检索结果-南通市图书馆

3D reconstruction and automatic leakage defect quantification of metro tunnel based on SfM-Deep learning method

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Underground Space 2022年第3期7卷 311-323页

作者： Yadong Xue Peizhe Shi Fei Jia Hongwei Huang Key Laboratory of Geotechnical and Underground Engineering of Education Ministry Tongji UniversityShanghai 200092China Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China

Various structural defects deteriorate tunnel operation status and threaten public safety.Current tunnel inspection methods face problems of low efficiency,high equipment expense,and difficult data management.Combining the deep learning model and the 3D reconstruction method based on structure from motion(SfM),this paper proposes a novel SfM-Deep learning method for tunnel inspection.The high-quality 3D tunnel model is constructed by using images taken every 1 m along the longitudinal direction.The instance segmentation of leakage in longitudinal images is realized using the mask region-based convolutional neural network deep learning model.The SfM-Deep learning method projects the texture of the images after defect recognition to the 3D model and realizes the visualization of leakage defects.By projecting the model to the design cylindrical surface and expanding it,the tunnel leakage area is quantified.Through its practical application in a Shanghai metro shield tunnel,the reliability of the proposed method was verified.The novel SfM-Deep learning method can help engineers efficiently carry out intelligent tunnel detection.

关键词： 3D reconstruction Leakage defect quantification Visualization Metro tunnel structure from motion Deep learning

A comparison of three surface roughness characterization techniques:photogrammetry,pin profiler,and smartphone-based LiDAR

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2022年第1期15卷 2422-2439页

作者： Zohreh Alijani Julien Meloche Alexander McLaren John Lindsay Alexandre Roy Aaron Berg Department of Geography Environment and GeomaticsUniversity of GuelphGuelphCanada Département de Géomatique Appliquée Université de SherbrookeSherbrookeCanada Département des Sciences de l’Environment Université du Québec à Trois-RivièresTrois-RivièresCanada

Surface roughness plays an important role in microwave remote sensing.In the agricultural domain,surface roughness is crucial for soil moisture retrieval methods that use electromagnetic surface scattering or microwave radiative transfer models.Therefore,improved characterization of Soil Surface Roughness(SSR)is of considerable importance.In this study,three approaches,including a standard pin profiler,a LiDAR point cloud generated from an iPhone 12 Pro,and a structure from motion(SfM)photogrammetric point cloud,were applied over 24 surface profiles with different roughness variations to measure surface roughness.The objective of this study was to evaluate the capability of smartphone-based LiDAR technology to measure surface roughness parameters and compare the results of this technique with the more common approaches.Results showed that the iPhone LiDAR technology,when point cloud data is captured in a fine-resolution mode,has a significant correlation with SfM photogrammetry(R2=0.70)and a relatively close agreement with pin profiler(R2=0.60).However,this accuracy tends to be greater for random surfaces and rough profiles with row structure orientations.The results of this study confirm that smartphone-based LiDAR can be used as a cost-effective,fast,and time-efficient alternative tool for measuring surface roughness,especially for rough,wide,and inaccessible areas.

关键词： LiDAR surface roughness structure from motion iPhone pin profiler

Individual tree segmentation and biomass estimation based on UAV Digital aerial photograph

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Mountain Science 2023年第3期20卷 724-737页

作者： SUN Zhao WANG Yi-fu DING Zhi-dan LIANG Rui-ting XIE Yun-hong LI Rui LI Hao-wei PAN Lei SUN Yu-jun State Forestry&Grassland Administration Key Laboratory of Forest Resources&Environmental Management Beijing Forestry UniversityBeijing 100083China Northwest Surveying Planning and Designing Institute of National Forestry and Grassland AdministrationXi'an 710048China

Digital aerial photograph(DAP)data is processed based on structure from motion(Sf M)algorithm and regional net adjustment method to generate digital surface discrete point clouds similar to Light Detection and Ranging(LiDAR)and digital orthophoto mosaic(DOM)similar to optical remote sensing image.In this study,we obtained highresolution images of mature forests of Chinese fir by unmanned aerial vehicle(UAV)flying through crossroute flight,and then reconstructed the threedimensional point clouds in the UAV aerial area by SfM technique.The point cloud segmentation(PCS)algorithm was used for the individual tree segmentation,and the F-score of the three sample plots were 0.91,0.94,and 0.94,respectively.Individual tree biomass modeling was conducted using 155 mature Chinese fir forests which were correctly segmented.The relative root mean squared error(rRMSE)values of random forest(RF),bagged tree(BT)and support vector regression(SVR)were 34.48%,35.74%and 40.93%,respectively.Our study demonstrated that DAP point clouds had great potential to extract forest vertical parameters and could be applied successfully in individual tree segmentation and individual tree biomass modeling.

