View management for lifelong visual maps

The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored [1], [2]. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.

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

[2]  Scott Lenser,et al.  Fast Nonlinear Approximation of Pose Graph Node Marginalization , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Kurt Konolige,et al.  Towards lifelong visual maps , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Michael Bosse,et al.  Keep it brief: Scalable creation of compressed localization maps , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[5]  Christian Schlegel,et al.  Lifelong localization of a mobile service-robot in everyday indoor environments using omnidirectional vision , 2009, 2009 IEEE International Conference on Technologies for Practical Robot Applications.

[6]  Roland Siegwart,et al.  Erasing bad memories: Agent-side summarization for long-term mapping , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Konrad Schindler,et al.  Predicting Matchability , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Winston Churchill,et al.  Experience-based navigation for long-term localisation , 2013, Int. J. Robotics Res..

[9]  Dario Maio,et al.  Saliency-based keypoint selection for fast object detection and matching , 2015, Pattern Recognit. Lett..

[10]  Paul Newman,et al.  Practice makes perfect? Managing and leveraging visual experiences for lifelong navigation , 2012, 2012 IEEE International Conference on Robotics and Automation.

[11]  Niko Sünderhauf,et al.  Towards a robust back-end for pose graph SLAM , 2012, 2012 IEEE International Conference on Robotics and Automation.

[12]  Vincent Lepetit,et al.  View-based Maps , 2010, Int. J. Robotics Res..

[13]  Mario E. Munich,et al.  Monocular graph SLAM with complexity reduction , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  David G. Lowe,et al.  Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration , 2009, VISAPP.

[15]  Frank Dellaert,et al.  Factor Graphs for Robot Perception , 2017, Found. Trends Robotics.

[16]  Roland Siegwart,et al.  Appearance-based landmark selection for efficient long-term visual localization , 2016, IROS 2016.