|
|
- 2018
城市环境下基于C/S架构的影像空间定位
|
Abstract:
针对城市环境下影像空间定位精度低等问题，提出了一种在C/S架构下基于影像的移动平台空间自定位方法。首先对预采集的城市建筑物序列影像，利用最近邻距离比率（nearest neighbor distance ratio，NNDR）算法和归一化互相关匹配（normalized cross correlation，NCC）算法得到SIFT粗匹配，通过随机抽样一致（random sample consensus，RANSAC）算法对粗匹配点进行优化，通过精确解算基本矩阵F和投影矩阵P，建立建筑物三维点云模型，进而获得由影像特征点、像点坐标以及物方点坐标组成的物方特征库。其次以用户通过手机拍摄的影像作为定位影像，进行特征提取并与物方特征库影像匹配，获取对应物方点坐标。最后通过精确计算定位影像外方位元素，并在手机客户端中显示所拍照瞬间手机的空间位置，实现移动平台空间自定位。实验结果表明，该方法能够达到厘米级定位精度，可作为其他空间定位方法的有效补充
| [1] | Ruan Ling,Zhang Ling,Xu Yue, et al. Indoor Positioning:Classification, Methods and Applications[J].<em>Geomatics World</em>,2015,22(2):8-14(阮陵,张翎,许越,等.室内定位:分类、方法与应用综述[J]. 地理信息世界,2015,22(2):8-14) |
| [2] | Hartley R, Zisserman A. Multiple View Geometry in Computer Vision[M]. Cambridge:Cambridge University Press,2000 |
| [3] | Feng Chun. Research on Identification and Location of Object Based on Monocular Vision[D]. Nanjing:University of Aeronautics and Astronautics,2013(冯春. 基于单目视觉的目标识别与定位研究[D]. 南京:南京航空航天大学,2013) |
| [4] | Wang Baofeng, Zhou Jianliang, Tang Geshi, et al. Research on Visual Localization Method of Lunar Rover[J]. <em>Science China:Information Sciences</em>, 2014,44(4):452-460(王保丰,周建亮,唐歌实,等. 嫦娥三号巡视器视觉定位方法[J]. 中国科学:信息科学,2014,44(4):452-460) |
| [5] | Lu Y H, Delp E J. An Overview of Problems in Image-Based Location Awareness and Navigation[C]. SPIE Conference on Electronic Imaging,San Jose, California, USA, 2004 |
| [6] | Zhang W, Kosecka J. Image Based Localization in Urban Environments[C]. International Symposium on 3D Data Processing, Visualization and Transmission, Chapel Hill, USA, 2006 |
| [7] | Li Haifeng. Research on Visual Localization for Mobile Robot in Urban Environment[D]. Tianjin:Nankai University, 2012(李海丰. 城市环境中移动机器人视觉定位研究[D]. 天津:南开大学,2012) |
| [8] | Dou Yanyan. Research of 3D Reconstruction Based on Image Sequence[D]. Nanjing:Nanjing University of Information Science and Technology,2013(窦艳艳.基于图像序列三维重建相关技术研究[D].南京:南京信息工程大学,2013) |
| [9] | Xiao Xiongwu,Guo Bingxuan,Li Deren,et al. A Quick and Affine Invariance Matching Method for Oblique Images[J]. <em>Acta Geodaetica et Cartographica Sinica</em>,2015,44(4):414-421(肖雄武,郭丙轩,李德仁,等. 一种具有仿射不变性的倾斜影像快速匹配方法[J]. 测绘学报,2015,44(4):414-421) |
| [10] | David G L. Distinctive Image Features from Scale-Invariant Keypoints[J]. <em>International Journal of Computer Vision</em>,2004,60(2):91-110 |
| [11] | Klippenstein J, Zhang H. Quantitative Evaluation of Feature Extractors for Visual SLAM[C]. The 4th Canadian Conference on Computer and Robot Vision,Montreal, Quebec, Canada, 2007 |