关键词： UAV images structure from motion DAP point clouds Individual tree segmentation Individual tree biomass models

维普期刊数据库

Visual localization for asteroid touchdown operation based on local image features

在线全文

学校读者我要写书评

暂无评论

Astrodynamics 2020年第2期4卷 149-161页

作者： Yoshiyuki Anzai Takehisa Yairi Naoya Takeishi Yuichi Tsuda Naoko Ogawa The University of Tokyo Tokyo113-8654Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027Japan Japan Aerospace Exploration Agency Sagamihara252-5210Japan

In an asteroid sample-return mission,accurate position estimation of the spacecraft relative to the asteroid is essential for landing at the target point.During the missions of Hayabusa and Hayabusa2,the main part of the visual position estimation procedure was performed by human operators on the Earth based on a sequence of asteroid images acquired and sent by the spacecraft.Although this approach is still adopted in critical space missions,there is an increasing demand for automated visual position estimation,so that the time and cost of human intervention may be reduced.In this paper,we propose a method for estimating the relative position of the spacecraft and asteroid during the descent phase for touchdown from an image sequence using state-of-the-art techniques of image processing,feature extraction,and structure from motion.We apply this method to real Ryugu images that were taken by Hayabusa2 from altitudes of 20 km-500 m.It is demonstrated that the method has practical relevance for altitudes within the range of 5-1 km.This result indicates that our method could improve the efficiency of the ground operation in the global mapping and navigation during the touchdown sequence,whereas full automation and autonomous on-board estimation are beyond the scope of this study.Furthermore,we discuss the challenges of developing a completely automatic position estimation framework.

关键词： visual navigation structure from motion asteroid touchdown Hayabusa2

Geo-registered 3D models from crowdsourced image collections

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2013年第1期16卷 55-60页

作者： Jan-Michael FRAHM Jared HEINLY Enliang ZHENG Enrique DUNN Pierre FITE-GEORGEL Marc POLLEFEYS Department of Computer Science University of North Carolina at Chapel HillBrooks Computer Science BuildingCB#3175Chapel HillNC 27599USA Dekko Inc. San FranciscoUSA Department of Computer Science Eidgenössische Technische Hochschule ZürichZürichSwitzerland

In this article we present our system for scalable,robust,and fast city-scale reconstruction from Internet photo collections(IPC)obtaining geo-registered dense 3D models.The major achievements of our system are the efficient use of coarse appearance descriptors combined with strong geometric constraints to reduce the computational complexity of the image overlap search.This unique combination of recognition and geometric constraints allows our method to reduce from quadratic complexity in the number of images to almost linear complexity in the IPC size.Accordingly,our 3D-modeling framework is inherently better scalable than other state of the art methods and in fact is currently the only method to support modeling from millions of images.In addition,we propose a novel mechanism to overcome the inherent scale ambiguity of the reconstructed models by exploiting geo-tags of the Internet photo collection images and readily available StreetView panoramas for fully automatic geo-registration of the 3D model.Moreover,our system also exploits image appearance clustering to tackle the challenge of computing dense 3D models from an image collection that has significant variation in illumination between images along with a wide variety of sensors and their associated different radiometric camera parameters.Our algorithm exploits the redundancy of the data to suppress estimation noise through a novel depth map fusion.The fusion simultaneously exploits surface and free space constraints during the fusion of a large number of depth maps.Cost volume compression during the fusion achieves lower memory requirements for high-resolution models.We demonstrate our system on a variety of scenes from an Internet photo collection of Berlin containing almost three million images from which we compute dense models in less than the span of a day on a single computer.

关键词： 3d modeling structure from motion photo collection modeling

Image-based self-position and orientation method for moving platform

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2013年第4期56卷 5-18页

作者： LI DeRen LIU Yong YUAN XiuXiao State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan University School of Electronic Information Wuhan University School of Remote Sensing and Information Engineering Wuhan University

The position and orientation of moving platform mainly depends on global positioning system and inertial navigation system in the field of low-altitude surveying,mapping and remote sensing and land-based mobile mapping system.However,GPS signal is unavailable in the application of deep space exploration and indoor robot control.In such circumstances,image-based methods are very important for self-position and orientation of moving platform.Therefore,this paper firstly introduces state of the art development of the image-based self-position and orientation method(ISPOM) for moving platform from the following aspects:1) A comparison among major image-based methods(i.e.,visual odometry,structure from motion,simultaneous localization and mapping) for position and orientation;2) types of moving platform;3) integration schemes of image sensor with other sensors;4) calculation methodology and quantity of image sensors.Then,the paper proposes a new scheme of ISPOM for mobile robot-depending merely on image sensors.It takes the advantages of both monocular vision and stereo vision,and estimates the relative position and orientation of moving platform with high precision and high frequency.In a word,ISPOM will gradually speed from research to application,as well as play a vital role in deep space exploration and indoor robot control.

