Pub Date : 2024-04-01DOI: 10.14358/pers.23-00042r2
Seda Nur Gamze Hamal, A. Ulvi
Currently, digital cameras and equipment used underwater are often inaccessible to the general public due to their professional-grade quality and high cost. Therefore alternative solutions have been sought that are both cost-effective and suitable for nonprofessional use. A review of the literature shows that researchers primarily use GoPro action cameras, while other action cameras with similar capabilities are rarely used. This study thus examines underwater photogrammetry methods using a widely recognized action camera as a reference and compares it with another camera of similar characteristics as a potential alternative. For a comprehensive temporal analysis in underwater studies, both cameras were used to capture photographic and video imagery, and the resulting 3D point clouds were compared. Comparison criteria included data collection and processing times, point cloud densities, cloud-to-cloud analysis, and assessments of surface density and roughness. Having analysed, the study concluded that the proposed alternative action camera can feasibly be used in underwater photogrammetry.
{"title":"Investigation of Underwater Photogrammetry Method with Cost-Effective Action Cameras and Comparative Analysis between Reconstructed 3D Point Clouds","authors":"Seda Nur Gamze Hamal, A. Ulvi","doi":"10.14358/pers.23-00042r2","DOIUrl":"https://doi.org/10.14358/pers.23-00042r2","url":null,"abstract":"Currently, digital cameras and equipment used underwater are often inaccessible to the general public due to their professional-grade quality and high cost. Therefore alternative solutions have been sought that are both cost-effective and suitable for nonprofessional use. A review of\u0000 the literature shows that researchers primarily use GoPro action cameras, while other action cameras with similar capabilities are rarely used. This study thus examines underwater photogrammetry methods using a widely recognized action camera as a reference and compares it with another camera\u0000 of similar characteristics as a potential alternative. For a comprehensive temporal analysis in underwater studies, both cameras were used to capture photographic and video imagery, and the resulting 3D point clouds were compared. Comparison criteria included data collection and processing\u0000 times, point cloud densities, cloud-to-cloud analysis, and assessments of surface density and roughness. Having analysed, the study concluded that the proposed alternative action camera can feasibly be used in underwater photogrammetry.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140771263","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 : 2024-04-01DOI: 10.14358/pers.23-00066r2
Zhenhui Sun, Ying Xu, Dongchuan Wang, Qingyan Meng, Yunxiao Sun
This paper proposes a framework that combines the improved "You Only Look Once" version 5 (YOLOv5) and SegFormer to extract tailings ponds from multi-source data. Points of interest (POIs) are crawled to capture potential tailings pond regions. Jeffries–Matusita distance is used to evaluate the optimal band combination. The improved YOLOv5 replaces the backbone with the PoolFormer to form a PoolFormer backbone. The neck introduces the CARAFE operator to form a CARAFE feature pyramid network neck (CRF-FPN). The head is substituted with an efficiency decoupled head. POIs and classification data optimize improved YOLOv5 results. After that, the SegFormer is used to delineate the boundaries of tailings ponds. Experimental results demonstrate that the mean average precision of the improved YOLOv5s has increased by 2.78% compared to the YOLOv5s, achieving 91.18%. The SegFormer achieves an intersection over union of 88.76% and an accuracy of 94.28%.
