顾及影像拓扑的SfM算法改进及其在灾场三维重建中的应用
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
快速、准确的大场景影像三维重建技术可为灾害应急响应和灾情评估提供重要的决策依据。本文针对运动恢复结构(SfM)算法效率低的问题,提出了一种顾及影像拓扑关联关系的拓扑-运动恢复结构(TSfM)算法。TSfM算法利用低空无人机(UAV)自身的飞控记录构建影像拓扑关联关系,缩小了特征匹配时的影像搜索范围,与传统SfM算法相比,影像匹配的时间复杂度由O(n2)降低为O(n)。实验结果表明,TSfM算法实现了基于无人机影像序列的灾场快速三维重建,重建模型的相对精度与SfM算法的重建精度一致。将该方法用于四川芦山地震UAV影像三维重建,可检测出地震滑坡体及其形态信息。
The rapid and accurate large scene 3Dreconstruction technique from multi-view images can provide important and reliable information for emergency response and disaster assessment.Against the low efficiency of Structure from Motion(SfM)algorithm,this paper develops an image Topology based Structure from Motion(TSfM)algorithm referring to image topological conjunction.Generating the image topological conjunction with the flight-control data acquired by unmanned aerial vehicle system(UAV),the searching range for matched images is reduced in the process of feature matching,and the time complexity of TSfM algorithm in the feature matching stage decreases from O(n2)to O(n)as compared with SfM algorithm.The experimental results show that TSfM algorithm makes it possible for rapid large scene 3Dreconstruction with sequence images from UAV.Furthermore,it is reached that the relative error of the 3Dscene model reconstructed by TSfM algorithm is comparable with that by SfM algorithm.The proposed TSfM algorithm is applied for Lushan earthquake disaster3 Dreconstruction with UAV images,which can help to detect the seismic-induced landslides with more information.
引文
[1]Yan Lei,Lu Shuqiang,Zhao Hongying,et al.Research on Key Techniques of Aerial Remote Sensing System for Unmanned Aerial Vehicles[J].Engineering Journal of Wuhan University,2004,37(6):67-71(晏磊,吕书强,赵红颖,等.无人机航空遥感系统关键技术研究[J].武汉大学学报(工学版),2004,37(6):67-71)
    [2]Zang Ke,Sun Yonghua,Li Jing,et al.Application of Miniature Unmanned Aerial Vehicle Remote Sensing System to Wenchuan Earthquake[J].Journal of Natural Disasters,2010,19(3):162-166(臧克,孙永华,李京,等.微型无人机遥感系统在汶川地震中的应用[J].自然灾害学报,2010,19(3):162-166)
    [3]Niethammer U,James M R,Rothmund S,et al.UAV-Based Remote Sensing of the Super-Sauze Landslide:Evaluation and Results[J].Engineering Geology,2012,128(1):2-11
    [4]Douterloigne K,Gautama S,Philips W,et al.On the Accuracy of 3DLandscapes from UAV Image Data[C].IGARSS,Honolulu,Hawaii,USA,2010
    [5]Gademer A,Petipas B,Mobaied S,et al.Developing a Lowcost Vertical Take off and Landing Unmanned Aerial System for Centimetric Monitoring of Biodiversity the Fontainebleau Forest Case[C].IGARSS,Honolulu,Hawaii,USA,2010
    [6]Xiang H T,Lei T,Method for AutomaticGeoreferencing Aerial Remote Sensing Images from an Unmanned Aerial Vehicle(UAV)Platform[J].Biosystem Engineering,2011,108(2):104-113
    [7]Tong Shuai,Xu Xiaogang,Yi Chengtao,et al.Overview on Vision-Based 3D Reconstruction[J].Application Research of Computer,2011,28(7):2 411-2 417(佟帅,徐晓刚,易成涛,等.基于视觉的三维技术综述[J].计算机应用研究.2011,28(7):2 411-2 417
    [8]Horn B.Shape from Shading:A Method for Obtaining the Shape of A Smooth Opaque Object from One View[D].Cambridge:Cambridge University,1970
    [9]Woodham R J.Photometric Method for Determining Surface Orientation from Multiple images[J].Optical Engineering,1980,19(1):139-144
    [10]Wiktin A.Recovering Surface Shape and Orientation from Texture[J].Artificial Intelligence,1981,17(1-3):17-45
    [11]Martin W N,Aggarwal J K.Volumetric Descriptions of Objects from Multiple Views[J].IEEE Trans on PAMI,1983,5(2):150-158
    [12]Snavely N.Scene Reconstruction and Visualization from Internet Photo Collections[D].Washington:University of Washington,2008
    [13]Niethammer U,Rothmund S.UAV-Based Remote Sensing of Landslides[C].International Archives of Photogrammetry,Remote Sensing and Spatial Information Sciences Symposium,Newcastle Upon Tyne,UK,2010
    [14]Rosnell T,Honkavaara E.Point Cloud Generation from Aerial Image Data Acquired by a Quadrocopter Type Micro Unmanned Aerial Vehicle and a Digital Still Camera[J].Sensors,2012,12:453-480
    [15]Shen Yonglin,Liu Jun,Wu Lixin,et al.Reconstruction of Disaster Scene from UAV Images and Flight-Control Data[J].Geography and Geo-Information Science,2011,27(6):13-17(沈永林,刘军,吴立新,等.基于无人机影像和飞控数据的灾场重建方法研究[J].地理与地理信息科学,2011,27(6):13-17)
    [16]Turner D,Lucieer A.Using a Micro Unmanned Aerial Vehicle(UAV)for Ultra High Resolution Mapping and Monitoring of Landslide Dynamics[C].IGARSS,Melbourne,Austrilia,2013
    [17]Agarwal S,Snavely N,Simon I,et al.Building Rome in a Day[C].ICCV,Kyoto,Japan,2009
    [18]Wu C.Towards Linear-Time Incremental Structure from Motion[C].3DV,Seattle,WA,USA,2013
    [19]Lowe D.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110
    [20]Liu Jun,Zhang Yongsheng,Wang Donghong,et al.Computing Method of Exterior Orientation Elements of POS AV 510-DC System[J].Geomatics Technology and Equipment,2004,6(4):43-47(刘军,张永生,王冬红,等.POS AV510-DG系统外方位元素的计算方法[J].测绘技术装备,2004,6(4):43-47)
    [21]Fischler M A,Bolles R C.Random Sample Consensus:A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography[J].Communications of the ACM,1981,24(6):381-395
    [22]Hartley R I.In Defense of the Eight-Point Algorithm[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(6):580-593
    [23]Hartley R,Zisserman A.Multiple View Geometry in Computer Vision[M].Cambridge,UK:Cambridge University Press,2000
    [24]Lourakis M,Argyros A.The Design and Implementation of a Generic Sparse Bundle Adjustment Software Package Based on the Levenberg-Marquardt Algorithm[R].Technical Report 340,Inst.of Computer Science-FORTH,Heraklion,Greece,2004
    [25]Xu Zhihua,Liu Chunbo,Wang Ping,et al.Airborne Union Observation and Disaster Enhanced Identification of Ms 7.0Lushan Earthquake[J].Science and Technology Review,2013,31(12):37-41(许志华,刘纯波,王平,等.四川芦山Ms7.0级地震空基联合观测与灾情增强识别[J].科技导报,2013,31(12):37-41)

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心