基于即时稠密三维重构的无人机视觉定位

doi:10.3969/j.issn.0372-2112.2017.06.003

电子学报 ›› 2017, Vol. 45 ›› Issue (6): 1294-1300.DOI: 10.3969/j.issn.0372-2112.2017.06.003

基于即时稠密三维重构的无人机视觉定位

陈宝华, 邓磊, 陈志祥, 段岳圻, 周杰

清华大学自动化系, 北京 100084

收稿日期:2015-09-16 修回日期:2016-05-04 出版日期:2017-06-25
- 作者简介:
- 陈宝华 男,1978年2月生于内蒙兴安.清华大学自动化系博士研究生,研究方向为无人机视觉导航与场景分析.E-mail:cbh1111@sina.com;邓磊男,1988年9月生于山西侯马.清华大学自动化系博士研究生.研究方向为计算机视觉中的三维重建和视觉定位.E-mail:dally211@163.com
- 基金资助:
- 国家自然科学基金 (No.61225008，No.61373074，No.61020106004）

Instant Dense 3D Reconstruction-Based UAV Vision Localization

CHEN Bao-hua, DENG Lei, CHEN Zhi-xiang, DUAN Yue-qi, ZHOU Jie

Department of Automation, Tsinghua University. Beijing 100084, China

Received:2015-09-16 Revised:2016-05-04 Online:2017-06-25 Published:2017-06-25
- Supported by:
- National Natural Science Foundation of China (No.61225008, No.61373074, No.61020106004)

摘要/Abstract

摘要：

传统景象匹配定位方法在用于低空无人机定位时，易因低空航拍图像视场小，且与卫星图像（带有地理信息）的拍摄角度差异大而失败.本文提出了一种基于即时稠密三维重构的无人机视觉定位方法，通过将稠密三维点云与卫星图像匹配以实现无人机定位.首先根据图像序列快速估计摄像机位姿，而后使用多深度图协同去噪与优化算法生成稠密三维点云，随后通过变换观察视角由稠密三维点云生成与卫星图像拍摄视角相近的虚拟视图，最后将虚拟视图与卫星图像匹配并得到无人机的地理坐标.由于稠密三维点云包含多张图像的信息，覆盖面积大，且可变化观察视角，因此能够有效克服上述两个问题.实验证明了本文方法的有效性.

关键词: 无人机视觉定位, 三维重建, 即时构图及定位

Abstract:

The corresponding matched images are hard to obtain by the convetional scene matching localization method applied in UAV (Unmanned Aerial Vehicle) at a low altitude because of the small viewing coverage and the big capturing angle difference comparing with the satellite images.We propose a localization method based on instant dense 3D reconstruction.Firstly,we use a fast SLAM (Simultaneous Localization And Mapping) method to retrieve camera poses of image sequence captured by UAV.Secondly,cooperative denoising and optimization algorithm across multiple key frames is applied to obtain dense depth map and dense point cloud.Thirdly,a virtual view,the angle of which is similar to that of satellite,is generated by iterative optimizing method.Finally,we estimate the position of UAV by correspondence between the satellite map and the previous generated virtual view.Since the dense 3D point cloud integrates the information of multiple aerial images with small field of view and the viewing angles of some generated virtual views are close to those of satellite images,the proposed method provides a higher success rate and accuracy for localization.Experimental results illustrate the effectiveness and applicability of the proposed framework.

Key words: UAV vision localization, 3D reconstruction, SLAM

中图分类号:

TP391

陈宝华, 邓磊, 陈志祥, 等. 基于即时稠密三维重构的无人机视觉定位[J]. 电子学报, 2017, 45(6): 1294-1300.

CHEN Bao-hua, DENG Lei, CHEN Zhi-xiang, et al. Instant Dense 3D Reconstruction-Based UAV Vision Localization[J]. Acta Electronica Sinica, 2017, 45(6): 1294-1300.

