Pub Date : 2024-06-10DOI: 10.5194/isprs-annals-x-2-2024-247-2024
J. Zhong, Ming Li, A. Gruen, Jianya Gong, Deren Li, Mingjie Li, J. Qin
Abstract. Underwater mapping is vital for engineering applications and scientific research in ocean environments, with coral reefs being a primary focus. Unlike more uniform and predictable terrestrial environments, coral reefs present a unique challenge for 3D reconstruction due to their intricate and irregular structures. Traditional 3D reconstruction methods struggle to accurately capture the nuances of coral reefs. This is primarily because coral reefs exhibit a high degree of spatial heterogeneity, featuring diverse shapes, sizes, and textures. Additionally, the dynamic nature of underwater conditions, such as varying light, water clarity, and movement, further complicates the accurate geometrical estimation of these ecosystems. With the rapid advancement of photogrammetric computer vision and deep learning technologies, there are emerging methods that have potential to enhance the quality of its 3D reconstruction. In this context, this study formulates a coral reef reconstruction workflow that incorporates these cutting-edge technologies. This workflow is divided into two core stages: sparse reconstruction and dense reconstruction. We conduct individual summaries of the relevant research efforts in these stages and outline the available methods. To assess the specific capabilities of these methods, we apply them to real-world coral reef images and conduct a comprehensive evaluation. Additionally, we analyze the strengths and weaknesses of different methods and identify areas for improvement. We believe this study offers valuable references for future research in underwater mapping.
{"title":"Application of Photogrammetric Computer Vision and Deep Learning in High-Resolution Underwater Mapping: A Case Study of Shallow-Water Coral Reefs","authors":"J. Zhong, Ming Li, A. Gruen, Jianya Gong, Deren Li, Mingjie Li, J. Qin","doi":"10.5194/isprs-annals-x-2-2024-247-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-247-2024","url":null,"abstract":"Abstract. Underwater mapping is vital for engineering applications and scientific research in ocean environments, with coral reefs being a primary focus. Unlike more uniform and predictable terrestrial environments, coral reefs present a unique challenge for 3D reconstruction due to their intricate and irregular structures. Traditional 3D reconstruction methods struggle to accurately capture the nuances of coral reefs. This is primarily because coral reefs exhibit a high degree of spatial heterogeneity, featuring diverse shapes, sizes, and textures. Additionally, the dynamic nature of underwater conditions, such as varying light, water clarity, and movement, further complicates the accurate geometrical estimation of these ecosystems. With the rapid advancement of photogrammetric computer vision and deep learning technologies, there are emerging methods that have potential to enhance the quality of its 3D reconstruction. In this context, this study formulates a coral reef reconstruction workflow that incorporates these cutting-edge technologies. This workflow is divided into two core stages: sparse reconstruction and dense reconstruction. We conduct individual summaries of the relevant research efforts in these stages and outline the available methods. To assess the specific capabilities of these methods, we apply them to real-world coral reef images and conduct a comprehensive evaluation. Additionally, we analyze the strengths and weaknesses of different methods and identify areas for improvement. We believe this study offers valuable references for future research in underwater mapping.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"107 32","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141361273","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-2-2024-171-2024
David Novikov, Paul Sotirelis, Alper Yilmaz
Abstract. We have developed a robust, novel, and cost-effective method for determining the geolocation of vehicles observed in drone camera footage. Previous studies in this area have relied on platform GPS and camera geometry to estimate the position of objects in drone footage, which we will refer to as object-to-drone location (ODL). The performance of these techniques is degraded with decreasing GPS measurement accuracy and camera orientation problems. Our method overcomes these shortcomings and reliably geolocates objects on the ground. We refer to our approach as object-to-map localization (OML). The proposed technique determines a transformation between drone camera footage and georectified aerial images, for example, from Google Maps. This transformation is then used to calculate the positions of objects captured in the drone camera footage. We provide an ablation study of our method’s configuration parameter, which are: feature extraction methods, key point filtering schemes, and types of transformations. We also conduct experiments with a simulated faulty GPS to demonstrate our method’s robustness to poor estimation of the drone’s position. Our approach requires only a drone with a camera and a low-accuracy estimate of its geoposition, we do not rely on markers or ground control points. As a result, our method can determine the geolocation of vehicles on the ground in an easy-to-set up and costeffective manner, making object geolocalization more accessible to users by decreasing the hardware and software requirements. Our GitHub with code can be found at https://github.com/OSUPCVLab/VehicleGeopositioning
