基于分块聚类特征匹配的无人机航拍三维场景重建 -- 西北工业大学学报,2016,34(4):731-737
论文:2016,Vol:34,Issue(4):731-737
引用本文:
宋征玺, 张明环. 基于分块聚类特征匹配的无人机航拍三维场景重建[J]. 西北工业大学学报
Song Zhengxi, Zhang Minghuan. 3D Reconstruction on Unmanned Aerial Video by Using Patch Clustering Matching Method[J]. Northwestern polytechnical university

基于分块聚类特征匹配的无人机航拍三维场景重建
宋征玺1, 张明环2
1. 西北工业大学 图书馆, 陕西 西安 710072;
2. 西北工业大学 航天学院, 陕西 西安 710072
摘要:
针对无人机航拍采集的海量无标定图像,在SFM(structure from motion)重建框架下,提出了基于分块聚类特征匹配的三维重建方法。文章将航拍图像的匹配问题转化为待匹配图像集合的筛选以及图像局部特征配准。通过增加筛选步骤,提出了在缩略图尺度下利用词汇树的评分机制构建待匹配图像集合的方法;利用特征成簇状分布的数据特性,提出了先聚类再匹配的局部特征配准方法。优化了SFM重建框架的特征匹配部分,在航拍数据库PAMView中进行了三维重建实验。实验结果表明,该方法在不影响重建性能下有效提高运算速率。
关键词:    图像匹配    像素点    无人机航拍视频    三维重建    聚类   
3D Reconstruction on Unmanned Aerial Video by Using Patch Clustering Matching Method
Song Zhengxi1, Zhang Minghuan2
1. Library, Northwestern Polytechnical University, Xi'an 710072, China;
2. School of Astronautics, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
Under Structure from Motion (SFM) framework, this paper proposes a 3D Reconstruction method on unmanned aerial video by using Patch Clustering Matching. This method separates massive uncalibrated images matching into candidate image set screening and local feature matching. Through screening procedure, candidate set is build by scoring process of vocabulary tree on thumbnail images; Take the feature spatial distribution, this paper presents a local feature matching method after clustering. By optimizing image matching module of SFM frame, 3D reconstruction experiment is carried out on the aerial database in PAMView. The experiment results show that this method improves operating rate without impact the reconstruction performance.
Key words:    image matching    pixels    unmanned aerial video    3D reconstruction    clustering   
收稿日期: 2016-03-18     修回日期:
DOI:
基金项目: 航天支撑技术基金(N2015KC0121)资助
通讯作者:     Email:
作者简介: 宋征玺(1990-),女,西北工业大学硕士研究生,主要从事计算机视觉及应用的研究。
相关功能
PDF(7892KB) Free
打印本文
把本文推荐给朋友
作者相关文章
宋征玺  在本刊中的所有文章
张明环  在本刊中的所有文章

参考文献:
[1] Snavely N, Seitz S M, Szeliski R. Photo Tourism: Exploring Photo Collections in 3D[J]. ACM Trans on Graphics, 2006, 25(3): 835-846
[2] Nister D, Stewenius H. Scalable Recognition with a Vocabulary Tree[C]//IEEE Conference on Computer Vision and Pattem Recognition, 2006: 2161-2168
[3] He K M, Sun J. Computing Nearest-Neighbor Fields Via Propagation-Assisted KD-Trees[C]//IEEE Conference on Computer Vision and Pattem Recognition, 2012: 111-118
[4] Muja M, Lowe D G. Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration[C]//International Conference on Computer Vision Theory and Applications, 2009: 331-340
[5] Wei L Y, Levoy M. Fast Texture Synthesis Using Tree Structured Vector Quantization[C]//Conference on Computer Graphics & Interactive Techniques, 2000: 479-488
[6] Kumar N, Zhang L, Nayar S. What is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images[C]//European Conference on Computer Vision, 2008: 364-378
[7] Silpa-Anan C, Hartley R. Optimised KD-Trees for Fast Image Descriptor Matching[C]//IEEE Conference on Computer Vision and Pattem Recognition, 2008: 1-8
[8] Barnes C, Shechtman E, Finkelstein A, et al. Patchmatch: A Randomized Correspondence Algorithm for Structural Image Editing[J]. Acm Transactions on Graphics, 2009, 28(3): 341-352
[9] Restrepo M I, Mayer B A, Ulusoy A O, et al. Characterization of 3-D Volumetric Probabilistic Scenes for Object Recognition[J]. IEEE Journal of Selected Topics in Signal Processing, 2012, 6: 522-537
[10] Furukawa Y , Curless B, Seitz S M, et al. Towards Internet-Scale Multi-View Stereo[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2010: 1434-1441