参考文献

[1] Majdik L,Verda D,Albers-schoenberg Y,et al.Air-ground matching:appearance-based GPS-denied urban localization of micro aerial vehicles[J].Journal of Field Robotics,2015,32(7):1015-1039.
[2] Gálvez-López D,Tardós J.Bags of binary words for fast place recognition in image sequences[J].IEEE Transactions on Robotics,2012,28(5):1188-1197.
[3] Cummins M,Newman P.Appearance-only SLAM at large scale with FAB-MAP2.0[J].International Journal of Robotic Research,2011,30(9):1100-1123.
[4] Morel J,Yu G.ASIFT:A new framework for fully affine invariant image comparison[J].SIAM Journal.Imaging Sciences,2009,2(2):438-469.
[5] Bansal M,Daniilidis K,Sawhney H.Ultra-wide baseline facade matching for geo-localization[A].Proceedings of the European Conference on Computer Vision Workshops and Demonstrations[C].Florence,Italy:IEEE,2012.175-186.
[6] Bansal M,Sawhney H,Cheng H,et al.Geo-localization of street views with aerial image databases[A].Proceedings of the 19th International Conference on Multimedia[C].Scottsdale,AZ,USA:IEEE,2011.1125-1128.
[7] 邸男,李桂菊,魏雅娟.采用SIFT的末制导图像匹配技术[J].红外与激光工程,2011,40(8):1589-1593. Di N,Li G,Wei Y.Image matching technology based on SIFT for terminal-guiding system[J].Infrared and Laser Engineering,2011,40(8):1589-1593.(in Chinese)
[8] 陈冰,赵亦工,李欣.基于快速鲁棒性特征的景象匹配[J].系统工程与电子技术,2009,31(11):2714-2718. Bing C,Zhao Y G,Xin L I.Scene matching based on speeded up robust features[J].Systems Engineering and Electronics,2009,31(11):2714-2718.(in Chinese)
[9] Klein G,Murray W.Parallel tracking and mapping for small AR workspaces[A].Proceedings of the Sixth IEEE/ACM International Symposium on Mixed and Augmented Reality[C].Nara,Japan:IEEE,2007.225-234.
[10] Newcombe R,Lovegrove S,Davison J.DTAM:dense tracking and mapping in real-time[A].Proceedings of the IEEE International Conference on Computer Vision[C].Barcelona,Spain:IEEE,2011.2320-2327.
[11] Engel J,Sch ps T,Cremers D.LSD-SLAM:large-scale direct monocular SLAM[A].Proceedings of the 13th European Conference on Computer Vision[C].Zurich,Switzerland:IEEE,2014.834-849.
[12] Forster C,Pizzoli M,Scaramuzza D.SVO:fast semi-direct monocular visual odometry[A].Proceedings of the 2014 IEEE International Conference on Robotics and Automation[C].Hong Kong,China:IEEE,2014.15-22.
[13] Davison A,Reid I,Molton N,et al.MonoSLAM:real-time single camera SLAM[J].IEEE Transactions,2007,PAMI-29(6):1052-1067.
[14] Murray R,Li Z,Sastry S.A Mathematical Introduction to Robotics Manipulation[M].Florida:CRC Press,1994.36-40.
[15] Absil P,Mahony R,Sepulchre R.Optimization Algorithms on Matrix Manifolds[M].Princeton:Princeton University Press,2009.5-12.
[16] Furakawa Y,Ponce J.Accurate,dense,and robust multiview stereopsis[J].IEEE Transactions,2010,PAMI-32(8):1362-1376.
[17] Wu C.Towards linear-time incremental structure from motion[A].Proceedings of the 2013 International Conference on 3D Vision[C].Seattle USA:IEEE,2013.127-134.

基于即时稠密三维重构的无人机视觉定位

Instant Dense 3D Reconstruction-Based UAV Vision Localization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

[1]	刘玉轩, 张力, 艾海滨, 许彪, 孙钰珊, 樊仲藜. 光场相机三维重建研究进展与展望[J]. 电子学报, 2022, 50(7): 1774-1792.
[2]	李燕, 严永财. 基于同心圆阵列的结构光主动视觉系统标定算法[J]. 电子学报, 2021, 49(3): 536-541.
[3]	张成, 汪东, 沈川, 王美琴, 陈倩文, 韦穗. 部分遮挡三维彩色物体的压缩全息[J]. 电子学报, 2019, 47(1): 33-39.
[4]	邓磊, 陈宝华, 黄思远, 段岳圻, 周杰. 一种基于射线模型的图像定位系统[J]. 电子学报, 2017, 45(1): 1-7.
[5]	张聪炫, 陈震, 黎明. 单目图像序列光流三维重建技术研究综述[J]. 电子学报, 2016, 44(12): 3044-3052.
[6]	张慧滔;于平;胡修炎;张朋. 利用GPU实现单层螺旋CT的三维图像重建[J]. 电子学报, 2011, 39(1): 76-81.
[7]	署光;姚莉秀;杨晓超;左昕;杨杰. 基于稀疏形变模型的三维卡通人脸生成[J]. 电子学报, 2010, 38(8): 1798-1802.
[8]	侯文广, 陈大为, 丁明跃. 一种基于多重影像实现真实感人脸三维重建的方法[J]. 电子学报, 2008, 36(4): 661-666.
[9]	邱兆文;张田文. 文物三维重建关键技术[J]. 电子学报, 2008, 36(12): 2423-2427.
[10]	洪伟, 牟轩沁, 蔡元龙. 基于多分辨投影匹配和对应点分析的三维血管轴重建[J]. 电子学报, 2005, 33(10): 1901-1904.
[11]	俞恒永;牟轩沁;汤少杰;蔡元龙. 基于先验信息的二值血管锥束迭代重建[J]. 电子学报, 2004, 32(4): 575-579.