{"title":"Using Improved YOLOv5 and SegFormer to Extract Tailings Ponds from Multi-Source Data","authors":"Zhenhui Sun, Ying Xu, Dongchuan Wang, Qingyan Meng, Yunxiao Sun","doi":"10.14358/pers.23-00066r2","DOIUrl":"https://doi.org/10.14358/pers.23-00066r2","url":null,"abstract":"This paper proposes a framework that combines the improved \"You Only Look Once\" version 5 (YOLOv5) and SegFormer to extract tailings ponds from multi-source data. Points of interest (POIs) are crawled to capture potential tailings pond regions. Jeffries–Matusita distance is used\u0000 to evaluate the optimal band combination. The improved YOLOv5 replaces the backbone with the PoolFormer to form a PoolFormer backbone. The neck introduces the CARAFE operator to form a CARAFE feature pyramid network neck (CRF-FPN). The head is substituted with an efficiency decoupled head.\u0000 POIs and classification data optimize improved YOLOv5 results. After that, the SegFormer is used to delineate the boundaries of tailings ponds. Experimental results demonstrate that the mean average precision of the improved YOLOv5s has increased by 2.78% compared to the YOLOv5s, achieving\u0000 91.18%. The SegFormer achieves an intersection over union of 88.76% and an accuracy of 94.28%.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140782593","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 : 2024-04-01DOI: 10.14358/pers.23-00010r2
Inam Ullah, Weidong Li, Fanqian Meng, Muhammad Imran Nadeem, Kanwal Ahmed
This article introduces a comprehensive methodology for mapping and assessing the urban built-up areas and establishing a spatial gross domestic product (GDP) model for Zhengzhou using night-time light (NTL) data, alongside socioeconomic statistical data from 2012 to 2017. Two supervised sorting algorithms, namely the support vector machine (SVM) algorithm and the deep learning (DL) algorithm, which includes the U-Net and fully convolutional neural (FCN) network models, are proposed for urban built-up area identification and image classification. Comparisons with Municipal Bureau of Statistics data highlight the U-Net neural network model exhibits superior accuracy, especially in areas with diverse characteristics. For each year from 2012 to 2017, a spatial GDP model was developed based on Zhengzhou's urban GDP and U-Net sorted images. This research provides valuable insights into urban development and economic assessment for the city.
本文介绍了一种利用夜间照明（NTL）数据以及 2012 年至 2017 年的社会经济统计数据绘制和评估城市建成区并建立郑州空间国内生产总值（GDP）模型的综合方法。提出了两种监督分类算法，即支持向量机（SVM）算法和深度学习（DL）算法，其中包括 U-Net 和全卷积神经（FCN）网络模型，用于城市建成区识别和图像分类。通过与市统计局数据的比较，U-Net 神经网络模型显示出更高的准确性，尤其是在具有不同特征的区域。基于郑州城市 GDP 和 U-Net 分类图像，建立了 2012 年至 2017 年每年的空间 GDP 模型。这项研究为该市的城市发展和经济评估提供了有价值的见解。
{"title":"GDP Spatialization in City of Zhengzhou Based on NPP/VIIRS Night-time Light and Socioeconomic Statistical Data Using Machine Learning","authors":"Inam Ullah, Weidong Li, Fanqian Meng, Muhammad Imran Nadeem, Kanwal Ahmed","doi":"10.14358/pers.23-00010r2","DOIUrl":"https://doi.org/10.14358/pers.23-00010r2","url":null,"abstract":"This article introduces a comprehensive methodology for mapping and assessing the urban built-up areas and establishing a spatial gross domestic product (GDP) model for Zhengzhou using night-time light (NTL) data, alongside socioeconomic statistical data from 2012 to 2017. Two supervised\u0000 sorting algorithms, namely the support vector machine (SVM) algorithm and the deep learning (DL) algorithm, which includes the U-Net and fully convolutional neural (FCN) network models, are proposed for urban built-up area identification and image classification. Comparisons with Municipal\u0000 Bureau of Statistics data highlight the U-Net neural network model exhibits superior accuracy, especially in areas with diverse characteristics. For each year from 2012 to 2017, a spatial GDP model was developed based on Zhengzhou's urban GDP and U-Net sorted images. This research provides\u0000 valuable insights into urban development and economic assessment for the city.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140755885","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}
A devastating landslide incident occurred on 24 June 2017, causing huge losses for Xinmo Village in western Sichuan. In this paper, we used two interferometric synthetic aperture radar (InSAR) methods, permanent scatterer (PS)-InSAR and small baseline subset (SBAS)- InSAR, to analyze deformation signals in the area in the 2 years leading up to the landslide event using Sentinel-1A ascending data. Our experimental findings from PS-InSAR and SBAS-InSAR revealed that the deformation rates in the study region ranged between –50 to 20 mm/year and –30 to 10 mm/year, respectively. Furthermore, the deformation rates of the same points, as determined by these methods, exhibited a significant increase prior to the event. We also investigated the causal relationship between rainfall and landslide events, demonstrating that deformation rates correlate with changes in rainfall, albeit with a time lag. Therefore, using time-series InSAR for landslide monitoring in Xinmo Village is a viable approach.
