A Switched Systems Approach to Image-Based Localization of Targets That Temporarily Leave the Camera Field of View

Image sensors have widespread use in many robotics applications and, in particular, in target tracking. While existing methods assume continuous image feedback, the novelty of this brief stems from the development of dwell time conditions to guarantee convergence of state estimates to an ultimate bound for a class of image-based observers in the presence of intermittent measurements. A Lyapunov analysis for the switched system is performed to develop convergence conditions based on the minimum amount of time the object must be visible and on the maximum amount of time the object may remain outside the camera view. Experimental results are included to verify the theoretical results and elucidate real-world performance.

[1]  S. Shankar Sastry,et al.  An Invitation to 3-D Vision , 2004 .

[2]  Rafael Murrieta-Cid,et al.  Optimal Paths for Landmark-Based Navigation by Differential-Drive Vehicles With Field-of-View Constraints , 2007, IEEE Transactions on Robotics.

[3]  Zidong Wang,et al.  State Estimation for Coupled Uncertain Stochastic Networks With Missing Measurements and Time-Varying Delays: The Discrete-Time Case , 2009, IEEE Transactions on Neural Networks.

[4]  Hui Zhang,et al.  Observer-Based ℋ∞ Feedback Control for Arbitrarily Time-Varying Discrete-Time Systems With Intermittent Measurements and Input Constraints , 2012 .

[5]  P. Seiler,et al.  Optimal pseudo-steady-state estimators for systems with Markovian intermittent measurements , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[6]  W. Rudin.  Principles of mathematical analysis , 1964 .

[7]  Nicholas R. Gans,et al.  A Stable Vision-Based Control Scheme for Nonholonomic Vehicles to Keep a Landmark in the Field of View , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[8]  Emanuel Aldea,et al.  SO(3)-invariant asymptotic observers for dense depth field estimation based on visual data and known camera motion , 2011, 2012 American Control Conference (ACC).

[9]  Nicholas R. Gans,et al.  Homography-Based Control Scheme for Mobile Robots With Nonholonomic and Field-of-View Constraints , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[10]  Xinkai Chen,et al.  State observer for a class of nonlinear systems and its application to machine vision , 2004, IEEE Transactions on Automatic Control.

[11]  François Chaumette,et al.  Active Structure From Motion: Application to Point, Sphere, and Cylinder , 2014, IEEE Transactions on Robotics.

[12]  Lihua Xie,et al.  Mean square stability for Kalman filtering with Markovian packet losses , 2011, Autom..

[13]  Ashwin P. Dani,et al.  Structure and motion estimation of a moving object using a moving camera , 2010, Proceedings of the 2010 American Control Conference.

[14]  Tao Ding,et al.  Receding horizon rank minimization based estimation with applications to visual tracking , 2008, 2008 47th IEEE Conference on Decision and Control.

[15]  Jiri Matas,et al.  Sputnik Tracker: Having a Companion Improves Robustness of the Tracker , 2009, SCIA.

[16]  Guoqiang Hu,et al.  Lyapunov-Based Range Identification For A Paracatadioptric System , 2006, CDC.

[17]  Rogelio Lozano,et al.  Quad Rotorcraft Switching Control: An Application for the Task of Path Following , 2014, IEEE Transactions on Control Systems Technology.

[18]  Konrad Reif,et al.  Stochastic Stability of the Extended Kalman Filter With Intermittent Observations , 2010, IEEE Transactions on Automatic Control.

[19]  Domenico Prattichizzo,et al.  Range estimation from a moving camera: An Immersion and Invariance approach , 2009, 2009 IEEE International Conference on Robotics and Automation.

[20]  Stergios I. Roumeliotis,et al.  Performance analysis of multirobot Cooperative localization , 2006, IEEE Transactions on Robotics.

[21]  Warren E. Dixon,et al.  Euclidean Calculation of Feature Points of a Rotating Satellite: A Daisy Chaining Approach , 2007, ACC.

[22]  Edwin Engin Yaz,et al.  Robust minimum variance linear state estimators for multiple sensors with different failure rates , 2007, Autom..

[23]  Binlong Li,et al.  Dynamic subspace-based coordinated multicamera tracking , 2011, 2011 International Conference on Computer Vision.

[24]  Zidong Wang,et al.  On Nonlinear $H_{\infty }$ Filtering for Discrete-Time Stochastic Systems With Missing Measurements , 2008, IEEE Transactions on Automatic Control.

[25]  Agostino Martinelli,et al.  Vision and IMU Data Fusion: Closed-Form Solutions for Attitude, Speed, Absolute Scale, and Bias Determination , 2012, IEEE Transactions on Robotics.

[26]  Jamie S. Evans,et al.  Kalman filtering with faded measurements , 2009, Autom..

[27]  Bijoy K. Ghosh,et al.  Nonlinear observers for perspective time-invariant linear systems , 2004, Autom..

