Biologically Motivated Novel Localization Paradigm by High-Level Multiple Object Recognition in Panoramic Images

This paper presents the novel paradigm of a global localization method motivated by human visual systems (HVSs). HVSs actively use the information of the object recognition results for self-position localization and for viewing direction. The proposed localization paradigm consisted of three parts: panoramic image acquisition, multiple object recognition, and grid-based localization. Multiple object recognition information from panoramic images is utilized in the localization part. High-level object information was useful not only for global localization, but also for robot-object interactions. The metric global localization (position, viewing direction) was conducted based on the bearing information of recognized objects from just one panoramic image. The feasibility of the novel localization paradigm was validated experimentally.

[1]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[2]  Jochen Triesch,et al.  Shared Features for Scalable Appearance-Based Object Recognition , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[3]  In-So Kweon,et al.  Object recognition using a generalized robust invariant feature and Gestalt's law of proximity and similarity , 2008, Pattern Recognit..

[4]  Jing Liu,et al.  Robust Structured Subspace Learning for Data Representation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  José Jesús Guerrero,et al.  Topological and Metric Robot Localization through Computer Vision Techniques , 2008 .

[6]  Amy J. Briggs,et al.  Real-time recognition of self-similar landmarks , 2001, Image Vis. Comput..

[7]  Sungho Kim,et al.  Single-camera panoramic stereo system with single-viewpoint optics. , 2006, Optics letters.

[8]  Davide Scaramuzza,et al.  Robot localization using soft object detection , 2012, 2012 IEEE International Conference on Robotics and Automation.

[9]  Jing Liu,et al.  Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection , 2014, IEEE Transactions on Knowledge and Data Engineering.

[10]  Adriana Tapus,et al.  Mobile robot localization using panoramic vision and combinations of feature region detectors , 2008, 2008 IEEE International Conference on Robotics and Automation.

[11]  Ilan Shimshoni,et al.  On mobile robot localization from landmark bearings , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

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

[13]  Jana Kosecka,et al.  Vision based topological Markov localization , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[14]  Mignon Park,et al.  Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts , 2009, Inf. Sci..

[15]  Jean-Arcady Meyer,et al.  Visual topological SLAM and global localization , 2009, 2009 IEEE International Conference on Robotics and Automation.

[16]  Hugh Durrant-Whyte,et al.  Simultaneous Localisation and Mapping ( SLAM ) : Part I The Essential Algorithms , 2006 .

[17]  Wolfram Burgard,et al.  Monte Carlo Localization: Efficient Position Estimation for Mobile Robots , 1999, AAAI/IAAI.

[18]  In-So Kweon,et al.  Scalable representation for 3D object recognition using feature sharing and view clustering , 2008, Pattern Recognit..

[19]  In-So Kweon,et al.  Recognition-based indoor topological navigation using robust invariant features , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Haibo He,et al.  IMORL: Incremental Multiple-Object Recognition and Localization , 2008, IEEE Transactions on Neural Networks.

[21]  Wan Kyun Chung,et al.  Autonomous topological modeling of a home environment and topological localization using a sonar grid map , 2011, Auton. Robots.

[22]  Pietro Perona,et al.  Recognition by Probabilistic Hypothesis Construction , 2004, ECCV.

[23]  Hans-Otto Karnath,et al.  Dorsal and Ventral Stream Interaction: Contributions from Optic Ataxia , 2005, Journal of Cognitive Neuroscience.

[24]  James Danckert,et al.  Dorsal and ventral stream interactions: Evidence from optic ataxia , 2008, Brain and Cognition.

[25]  In-So Kweon,et al.  Color landmark based self-localization for indoor mobile robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).