{"title":"Monitoring Based on InSAR for the Xinmo Village Landslide in Western Sichuan, China","authors":"Zezhong Zheng, Shuang Yu, Chuhang Xie, Jiali Yang, Mingcang Zhu, He Yong","doi":"10.14358/pers.23-00072r2","DOIUrl":"https://doi.org/10.14358/pers.23-00072r2","url":null,"abstract":"A devastating landslide incident occurred on 24 June 2017, causing huge losses for Xinmo Village in western Sichuan. In this paper, we used two interferometric synthetic aperture radar (InSAR) methods, permanent scatterer (PS)-InSAR and small baseline subset (SBAS)- InSAR, to analyze\u0000 deformation signals in the area in the 2 years leading up to the landslide event using Sentinel-1A ascending data. Our experimental findings from PS-InSAR and SBAS-InSAR revealed that the deformation rates in the study region ranged between –50 to 20 mm/year and –30 to 10 mm/year,\u0000 respectively. Furthermore, the deformation rates of the same points, as determined by these methods, exhibited a significant increase prior to the event. We also investigated the causal relationship between rainfall and landslide events, demonstrating that deformation rates correlate with\u0000 changes in rainfall, albeit with a time lag. Therefore, using time-series InSAR for landslide monitoring in Xinmo Village is a viable approach.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140760765","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}
As we are writing this column from Florida, it is early January, and the trees are beginning to leaf out. I am reminded that spring is still three months away. So, looking forward to the spring, we are thinking of helpful, hidden (aka Easter eggs), and not-so-obvious features that are easy to overlook in GIS software programs. With the help of my colleagues, Chloe Eaton and Zac Winters, we compiled three GIS Tips and Tricks to increase your GIS workflow efficiency using not-so-obvious features.
{"title":"GIS Tips & Tricks","authors":"Chloe Eaton, Zachary Winters, Al Karlin","doi":"10.14358/pers.90.4.193","DOIUrl":"https://doi.org/10.14358/pers.90.4.193","url":null,"abstract":"As we are writing this column from Florida, it is early January, and the trees are beginning to leaf out. I am reminded that spring is still three months away. So, looking forward to the spring, we are thinking of helpful, hidden (aka Easter eggs), and not-so-obvious features that are\u0000 easy to overlook in GIS software programs. With the help of my colleagues, Chloe Eaton and Zac Winters, we compiled three GIS Tips and Tricks to increase your GIS workflow efficiency using not-so-obvious features.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140788209","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}
Dr. Abdullah: Your concern about the concept of using two different datums to represent the horizontal and vertical position and height is valid, and using a single datum for both horizontal and vertical coordinates sounds like a good idea. A single datum representing horizontal coordinates and height is possible and may be used for certain applications. Unfortunately it is not practical for many of us in the mapping industry. The World Geodetic Systems of 1984 (WGS84) and the International Terrestrial Reference System (ITRS) are examples of such three-dimensional systems. WGS84 and ITRS provide users with unique position and height values based on the three-dimensional Cartesian system. The Cartesian system, when associated with a geo-centric system (in which the center of the system’s ellipsoid coincides with or near the mass center of Earth), is known as Earth Centered, Earth Fixed (ECEF). Therefore, position and height of a point near or on the surface of the Earth as defined by ECEF systems are referenced to the mass center of the Earth (or near it). GPS provides global positions (X,Y,Z) in WGS84-based ECEF systems. To many users, expressing coordinates in ECEF is not practical as positions are referenced to the mass center of the Earth. The following values are the three-dimensional coordinates for the CORS station AMC2 located in Colorado Springs, Colorado, USA based on ITRF2000 ECEF: X = -1248596.072 m | Y = -4819428.218 m | Z = 3976506.023 m The above coordinates are also published in geographic representation as follows: latitude = 38o 48’ 11.249150” N longitude = 104o 31’ 28.53276” W ellipsoid height = 1911.393m Examining the above coordinates one can easily realize that the height value of 3,976,506.023m is too large to