Active gaze stabilization

We describe a system for active stabilization of cameras mounted on highly dynamic robots. To focus on careful performance evaluation of the stabilization algorithm, we use a camera mounted on a robotic test platform that can have unknown perturbations in the horizontal plane, a commonly occurring scenario in mobile robotics. We show that the camera can be effectively stabilized using an inertial sensor and a single additional motor, without a joint position sensor. The algorithm uses an adaptive controller based on a model of the vertebrate Cerebellum for velocity stabilization, with additional drift correction. We have also developed a resolution adaptive retinal slip algorithm that is robust to motion blur. We evaluated the performance quantitatively using another high speed robot to generate repeatable sequences of large and fast movements that a gaze stabilization system can attempt to counteract. Thanks to the high-accuracy repeatability, we can make a fair comparison of algorithms for gaze stabilization. We show that the resulting system can reduce camera image motion to about one pixel per frame on average even when the platform is rotated at 200 degrees per second. As a practical application, we also demonstrate how the common task of face detection benefits from active gaze stabilization.

[1]  P. Schönemann,et al.  A generalized solution of the orthogonal procrustes problem , 1966 .

[2]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[3]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[4]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Peter Corke,et al.  High-Performance Visual Closed-Loop Robot Control , 1994 .

[6]  Rama Chellappa,et al.  Fast Electronic Digital Image Stabilization for Off-Road Navigation , 1996, Real Time Imaging.

[7]  Giorgio Metta,et al.  BabyRoBot: A study in sensori-motor development , 1999 .

[8]  R. Brooks,et al.  The cog project: building a humanoid robot , 1999 .

[9]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Masatoshi Ishikawa,et al.  1 ms column parallel vision system and its application of high speed target tracking , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[11]  Chrystopher L. Nehaniv.  Computation for Metaphors, Analogy, and Agents , 2000, Lecture Notes in Computer Science.

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

[13]  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.

[14]  Stefan Schaal,et al.  Biomimetic Oculomotor Control , 2001, Adapt. Behav..

[15]  James V. Stone,et al.  Decorrelation control by the cerebellum achieves oculomotor plant compensation in simulated vestibulo-ocular reflex , 2002, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[16]  Giulio Sandini,et al.  Learning visual stabilization reflexes in robots with moving eyes , 2002, Neurocomputing.

[17]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[18]  Sei-Wang Chen,et al.  Video stabilization for a camcorder mounted on a moving vehicle , 2004, IEEE Transactions on Vehicular Technology.

[19]  H. Ulbrich,et al.  An Inertially Stabilised Vehicle Camera System - Hardware, Algorithms, Test Drives , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[20]  Giorgio Metta,et al.  Design of the robot-cub (iCub) head , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[21]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[22]  P. Dean,et al.  Oculomotor anatomy and the motor-error problem: the role of the paramedian tract nuclei. , 2008, Progress in brain research.

[23]  Giulio Sandini,et al.  Eyes-Neck Coordination Using Chaos , 2008, EUROS.

[24]  Sean R. Anderson,et al.  Cerebellar-Inspired Adaptive Control of a Robot Eye Actuated by Pneumatic Artificial Muscles , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  S. B. Kang,et al.  Image deblurring using inertial measurement sensors , 2010, ACM Trans. Graph..

[26]  Jean Ponce,et al.  Non-uniform Deblurring for Shaken Images , 2012, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  H Ulbrich,et al.  Design and Control of a Compact High-Dynamic Camera-Orientation System , 2011, IEEE/ASME Transactions on Mechatronics.

[28]  Robert H. Halstead,et al.  Matrix Computations , 2011, Encyclopedia of Parallel Computing.