Visual Motion Tracking and Sensor Fusion for Kite Power Systems

An estimation approach is presented for kite power systems with groundbased actuation and generation. Line-based estimation of the kite state, including position and heading, limits the achievable cycle efficiency of such airborne wind energy systems due to significant estimation delay and line sag. We propose a filtering scheme to fuse onboard inertial measurements with ground-based line data for ground-based systems in pumping operation. Estimates are computed using an extended Kalman filtering scheme with a sensor-driven kinematic process model which propagates and corrects for inertial sensor biases. We further propose a visual motion tracking approach to extract estimates of the kite position from ground-based video streams. The approach combines accurate object detection with fast motion tracking to ensure long-term object tracking in real time. We present experimental results of the visual motion tracking and inertial sensor fusion on a ground-based kite power system in pumping operation and compare both methods to an existing estimation scheme based on line measurements.

[1]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[2]  Rui Caseiro,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence High-speed Tracking with Kernelized Correlation Filters , 2022 .

[3]  Lorenzo Fagiano,et al.  On Sensor Fusion for Airborne Wind Energy Systems , 2012, IEEE Transactions on Control Systems Technology.

[4]  Aldo U. Zgraggen,et al.  Model-based identification and control of the velocity vector orientation for autonomous kites , 2015, 2015 American Control Conference (ACC).

[5]  Bernhard Schölkopf,et al.  A Generalized Representer Theorem , 2001, COLT/EuroCOLT.

[6]  Angelo M. Sabatini,et al.  Kalman-Filter-Based Orientation Determination Using Inertial/Magnetic Sensors: Observability Analysis and Performance Evaluation , 2011, Sensors.

[7]  Lorenzo Fagiano,et al.  Automatic Crosswind Flight of Tethered Wings for Airborne Wind Energy: Modeling, Control Design, and Experimental Results , 2013, IEEE Transactions on Control Systems Technology.

[8]  Aldo U. Zgraggen,et al.  Model-based flight path planning and tracking for tethered wings , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[9]  Ming-Hsuan Yang,et al.  Object Tracking Benchmark , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Janne Heikkilä,et al.  A four-step camera calibration procedure with implicit image correction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Michael Erhard,et al.  Sensors and navigation algorithms for flight control of tethered kites , 2013, 2013 European Control Conference (ECC).

[12]  Piotr Dollár,et al.  Crosstalk Cascades for Frame-Rate Pedestrian Detection , 2012, ECCV.

[13]  Luc Van Gool,et al.  Depth and Appearance for Mobile Scene Analysis , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Tony A. Wood,et al.  Visual Motion Tracking for Estimation of Kite Dynamics , 2015 .

[15]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Tony A. Wood,et al.  Range-inertial estimation for airborne wind energy , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[18]  P. Savage.  STRAPDOWN INERTIAL NAVIGATION INTEGRATION ALGORITHM DESIGN. PART 2: VELOCITY AND POSITION ALGORITHMS , 1998 .

[19]  Pietro Perona,et al.  Quickly Boosting Decision Trees - Pruning Underachieving Features Early , 2013, ICML.

[20]  Simone Calderara,et al.  Visual Tracking: An Experimental Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Christian Gebhardt,et al.  Development of a Three-Line Ground-Actuated Airborne Wind Energy Converter , 2013 .

[22]  Michael Erhard,et al.  Theory and Experimental Validation of a Simple Comprehensible Model of Tethered Kite Dynamics Used for Controller Design , 2013 .

[23]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[24]  Roland Schmehl,et al.  The International Airborne Wind Energy Conference 2015: Book of abstracts , 2015 .

[25]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[26]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[27]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[28]  E. J. Lefferts,et al.  Kalman Filtering for Spacecraft Attitude Estimation , 1982 .

[29]  Robert M. Gray,et al.  Toeplitz and Circulant Matrices: A Review , 2005, Found. Trends Commun. Inf. Theory.

[30]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[31]  Jonathan Brandt,et al.  Robust object detection via soft cascade , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[32]  Lorenzo Fagiano,et al.  Automatic Retraction and Full-Cycle Operation for a Class of Airborne Wind Energy Generators , 2014, IEEE Transactions on Control Systems Technology.