Smart phone camera image localization method for narrow corridors based on epipolar geometry

As some public buildings have become large in spatial scale, people find it more and more difficult to know their actual location in these buildings. Generally in the indoor environment, to get location information is relatively more complex than that in the outdoor environment, for traditional outdoor localization methods do not perform well in indoor environment. Under this circumstances, image based indoor localization is a meaningful research topic under many application scenarios. In this paper, we presented a method for performing image based localization using smart phones in narrow corridors. In the first step, image fingerprint database is established, and then features of every image in the database are extracted. Users' query image is compared with the database to retrieve matched images and corresponding feature points. After that, epipolar geometry is utilized so as to calculate the actual location of query image. Besides, we make localization experiments in corridors and compare the result to that of localization method based on wireless local area network in the same environment. In our work, we achieve a slightly better localization accuracy over a set of 51 query images taken in an environment of narrow corridors than the accuracy attained by using wireless local area network based method with the same environmental conditions.

[1]  Zhen Zhang,et al.  Pose Estimation Based on Four Coplanar Point Correspondences , 2009, 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.

[2]  D. Gennery,et al.  Calibration and Orientation of Cameras in Computer Vision , 2001 .

[3]  Domenico Prattichizzo,et al.  EGT for multiple view geometry and visual servoing: robotics vision with pinhole and panoramic cameras , 2005, IEEE Robotics & Automation Magazine.

[4]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[5]  Marc Pollefeys,et al.  Live Metric 3D Reconstruction on Mobile Phones , 2013, 2013 IEEE International Conference on Computer Vision.

[6]  Shahrokh Valaee,et al.  A weighted KNN epipolar geometry-based approach for vision-based indoor localization using smartphone cameras , 2014, 2014 IEEE 8th Sensor Array and Multichannel Signal Processing Workshop (SAM).

[7]  Avideh Zakhor,et al.  Reduced-complexity data acquisition system for image-based localization in indoor environments , 2013, International Conference on Indoor Positioning and Indoor Navigation.

[8]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[9]  Paramvir Bahl,et al.  RADAR: an in-building RF-based user location and tracking system , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[10]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[11]  Uwe Stilla,et al.  A sensor-centric EKF for inertial-aided visual odometry , 2013, International Conference on Indoor Positioning and Indoor Navigation.

[12]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[13]  U. Grossmann,et al.  RSSI based WLAN Indoor Positioning with Personal Digital Assistants , 2007, 2007 4th IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications.

[14]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Avideh Zakhor,et al.  Image Based Localization in Indoor Environments , 2013, 2013 Fourth International Conference on Computing for Geospatial Research and Application.