{"title":"Vehicle Geolocalization from Drone Imagery","authors":"David Novikov, Paul Sotirelis, Alper Yilmaz","doi":"10.5194/isprs-annals-x-2-2024-171-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-171-2024","url":null,"abstract":"Abstract. We have developed a robust, novel, and cost-effective method for determining the geolocation of vehicles observed in drone camera footage. Previous studies in this area have relied on platform GPS and camera geometry to estimate the position of objects in drone footage, which we will refer to as object-to-drone location (ODL). The performance of these techniques is degraded with decreasing GPS measurement accuracy and camera orientation problems. Our method overcomes these shortcomings and reliably geolocates objects on the ground. We refer to our approach as object-to-map localization (OML). The proposed technique determines a transformation between drone camera footage and georectified aerial images, for example, from Google Maps. This transformation is then used to calculate the positions of objects captured in the drone camera footage. We provide an ablation study of our method’s configuration parameter, which are: feature extraction methods, key point filtering schemes, and types of transformations. We also conduct experiments with a simulated faulty GPS to demonstrate our method’s robustness to poor estimation of the drone’s position. Our approach requires only a drone with a camera and a low-accuracy estimate of its geoposition, we do not rely on markers or ground control points. As a result, our method can determine the geolocation of vehicles on the ground in an easy-to-set up and costeffective manner, making object geolocalization more accessible to users by decreasing the hardware and software requirements. Our GitHub with code can be found at https://github.com/OSUPCVLab/VehicleGeopositioning\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"8 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141362796","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-2-2024-239-2024
Hongxin Yang, Shangfeng Huang, Ruisheng Wang
Abstract. In this paper, we present a two-stage method for roof wireframe reconstruction employing a self-supervised pretraining technique. The initial stage utilizes a multi-scale mask autoencoder to generate point-wise features. The subsequent stage involves three steps for edge parameter regression. Firstly, the initial edge directions are generated under the guidance of edge point identification. The next step employs edge parameter regression and matching modules to extract the parameters (namely, direction vector and length) of edge representation from the obtained edge features. Finally, a specifically designed edge non-maximum suppression and an edge similarity loss function are employed to optimize the representation of the final wireframe models and eliminate redundant edges. Experimental results indicate that the pre-trained self-supervised model, enriched by the roof wireframe reconstruction task, demonstrates superior performance on both the publicly available Building3D dataset and its post-processed iterations, specifically the Dense dataset, outperforming even traditional methods.
{"title":"A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining","authors":"Hongxin Yang, Shangfeng Huang, Ruisheng Wang","doi":"10.5194/isprs-annals-x-2-2024-239-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-239-2024","url":null,"abstract":"Abstract. In this paper, we present a two-stage method for roof wireframe reconstruction employing a self-supervised pretraining technique. The initial stage utilizes a multi-scale mask autoencoder to generate point-wise features. The subsequent stage involves three steps for edge parameter regression. Firstly, the initial edge directions are generated under the guidance of edge point identification. The next step employs edge parameter regression and matching modules to extract the parameters (namely, direction vector and length) of edge representation from the obtained edge features. Finally, a specifically designed edge non-maximum suppression and an edge similarity loss function are employed to optimize the representation of the final wireframe models and eliminate redundant edges. Experimental results indicate that the pre-trained self-supervised model, enriched by the roof wireframe reconstruction task, demonstrates superior performance on both the publicly available Building3D dataset and its post-processed iterations, specifically the Dense dataset, outperforming even traditional methods.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":"119 44","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141361962","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-2-2024-193-2024
M. Recla, Michael Schmitt
Abstract. Rapid mapping demands efficient methods for a fast extraction of information from satellite data while minimizing data requirements. This paper explores the potential of deep learning for the generation of high-resolution urban elevation data from Synthetic Aperture Radar (SAR) imagery. In order to mitigate occlusion effects caused by the side-looking nature of SAR remote sensing, two SAR images from opposing aspects are leveraged and processed in an end-to-end deep neural network. The presented approach is the first of its kind to implicitly handle the transition from the SAR-specific slant range geometry to a ground-based mapping geometry within the model architecture. Comparative experiments demonstrate the superiority of the dual-aspect fusion over single-image methods in terms of reconstruction quality and geolocation accuracy. Notably, the model exhibits robust performance across diverse acquisition modes and geometries, showcasing its generalizability and suitability for height mapping applications. The study’s findings underscore the potential of deep learning-driven SAR techniques in generating high-quality urban surface models efficiently and economically.