deal with or to interpret. In addition, the geo-centric derived height, or Z, is not practical from the operational sense as it represents the perpendicular distance between the reference point and the plane of the equator and not the distance from the reference point to the local geoid as users are accustomed to. There are other reasons that have prevented users from using the three-dimensional ECEF for day-to-day operations, but there is no room in this column to discuss those. While using heights based on ellipsoidal, such GPS-derived heights based on WGS84, may serve the field commanders of the armed forces, it does not serve the needs of the larger community of users who are conducting accurate engineering operations for dams, sewers and pipelines, and tunnels. The previous operations require topographic details that reflect and explain the actual direction of water flow as influenced by gravity. Also, aircraft navigation databases need to provide pilots with accurate ground elevation to maintain constant altitude above the actual surface of the Earth. These are just examples on the reasons behind The orthometric height, which is derived from the geoid model that is modeled through gravity measurements, has a phys
阿卜杜拉博士你对使用两个不同的基准点来表示水平和垂直位置和高度的概念的担忧是有道理的，使用单一的基准点来表示水平和垂直坐标听起来是个好主意。用一个基准点来表示水平坐标和高度是可行的，在某些应用中也可以使用。遗憾的是，这对我们许多制图行业的人来说并不实用。1984 年世界大地测量系统 (WGS84) 和国际地面参考系统 (ITRS) 就是这种三维系统的例子。WGS84 和 ITRS 为用户提供基于三维笛卡尔系统的唯一位置和高度值。笛卡尔系统与地球中心系统（系统椭球中心与地球质心重合或接近地球质心）相关联时，被称为 "以地球为中心，固定在地球上"（ECEF）。因此，ECEF 系统所定义的地球附近或地球表面某点的位置和高度是以地球质量中心（或其附近）为参照的。全球定位系统以基于 WGS84 的 ECEF 系统提供全球位置（X、Y、Z）。对许多用户来说，用 ECEF 表示坐标并不实用，因为位置是以地球质量中心为参照的。以下是位于美国科罗拉多州科罗拉多斯普林斯的 CORS 站 AMC2 基于 ITRF2000 ECEF 的三维坐标值：X = -1248596.072 m | Y = -4819428.218 m | Z = 3976506.023 m 上述坐标的地理表示法也公布如下：纬度 = 38o 48' 11.249150" N 经度 = 104o 31' 28.53276" W 椭圆体高度 = 1911.393m 检查上述坐标，不难发现 3976506.023m 的高度值太大，难以处理或解释。此外，从操作意义上讲，地心推导高度或 Z 值并不实用，因为它代表的是参考点与赤道平面之间的垂直距离，而不是用户习惯的参考点与当地大地水准面之间的距离。还有其他原因妨碍用户在日常操作中使用三维 ECEF，但本专栏没有讨论这些问题的余地。虽然使用基于椭球面的高程，如基于 WGS84 的 GPS 导出高程，可以满足武装部队战地指挥官的需要，但却不能满足更多用户的需要，这些用户正在对水坝、下水道和管道以及隧道进行精确的工程作业。以前的工程需要地形细节，以反映和解释受重力影响的实际水流方向。此外，飞机导航数据库也需要为飞行员提供准确的地面高程，以保持在地球实际表面之上的恒定高度。以上只是举例说明正测高度背后的原因。正测高度来自通过重力测量建立模型的大地水准面模型，具有物理意义，被认为是高度的自然定义，因为重力是水流下山的原因。
{"title":"Mapping Matters: The layman's perspective on technical theory and practical applications of mapping and GIS","authors":"Qassim A. Abdullah","doi":"10.14358/pers.90.4.197","DOIUrl":"https://doi.org/10.14358/pers.90.4.197","url":null,"abstract":"Dr. Abdullah: Your concern about the concept of using two different datums to represent the horizontal and vertical position and height is valid, and using a single datum for both horizontal and vertical coordinates sounds like a good idea. A single datum representing horizontal coordinates and height is possible and may be used for certain applications. Unfortunately it is not practical for many of us in the mapping industry. The World Geodetic Systems of 1984 (WGS84) and the International Terrestrial Reference System (ITRS) are examples of such three-dimensional systems. WGS84 and ITRS provide users with unique position and height values based on the three-dimensional Cartesian system. The Cartesian system, when associated with a geo-centric system (in which the center of the system’s ellipsoid coincides with or near the mass center of Earth), is known as Earth Centered, Earth Fixed (ECEF). Therefore, position and height of a point near or on the surface of the Earth as defined by ECEF systems are referenced to the mass center of the Earth (or near it). GPS provides global positions (X,Y,Z) in WGS84-based ECEF systems. To many users, expressing coordinates in ECEF is not practical as positions are referenced to the mass center of the Earth. The following values are the three-dimensional coordinates for the CORS station AMC2 located in Colorado Springs, Colorado, USA based on ITRF2000 ECEF: X = -1248596.072 m | Y = -4819428.218 m | Z = 3976506.023 m The above coordinates are also published in geographic representation as follows: latitude = 38o 48’ 11.249150” N longitude = 104o 31’ 28.53276” W ellipsoid height = 1911.393m Examining the above coordinates one can easily realize that the height value of 3,976,506.023m is too large to deal with or to interpret. In addition, the geo-centric derived height, or Z, is not practical from the operational sense as it represents the perpendicular distance between the reference point and the plane of the equator