[28]  A. Michel,et al.  Stability analysis of switched systems with stable and unstable subsystems: an average dwell time approach , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[29]  Randal W. Beard,et al.  Bearing-only Cooperative Localization , 2013, J. Intell. Robotic Syst..

[30]  Tong Zhou,et al.  Robust state estimation for uncertain discrete-time stochastic systems with missing measurements , 2010, Proceedings of the 29th Chinese Control Conference.

[31]  Yuanqing Xia,et al.  Stochastic stability of the unscented Kalman filter with intermittent observations , 2012, Autom..

[32]  Warren E. Dixon,et al.  Vision-based localization of a wheeled mobile robot for greenhouse applications: A daisy-chaining approach , 2008 .

[33]  Anders Heyden,et al.  Observer forms for perspective systems , 2010, Autom..

[34]  João Carlos Basilio,et al.  Robust diagnosis of discrete event systems against intermittent loss of observations , 2012, Autom..

[35]  Zidong Wang,et al.  H∞ filtering with randomly occurring sensor saturations and missing measurements , 2012, Autom..

[36]  Stergios I. Roumeliotis,et al.  Robot-to-Robot Relative Pose Estimation From Range Measurements , 2008, IEEE Transactions on Robotics.

[37]  Antonio Bicchi,et al.  Shortest Paths for a Robot With Nonholonomic and Field-of-View Constraints , 2010, IEEE Transactions on Robotics.

[38]  Javier Civera,et al.  Inverse Depth Parametrization for Monocular SLAM , 2008, IEEE Transactions on Robotics.

[39]  Philippe C. Cattin,et al.  Tracking the invisible: Learning where the object might be , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[40]  S. Ullman.  The interpretation of structure from motion , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[41]  Stefano Soatto,et al.  Structure from Motion Causally Integrated Over Time , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  Guoqiang Hu,et al.  Lyapunov-Based Range Identification For Paracatadioptric Systems , 2006, IEEE Transactions on Automatic Control.

[43]  Daniel Liberzon,et al.  Switching in Systems and Control , 2003, Systems & Control: Foundations & Applications.

[44]  Warren E. Dixon,et al.  Globally exponentially stable observer for vision-based range estimation , 2012 .

[45]  Alessandro Astolfi,et al.  A new solution to the problem of range identification in perspective vision systems , 2005, IEEE Transactions on Automatic Control.

[46]  Stergios I. Roumeliotis,et al.  Distributed multirobot localization , 2002, IEEE Trans. Robotics Autom..

[47]  Tao Ding,et al.  The Role of Dynamics in Extracting Information Sparsely Encoded in High Dimensional Data Streams , 2010 .

[48]  Giuseppe Oriolo,et al.  Feature Depth Observation for Image-based Visual Servoing: Theory and Experiments , 2008, Int. J. Robotics Res..

[49]  Naira Hovakimyan,et al.  Fast estimation for range identification in the presence of unknown motion parameters , 2007, ICINCO-SPSMC.

[50]  Xinkai Chen,et al.  A new state observer for perspective systems , 2002, IEEE Trans. Autom. Control..

[51]  D. Dawson,et al.  Range identification for perspective vision systems , 2003, Proceedings of the 2003 American Control Conference, 2003..

[52]  Mario Sznaier,et al.  Motion Prediction for Continued Autonomy , 2009, Encyclopedia of Complexity and Systems Science.

[53]  Mrdjan Jankovic,et al.  Some Problems In Perspective System Theory And Its Application To Machine Vision , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[54]  Francisco José Madrid-Cuevas,et al.  Automatic generation and detection of highly reliable fiducial markers under occlusion , 2014, Pattern Recognit..

[55]  Fei Xiong,et al.  Dynamic Context for Tracking behind Occlusions , 2012, ECCV.

[56]  Daniel Liberzon,et al.  Input/output-to-state stability and state-norm estimators for switched nonlinear systems , 2012, Autom..

[57]  Gang Hua,et al.  Context-Aware Visual Tracking , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[58]  Hamid M. Faridani,et al.  Performance of kalman filter with missing measurements , 1986, Autom..

[59]  Warren E. Dixon,et al.  Structure estimation of a moving object using a moving camera: An unknown input observer approach , 2011, IEEE Conference on Decision and Control and European Control Conference.

[60]  François Chaumette,et al.  Visual servo control. I. Basic approaches , 2006, IEEE Robotics & Automation Magazine.

[61]  Darren M. Dawson,et al.  Euclidean position estimation of static features using a moving camera with known velocities , 2007, 2007 46th IEEE Conference on Decision and Control.

[62]  Anup Parikh,et al.  A switched systems approach to image-based localization of targets that temporarily leave the field of view , 2014, 53rd IEEE Conference on Decision and Control.

[63]  Anup Parikh,et al.  A switched systems approach to vision-based localization of a target with intermittent measurements , 2015, 2015 American Control Conference (ACC).

[64]  Balasubramaniam Natarajan,et al.  Stochastic state estimation for smart grids in the presence of intermittent measurements , 2012, 2012 IEEE Latin-America Conference on Communications.