{"title":"Deep Learning-based DSM Generation from Dual-Aspect SAR Data","authors":"M. Recla, Michael Schmitt","doi":"10.5194/isprs-annals-x-2-2024-193-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-193-2024","url":null,"abstract":"Abstract. Rapid mapping demands efficient methods for a fast extraction of information from satellite data while minimizing data requirements. This paper explores the potential of deep learning for the generation of high-resolution urban elevation data from Synthetic Aperture Radar (SAR) imagery. In order to mitigate occlusion effects caused by the side-looking nature of SAR remote sensing, two SAR images from opposing aspects are leveraged and processed in an end-to-end deep neural network. The presented approach is the first of its kind to implicitly handle the transition from the SAR-specific slant range geometry to a ground-based mapping geometry within the model architecture. Comparative experiments demonstrate the superiority of the dual-aspect fusion over single-image methods in terms of reconstruction quality and geolocation accuracy. Notably, the model exhibits robust performance across diverse acquisition modes and geometries, showcasing its generalizability and suitability for height mapping applications. The study’s findings underscore the potential of deep learning-driven SAR techniques in generating high-quality urban surface models efficiently and economically.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 85","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141365224","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-2-2024-41-2024
Johannes Dollinger, Philipp Brun, Vivien Sainte Fare Garnot, Jan Dirk Wegner
Abstract. We propose a deep learning approach for high-resolution species distribution modelling (SDM) at large scale combining point-wise, crowd-sourced species observation data and environmental data with Sentinel-2 satellite imagery. What makes this task challenging is the great variety of controlling factors for species distribution, such as habitat conditions, human intervention, competition, disturbances, and evolutionary history. Experts either incorporate these factors into complex mechanistic models based on presence-absence data collected in field campaigns or train machine learning models to learn the relationship between environmental data and presence-only species occurrence. We extend the latter approach here and learn deep SDMs end-to-end based on point-wise, crowd-sourced presence-only data in combination with satellite imagery. Our method, dubbed Sat-SINR, jointly models the spatial distributions of 5.6k plant species across Europe and increases the spatial resolution by a factor of 100 compared to the current state of the art. We exhaustively test and ablate multiple variations of combining geo-referenced point data with satellite imagery and show that our deep learning-based SDM method consistently shows an improvement of up to 3 percentage points across three metrics. We make all code publicly available at https://github.com/ecovision-uzh/sat-sinr.