and not the distance from the reference point to the local geoid as users are accustomed to. There are other reasons that have prevented users from using the three-dimensional ECEF for day-to-day operations, but there is no room in this column to discuss those. While using heights based on ellipsoidal, such GPS-derived heights based on WGS84, may serve the field commanders of the armed forces, it does not serve the needs of the larger community of users who are conducting accurate engineering operations for dams, sewers and pipelines, and tunnels. The previous operations require topographic details that reflect and explain the actual direction of water flow as influenced by gravity. Also, aircraft navigation databases need to provide pilots with accurate ground elevation to maintain constant altitude above the actual surface of the Earth. These are just examples on the reasons behind The orthometric height, which is derived from the geoid model that is modeled through gravity measurements, has a phys","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140789295","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 : 2024-03-01DOI: 10.14358/pers.23-00049r2
Xinyi Liu, Qingwu Hu, Xianfeng Huang
In this paper, we propose a novel approach for the extraction of high-quality frames to enhance the fidelity of videogrammetry by combining fuzzy frames removal and baseline constraints. We first implement a gradient-based mutual information method to filter out low-quality frames while preserving the integrity of the videos. After frame pose estimation, the geometric properties of the baseline are constrained by three aspects to extract the keyframes: quality of relative orientation, baseline direction, and base to distance ratio. The three-dimensional model is then reconstructed based on these extracted keyframes. Experimental results demonstrate that our approach maintains a strong robustness throughout the aerial triangulation, leading to high levels of reconstruction precision across diverse video scenarios. Compared to other methods, this paper improves the reconstruction accuracy by more than 0.2 mm while simultaneously maintaining the completeness.
{"title":"A Keyframe Extraction Approach for 3D Videogrammetry Based on Baseline Constraints","authors":"Xinyi Liu, Qingwu Hu, Xianfeng Huang","doi":"10.14358/pers.23-00049r2","DOIUrl":"https://doi.org/10.14358/pers.23-00049r2","url":null,"abstract":"In this paper, we propose a novel approach for the extraction of high-quality frames to enhance the fidelity of videogrammetry by combining fuzzy frames removal and baseline constraints. We first implement a gradient-based mutual information method to filter out low-quality frames while\u0000 preserving the integrity of the videos. After frame pose estimation, the geometric properties of the baseline are constrained by three aspects to extract the keyframes: quality of relative orientation, baseline direction, and base to distance ratio. The three-dimensional model is then reconstructed\u0000 based on these extracted keyframes. Experimental results demonstrate that our approach maintains a strong robustness throughout the aerial triangulation, leading to high levels of reconstruction precision across diverse video scenarios. Compared to other methods, this paper improves the reconstruction\u0000 accuracy by more than 0.2 mm while simultaneously maintaining the completeness.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140087813","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 : 2024-03-01DOI: 10.14358/pers.23-00018r2
Hamid Gharibi, Ayman Habib
The density and uniformity of lidar data play crucial roles in the cor-responding data processing steps. One factor influencing point density and spacing in lidar data is the presence of empty pulses, where no return is detected. Missing returns can occur due to atmospheric absorption, specular and diffusive reflection, etc. To address this issue and enhance point density, this paper introduces a novel method for approximating missing returns in airborne lidar data collected over urban areas. This technique focuses on approximating returns for empty pulses that hit spots near abrupt slope changes on building and ground surfaces. The proposed methodology is validated through experiments using a lidar data set from downtown Dublin, Ireland. The collected data contained numerous gaps associated with wet surfaces, as well as missing returns on vertical and oblique surfaces.
