual measured value to identify point cloud seismic information, and filter the points that tend to\u0000 the plane by setting the threshold value. Based on the statistical analysis of the normal vector, the raw point cloud data are deplanarized to obtain the preliminary results of seismic damage information. The density clustering algorithm is used to denoise the initially extracted seismic damage\u0000 information. Ultimately, we can obtain the distribution patterns and characteristics of cracks in the walls of the building. The extraction result of the seismic damage information point cloud data is compared with the photos collected at the site, showing that the algorithm steps successfully\u0000 identify the crack and shed wall skin information recorded in the site photos (identification rate: 95%). Point cloud distribution maps of cracked and shed siding areas determine quantitative information on seismic damage, providing a higher level of performance and detail than direct contact\u0000 measurements.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"4 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90519162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cloud pollution on remote sensing images seriously affects the actual use rate of remote sensing images. Therefore, cloud detection of remote sensing images is an indispensable part of image preprocessing and image availability screening. Aiming at the lack of short wave infrared and thermal infrared bands in ZY-3 high-resolution satellite images resulting in the poor detection effect, considering the obvious difference in geographic height between cloud and ground surface objects, this paper proposes a thick and thin cloud detection method combining spectral information and digital height model (DHM) based on multi-scale features-convolutional neural network (MF-CNN) model. To verify the importance of DHM height information in cloud detection of ZY-3 multi-angle remote sensing images, this paper implements cloud detection comparison of the data set with and without DHM height information based on the MF-CNN model. The experimental results show that the ZY-3 multi-angle image with DHM height information can effectively improve the confusion between highlighted surface and thin cloud, which also means the assistance of DHM height information can make up for the disadvantage of high-resolution image lacking short wave infrared and thermal infrared bands.
{"title":"Cloud Detection in ZY-3 Multi-Angle Remote Sensing Images","authors":"Haiyan Huang, Q. Cheng, Yin Pan, N. Lyimo, Hao Peng, Gui Cheng","doi":"10.14358/pers.21-00086r2","DOIUrl":"https://doi.org/10.14358/pers.21-00086r2","url":null,"abstract":"Cloud pollution on remote sensing images seriously affects the actual use rate of remote sensing images. Therefore, cloud detection of remote sensing images is an indispensable part of image preprocessing and image availability screening. Aiming at the lack of short wave infrared and\u0000 thermal infrared bands in ZY-3 high-resolution satellite images resulting in the poor detection effect, considering the obvious difference in geographic height between cloud and ground surface objects, this paper proposes a thick and thin cloud detection method combining spectral information\u0000 and digital height model (DHM) based on multi-scale features-convolutional neural network (MF-CNN) model. To verify the importance of DHM height information in cloud detection of ZY-3 multi-angle remote sensing images, this paper implements cloud detection comparison of the data set with and\u0000 without DHM height information based on the MF-CNN model. The experimental results show that the ZY-3 multi-angle image with DHM height information can effectively improve the confusion between highlighted surface and thin cloud, which also means the assistance of DHM height information can\u0000 make up for the disadvantage of high-resolution image lacking short wave infrared and thermal infrared bands.","PeriodicalId":49702,"journal":{"name":"Photogrammetric Engineering and Remote Sensing","volume":"29 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81773301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","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：