{"title":"Sat-SINR: High-Resolution Species Distribution Models Through Satellite Imagery","authors":"Johannes Dollinger, Philipp Brun, Vivien Sainte Fare Garnot, Jan Dirk Wegner","doi":"10.5194/isprs-annals-x-2-2024-41-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-41-2024","url":null,"abstract":"Abstract. We propose a deep learning approach for high-resolution species distribution modelling (SDM) at large scale combining point-wise, crowd-sourced species observation data and environmental data with Sentinel-2 satellite imagery. What makes this task challenging is the great variety of controlling factors for species distribution, such as habitat conditions, human intervention, competition, disturbances, and evolutionary history. Experts either incorporate these factors into complex mechanistic models based on presence-absence data collected in field campaigns or train machine learning models to learn the relationship between environmental data and presence-only species occurrence. We extend the latter approach here and learn deep SDMs end-to-end based on point-wise, crowd-sourced presence-only data in combination with satellite imagery. Our method, dubbed Sat-SINR, jointly models the spatial distributions of 5.6k plant species across Europe and increases the spatial resolution by a factor of 100 compared to the current state of the art. We exhaustively test and ablate multiple variations of combining geo-referenced point data with satellite imagery and show that our deep learning-based SDM method consistently shows an improvement of up to 3 percentage points across three metrics. We make all code publicly available at https://github.com/ecovision-uzh/sat-sinr.\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":"141365618","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}
Abstract. Airborne laser scanning (ALS) is able to penetrate sparse vegetation to obtain highly accurate height information on the ground surface. LiDAR point cloud filtering is an important prerequisite for downstream tasks such as digital terrain model (DTM) extraction and point cloud classification. Aiming at the problem that existing LiDAR point cloud filtering algorithms are prone to errors in complex terrain environments, an ALS point cloud filtering method based on supervoxel ground saliency (SGSF) is proposed in this paper. Firstly, a boundary-preserving TBBP supervoxel algorithm is utilized to perform supervoxel segmentation of ALS point clouds, and multi-directional scanning strip delineation and ground saliency computation are carried out for the clusters of supervoxel point clouds. Subsequently, the energy function is constructed by introducing the ground saliency and the optimal filtering plane of the supervoxel is solved using the semi-global optimization idea to realize the effective distinction between ground and non-ground points. Experimental results on the ALS point cloud filtering dataset openGF indicate that, compared to state-of-the-art surface-based filtering methods, the SGSF algorithm achieves the highest average values across various terrain conditions for multiple evaluation metrics. It also addresses the issue of recessed structures in buildings being prone to misclassification as ground points.
摘要。机载激光扫描（ALS）能够穿透稀疏植被，获取地表高精度高度信息。激光雷达点云过滤是数字地形模型（DTM）提取和点云分类等下游任务的重要前提。针对现有的激光雷达点云滤波算法在复杂地形环境下容易产生误差的问题，本文提出了一种基于上像素地面显著性（SGSF）的 ALS 点云滤波方法。首先，利用保界 TBBP 上像素算法对 ALS 点云进行上像素分割，并对上像素点云簇进行多向扫描带划分和地面突出度计算。随后，通过引入地面突出度构建能量函数，并利用半全局优化思想求解上位点的最优滤波平面，从而实现地面点与非地面点的有效区分。在 ALS 点云过滤数据集 openGF 上的实验结果表明，与最先进的基于地表的过滤方法相比，SGSF 算法在各种地形条件下的多个评价指标的平均值最高。它还解决了建筑物中的凹陷结构容易被误判为地面点的问题。
{"title":"Airborne LiDAR Point Cloud Filtering Algorithm Based on Supervoxel Ground Saliency","authors":"Weiwei Fan, Xinyi Liu, Yongjun Zhang, Dongdong Yue, Senyuan Wang, Jiachen Zhong","doi":"10.5194/isprs-annals-x-2-2024-73-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-2-2024-73-2024","url":null,"abstract":"Abstract. Airborne laser scanning (ALS) is able to penetrate sparse vegetation to obtain highly accurate height information on the ground surface. LiDAR point cloud filtering is an important prerequisite for downstream tasks such as digital terrain model (DTM) extraction and point cloud classification. Aiming at the problem that existing LiDAR point cloud filtering algorithms are prone to errors in complex terrain environments, an ALS point cloud filtering method based on supervoxel ground saliency (SGSF) is proposed in this paper. Firstly, a boundary-preserving TBBP supervoxel algorithm is utilized to perform supervoxel segmentation of ALS point clouds, and multi-directional scanning strip delineation and ground saliency computation are carried out for the clusters of supervoxel point clouds. Subsequently, the energy function is constructed by introducing the ground saliency and the optimal filtering plane of the supervoxel is solved using the semi-global optimization idea to realize the effective distinction between ground and non-ground points. Experimental results on the ALS point cloud filtering dataset openGF indicate that, compared to state-of-the-art surface-based filtering methods, the SGSF algorithm achieves the highest average values across various terrain conditions for multiple evaluation metrics. It also addresses the issue of recessed structures in buildings being prone to misclassification as ground points.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141363448","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 : 2024-05-09DOI: 10.5194/isprs-annals-x-1-2024-225-2024