{"title":"Scan Angle Analysis of Airborne Lidar Data for Missing Return Approximation in Urban Areas","authors":"Hamid Gharibi, Ayman Habib","doi":"10.14358/pers.23-00018r2","DOIUrl":"https://doi.org/10.14358/pers.23-00018r2","url":null,"abstract":"The density and uniformity of lidar data play crucial roles in the cor-responding data processing steps. One factor influencing point density and spacing in lidar data is the presence of empty pulses, where no return is detected. Missing returns can occur due to atmospheric absorption,\u0000 specular and diffusive reflection, etc. To address this issue and enhance point density, this paper introduces a novel method for approximating missing returns in airborne lidar data collected over urban areas. This technique focuses on approximating returns for empty pulses that hit spots\u0000 near abrupt slope changes on building and ground surfaces. The proposed methodology is validated through experiments using a lidar data set from downtown Dublin, Ireland. The collected data contained numerous gaps associated with wet surfaces, as well as missing returns on vertical and oblique\u0000 surfaces.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140091661","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}
{"title":"Geospatial Data, Information, and Intelligence by Aaron Jabbour and Renny Babiarz","authors":"D. Zourarakis","doi":"10.14358/pers.90.3.139","DOIUrl":"https://doi.org/10.14358/pers.90.3.139","url":null,"abstract":"","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140085845","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 : 2024-03-01DOI: 10.14358/pers.23-00069r2
Fengcan Peng, Qiuzhi Peng, Di Chen, Jiating Lu, Yufei Song
To extract terraced fields in hilly areas on a large scale in an automated and high-precision manner, this paper proposes a terrace extraction method that combines the Digital Elevation Model (DEM), Sentinel-2 imagery, and the improved U-Net semantic segmentation model. The U-Net model is modified by introducing Attention Gate modules into its decoding modules to suppress the interference of redundant features and adding Dropout and Batch Normalization layers to improve training speed, robustness, and fitting ability. In addition, the DEM band is combined with the red, green, and blue bands of the remote sensing images to make full use of terrain information. The experimental results show that the Precision, Recall, F1 score, and Mean Intersection over Union of the proposed method for terrace extraction are improved to other mainstream advanced methods, and the internal information of the terraces extracted is more complete, with fewer false positive and false negative results.
为了自动、高精度地大规模提取丘陵地区的梯田，本文提出了一种结合数字高程模型（DEM）、哨兵-2 图像和改进的 U-Net 语义分割模型的梯田提取方法。本文对 U-Net 模型进行了改进，在其解码模块中引入注意门模块以抑制冗余特征的干扰，并增加了 Dropout 层和批量归一化层以提高训练速度、鲁棒性和拟合能力。此外，还将 DEM 波段与遥感图像的红绿蓝波段相结合，以充分利用地形信息。实验结果表明，所提出的梯田提取方法的精度、召回率、F1 分数和平均交叉比 Union 均优于其他主流先进方法，提取的梯田内部信息更加完整，假阳性和假阴性结果更少。
{"title":"Extraction of Terraces in Hilly Areas from Remote Sensing Images Using DEM and Improved U-Net","authors":"Fengcan Peng, Qiuzhi Peng, Di Chen, Jiating Lu, Yufei Song","doi":"10.14358/pers.23-00069r2","DOIUrl":"https://doi.org/10.14358/pers.23-00069r2","url":null,"abstract":"To extract terraced fields in hilly areas on a large scale in an automated and high-precision manner, this paper proposes a terrace extraction method that combines the Digital Elevation Model (DEM), Sentinel-2 imagery, and the improved U-Net semantic segmentation model. The U-Net model\u0000 is modified by introducing Attention Gate modules into its decoding modules to suppress the interference of redundant features and adding Dropout and Batch Normalization layers to improve training speed, robustness, and fitting ability. In addition, the DEM band is combined with the red, green,\u0000 and blue bands of the remote sensing images to make full use of terrain information. The experimental results show that the Precision, Recall, F1 score, and Mean Intersection over Union of the proposed method for terrace extraction are improved to other mainstream advanced methods, and the\u0000 internal information of the terraces extracted is more complete, with fewer false positive and false negative results.","PeriodicalId":211256,"journal":{"name":"Photogrammetric Engineering & Remote Sensing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140087932","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：