关键词： self-position and orientation ISPOM visual odometry structure from motion simultaneous localization and mapping

Novel SfM-DLT method for metro tunnel 3D reconstruction and Visualization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Underground Space 2021年第2期6卷 134-141页

作者： Yadong Xue Sen Zhang Mingliang Zhou Hehua Zhu Key Laboratory of Geotechnical and Underground Engineering of Education Ministry Tongji UniversityShanghai 200092China Department of Geotechnical Engineering Tongji UniversityShanghai 200092China

Metro tunnels play a crucial role in urban transportation.However,with growing tunnel operation periods,defects,and large deformations appearing,these are influencing tunnel structural performance and threatening public safety.Three-dimensional(3D)tunnel reconstruction is an effective way to highlight tunnel conditions and provide a basis for engineering management and maintenance.However,the current methods of tunnel 3D reconstruction do not sufficiently combine the qualitative and quantitative characteristics of tunnel states.In this study,a novel method for metro tunnel 3D reconstruction based on structure from motion(SfM)and direct linear transformation(DLT)is proposed.The dimensionless 3D reconstruction point cloud acquired through the SfM method showcases the qualitative characteristics(such as leakage and pipelines)of the tunnel state.The close-range photogrammetry DLT method provides scale information missing from the SfM method and quantitative characteristics(such as profile deformation)of the tunnel state.The SfM-DLT method was tested in a Shanghai metro tunnel,and proved to be feasible and promising for future tunnel inspections.

关键词： Metro tunnel 3D reconstruction Visualization structure from motion Direct linear transformation

On the way to airborne gravelometry based on 3D spatial data derived from images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Sediment Research 2018年第1期33卷 84-92页

作者： M.Detert L.Kadinski V.Weitbrecht Laboratory of Hydraulics Hydrology and Glaciology VAWETH Zurich

This paper presents basic tests to develop an airborne photogrammetric methodology that derives grain size characteristics of gravel bed rivers. The data acquisition was done using a light weight action cam and a hand-held digital single lens reflex camera. Image processing comprised the structure from motion technique and multiview-stereo algorithms to obtain digital elevation models of non-cohesive gravel beds. Laboratory results indicate that the method accuracy is about four to six times lower than laserscan data when based on action cam data. The accuracy of digital elevation models computed via photos taken by the reflex camera is almost of the same range as the laser data. Field experiments were done to test the performance of image based gravelometry against manual surface sampling. For this application the action cam was mounted to a low-cost quadrocopter, while the reflex camera was operated by hand.Results indicate that this combination has a high potential to generate data from which characteristic grain size parameters can be estimated.

关键词： Airborne photogrammetry Grain size distribution Gravel bed Field work Gravelometry Image analysis Laboratory experiments structure from motion Surface sampling

Hybrid Parallel Bundle Adjustment for 3D Scene Reconstruction with Massive Points

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2012年第6期27卷 1269-1280页

作者：刘鑫高伟胡占义 National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences

Bundle adjustment （BA） is a crucial but time consuming step in 3D reconstruction. In this paper, we intend to tackle a special class of BA problems where the reconstructed 3D points are much more numerous than the camera parameters, called Massive-Points BA （MPBA） problems. This is often the case when high-resolution images are used. We present a design and implementation of a new bundle adjustment algorithm for efficiently solving the MPBA problems. The use of hardware parallelism, the multi-core CPUs as well as GPUs, is explored. By careful memory-usage design, the graphic-memory limitation is effectively alleviated. Several modern acceleration strategies for bundle adjustment, such as the mixed-precision arithmetics, the embedded point iteration, and the preconditioned conjugate gradients, are explored and compared. By using several high-resolution image datasets, we generate a variety of MFBA problems, with which the performance of five bundle adjustment algorithms are evaluated. The experimental results show that our algorithm is up to 40 times faster than classical Sparse Bundle Adjustment, while maintaining comparable precision.

关键词： sparse bundle adjustment GPU compute unified device architecture structure from motion

维普期刊数据库