Bo Wang, Yu Liu, Qinghong Sheng, Jun Li, Shuwei Wang, Yunfeng Qiao, Honglin He
Abstract. Synthetic aperture radar (SAR) has emerged as a promising technology for monitoring crop plant height due to its ability to capture the geometric properties of crops. Radar vegetation index (RVI) has been extensively utilized for qualitative and quantitative remote sensing monitoring of vegetation growth dynamics. However, the combination of crop, growing environment, and temporal dynamics makes crop monitoring data a complex task. Despite the relatively simple underlying mechanisms of this phenomenon, there is still a need for more research to identify specific vegetation structures that correspond to changes in the response of vegetation indices. Building upon this premise, this study utilized a dynamic monitoring model to conduct dynamic monitoring of plant height for three common crops: rice, wheat, and maize. The findings revealed that (1) models developed for specific spatial and temporal scales of particular crop varieties may not accurately predict crop growth in different regions or with different varieties in a timely manner, due to growth variations; (2) these models maintain accuracy over a range of plant heights, such as rice at around 70cm, wheat at around 50cm, and maize at around 150cm; (3) among the three crops, planting density was identified as the main factor influencing the differences in RVI response. This research contributes to our comprehension of the dynamic response of RVI to different growth conditions in crops, and offers valuable insights and references for agricultural monitoring.
{"title":"Exploring the effects of crop growth differences on radar vegetation index response and crop height estimation using dynamic monitoring model","authors":"Bo Wang, Yu Liu, Qinghong Sheng, Jun Li, Shuwei Wang, Yunfeng Qiao, Honglin He","doi":"10.5194/isprs-annals-x-1-2024-225-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-1-2024-225-2024","url":null,"abstract":"Abstract. Synthetic aperture radar (SAR) has emerged as a promising technology for monitoring crop plant height due to its ability to capture the geometric properties of crops. Radar vegetation index (RVI) has been extensively utilized for qualitative and quantitative remote sensing monitoring of vegetation growth dynamics. However, the combination of crop, growing environment, and temporal dynamics makes crop monitoring data a complex task. Despite the relatively simple underlying mechanisms of this phenomenon, there is still a need for more research to identify specific vegetation structures that correspond to changes in the response of vegetation indices. Building upon this premise, this study utilized a dynamic monitoring model to conduct dynamic monitoring of plant height for three common crops: rice, wheat, and maize. The findings revealed that (1) models developed for specific spatial and temporal scales of particular crop varieties may not accurately predict crop growth in different regions or with different varieties in a timely manner, due to growth variations; (2) these models maintain accuracy over a range of plant heights, such as rice at around 70cm, wheat at around 50cm, and maize at around 150cm; (3) among the three crops, planting density was identified as the main factor influencing the differences in RVI response. This research contributes to our comprehension of the dynamic response of RVI to different growth conditions in crops, and offers valuable insights and references for agricultural monitoring.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140994949","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}
Abstract. Surface reflectance data is the basic data source for the hyperspectral parametric remote sensing products and remote sensing quantitative application, which is widely used in various application fields such as natural resources and ecological environment monitoring. At present, multispectral data takes the leading role among the common land surface reflectance datasets and the reflectance data mainly involves the types of ground objects such as farmland, forest land, water body, soil, etc., while the datasets relatively less targets the types of rock and mineral surface objects, yet especially the reflectance datasets with the combination of time series and multi-scale satellite-earth are even more scarce. In order to better promote the application of hyperspectral surface reflectance and explore the advantages of joint application of satellite-earth multi-scale reflectance data, on the basis of field-measured rock and mineral target spectral, a comprehensive surface reflectance dataset was generated by using domestically produced hyperspectral satellite data as the data source in this study, mainly focusing on the typical ore concentration area in the Hami Remote Sensing test field in Xinjiang. The dataset includes multi-period hyperspectral satellite surface reflectance images, field measured rock and mineral spectral data, and multi-period sub-pixel spectral data collected based on ground spectral measured points, which can provide significant support for the research and development and accuracy verification as well as performance evaluation of algorithms such as surface reflectance inversion, mineral identification and ground object classification.
