An Improved Image Positioning Method Based on Local Changed Plane Eliminated by Homography

Over the past two decades, advances in computer vision technology have allowed image-based positioning method to work in large scale with higher reliability and precision. However, this positioning technology has not been widely applicated at present compare to GPS. One of the reasons is that large print advertisements on the surface of buildings which are common in cities are frequently updated. Positioning based on image may fail due to this scene changed relative to pre-build 3D model, which is still a challenge in the field of image-based location. To deal with positioning failure caused by changed plane, in this paper, we analyzed the effect of the changed plane size in query image on the positioning accuracy by systematic experiment with images collected regularly, and one improved 2D-to-3D positioning method based on local changed plane eliminated through homography transformation is proposed. Experiments show the method can raise the image-based localization success rate by 15%.

[1]  Yi-Ping Hung,et al.  Vision-Based Positioning for Internet-of-Vehicles , 2017, IEEE Transactions on Intelligent Transportation Systems.

[2]  Michael Bosse,et al.  Summary Maps for Lifelong Visual Localization , 2016, J. Field Robotics.

[3]  Ronen Basri,et al.  A Survey on Structure from Motion , 2017, ArXiv.

[4]  Torsten Sattler,et al.  Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Song Chen,et al.  Crowd-sourced pictures geo-localization method based on street view images and 3D reconstruction , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[6]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[7]  Valérie Gouet-Brunet,et al.  A survey on Visual-Based Localization: On the benefit of heterogeneous data , 2018, Pattern Recognit..

[8]  Robert Piché,et al.  A Survey of Selected Indoor Positioning Methods for Smartphones , 2017, IEEE Communications Surveys & Tutorials.

[9]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

[10]  Hongdong Li,et al.  Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Dieter Schmalstieg,et al.  Global Localization from Monocular SLAM on a Mobile Phone , 2014, IEEE Transactions on Visualization and Computer Graphics.

[12]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[13]  Yihong Wu,et al.  Image-based camera localization: an overview , 2016, Visual Computing for Industry, Biomedicine, and Art.

[14]  BosseMichael,et al.  Summary Maps for Lifelong Visual Localization , 2016 .

[15]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[16]  Torsten Sattler,et al.  Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Torsten Sattler,et al.  Fast image-based localization using direct 2D-to-3D matching , 2011, 2011 International Conference on Computer Vision.

[18]  Lei Deng,et al.  Image set querying based localization , 2015, 2015 Visual Communications and Image Processing (VCIP).

[19]  Zuzana Kukelova,et al.  A general solution to the P4P problem for camera with unknown focal length , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Peter I. Corke,et al.  Visual Place Recognition: A Survey , 2016, IEEE Transactions on Robotics.

[21]  Pascal Fua,et al.  Worldwide Pose Estimation Using 3D Point Clouds , 2012, ECCV.

[22]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[23]  Mohamed S. Shehata,et al.  Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images , 2017, ArXiv.

[24]  Pascal Monasse,et al.  Adaptive Structure from Motion with a Contrario Model Estimation , 2012, ACCV.

[25]  Michael Milford,et al.  Vision-based place recognition: how low can you go? , 2013, Int. J. Robotics Res..