{"title":"Research on Hyperspectral Surface Reflectance Dataset of Typical Ore Concentration Area in Hami Remote Sensing Test Field","authors":"Shuneng Liang, Yang Li, Hongyan Wei, Lina Dong, Jiaheng Zhang, Chenchao Xiao","doi":"10.5194/isprs-annals-x-1-2024-137-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-1-2024-137-2024","url":null,"abstract":"Abstract. Surface reflectance data is the basic data source for the hyperspectral parametric remote sensing products and remote sensing quantitative application, which is widely used in various application fields such as natural resources and ecological environment monitoring. At present, multispectral data takes the leading role among the common land surface reflectance datasets and the reflectance data mainly involves the types of ground objects such as farmland, forest land, water body, soil, etc., while the datasets relatively less targets the types of rock and mineral surface objects, yet especially the reflectance datasets with the combination of time series and multi-scale satellite-earth are even more scarce. In order to better promote the application of hyperspectral surface reflectance and explore the advantages of joint application of satellite-earth multi-scale reflectance data, on the basis of field-measured rock and mineral target spectral, a comprehensive surface reflectance dataset was generated by using domestically produced hyperspectral satellite data as the data source in this study, mainly focusing on the typical ore concentration area in the Hami Remote Sensing test field in Xinjiang. The dataset includes multi-period hyperspectral satellite surface reflectance images, field measured rock and mineral spectral data, and multi-period sub-pixel spectral data collected based on ground spectral measured points, which can provide significant support for the research and development and accuracy verification as well as performance evaluation of algorithms such as surface reflectance inversion, mineral identification and ground object classification.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140996949","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 : 2024-05-09DOI: 10.5194/isprs-annals-x-1-2024-163-2024
Charanya Manivannan, Jovina Virgin, Shivaani Suseendran, K. Vani
Abstract. Rapid urbanisation and population growth have led to an unprecedented increase in waste generation. In addition to this, increasing tourism has also increased the challenge of maintaining coastal areas. Inefficient and inadequate waste management practices pose significant environmental and health hazards to both humans and wildlife. Through deep learning and computer vision techniques, the garbage can be identified and its location can be extracted directly from the images. Videos are collected using UAVs. Auto generation of waste reports and additional services like chat-bots are also implemented. Furthermore, the system implements OR tools using which the routes of garbage collector vehicles is optimised. By minimising travel distances and maximising cleanup efficiency, the system reduces operational costs and enhances the overall effectiveness of beach cleanup initiatives. Predominant spots of garbage are analysed and the nearest dustbins are mapped along with the route to reach the dustbin. The garbage detection model gave a mAP of 0.845. The silhouette score of clustering was 70.1% for chameleon and 99.02% for k means. All of the above mentioned modules were integrated and presented on the user interface of the application developed.
摘要快速的城市化和人口增长导致废物产生量空前增加。此外，日益增长的旅游业也增加了维护沿海地区的挑战。低效和不适当的垃圾管理方法对人类和野生动物的环境和健康造成了严重危害。通过深度学习和计算机视觉技术，可以直接从图像中识别垃圾并提取其位置。使用无人机收集视频。还实现了自动生成垃圾报告和聊天机器人等附加服务。此外，该系统还使用 OR 工具优化垃圾收集车的行驶路线。通过最大限度地缩短旅行距离，最大限度地提高清理效率，该系统降低了运营成本，提高了海滩清理行动的整体效率。该系统分析了主要的垃圾点，并绘制了最近的垃圾箱以及到达垃圾箱的路线。垃圾检测模型的 mAP 值为 0.845。变色龙的聚类剪影得分率为 70.1%，K means 的聚类剪影得分率为 99.02%。上述所有模块均已集成并显示在所开发应用程序的用户界面上。
{"title":"Garbage Monitoring And Management Using Deep Learning","authors":"Charanya Manivannan, Jovina Virgin, Shivaani Suseendran, K. Vani","doi":"10.5194/isprs-annals-x-1-2024-163-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-1-2024-163-2024","url":null,"abstract":"Abstract. Rapid urbanisation and population growth have led to an unprecedented increase in waste generation. In addition to this, increasing tourism has also increased the challenge of maintaining coastal areas. Inefficient and inadequate waste management practices pose significant environmental and health hazards to both humans and wildlife. Through deep learning and computer vision techniques, the garbage can be identified and its location can be extracted directly from the images. Videos are collected using UAVs. Auto generation of waste reports and additional services like chat-bots are also implemented. Furthermore, the system implements OR tools using which the routes of garbage collector vehicles is optimised. By minimising travel distances and maximising cleanup efficiency, the system reduces operational costs and enhances the overall effectiveness of beach cleanup initiatives. Predominant spots of garbage are analysed and the nearest dustbins are mapped along with the route to reach the dustbin. The garbage detection model gave a mAP of 0.845. The silhouette score of clustering was 70.1% for chameleon and 99.02% for k means. All of the above mentioned modules were integrated and presented on the user interface of the application developed.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140994659","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 : 2024-05-09DOI: 10.5194/isprs-annals-x-1-2024-107-2024
Tao Ke, Zhouyuan Ye, Xiao Zhang, Yifan Liao, Pengjie Tao
Abstract. In this paper, we present a novel matching method tailored for unmanned aerial vehicle (UAV) thermal infrared images of photovoltaic (PV) panels characterized by highly repetitive textures. This method capitalizes on the integration of point and line features within the image to obtain reliable corresponding points. Furthermore, it employs multiple constraints to eliminate mismatched features and get rid of the interference of repetitive textures on feature matching. To verify the effectiveness of the proposed method, we used an UAV equipped with the DJI Zenmuse H20T thermal infrared gimbal to capture 3767 images of a PV power station in Guangzhou, China. Experiments demonstrate that, for UAV thermal infrared images of PV panels, our method outperforms the state-of-the-art techniques in terms of the density of matching points, matching success rate and matching reliability, consequently leading to robust aerial triangulation results.
{"title":"Sparse matching via point and line feature fusion for robust aerial triangulation of photovoltaic power stations’ thermal infrared imagery","authors":"Tao Ke, Zhouyuan Ye, Xiao Zhang, Yifan Liao, Pengjie Tao","doi":"10.5194/isprs-annals-x-1-2024-107-2024","DOIUrl":"https://doi.org/10.5194/isprs-annals-x-1-2024-107-2024","url":null,"abstract":"Abstract. In this paper, we present a novel matching method tailored for unmanned aerial vehicle (UAV) thermal infrared images of photovoltaic (PV) panels characterized by highly repetitive textures. This method capitalizes on the integration of point and line features within the image to obtain reliable corresponding points. Furthermore, it employs multiple constraints to eliminate mismatched features and get rid of the interference of repetitive textures on feature matching. To verify the effectiveness of the proposed method, we used an UAV equipped with the DJI Zenmuse H20T thermal infrared gimbal to capture 3767 images of a PV power station in Guangzhou, China. Experiments demonstrate that, for UAV thermal infrared images of PV panels, our method outperforms the state-of-the-art techniques in terms of the density of matching points, matching success rate and matching reliability, consequently leading to robust aerial triangulation results.\u0000","PeriodicalId":508124,"journal":{"name":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences","volume":" 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140994385","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：