Robust visual tracking framework in the presence of blurring by arbitrating appearance- and feature-based detection

Abstract This paper proposes a new visual tracking framework and demonstrates its merits via mobile robot experiments. An image sequence from the vision system of a mobile robot is not static when a mobile robot is moving, since slipping and vibration occur. These problems cause image blurring. Therefore, in this paper, we address the problem of robust object tracking under blurring and introduce a novel robust visual tracking framework based on the arbitration of the AdaBoost-based detection method and the appearance-based detection method to overcome the blurring problem. The proposed framework consists of three parts: (1) distortion error compensation and feature extraction using the Modified Discrete Gaussian–Hermite Moment (MDGHM) and fuzzy-based distortion error compensation, (2) object detection using arbitration of appearance- and feature-based object detection, and (3) object tracking using a Finite Impulse Response (FIR) filter. To demonstrate the performance of the proposed framework, mobile robot visual tracking experiments are carried out. The results show that the proposed framework is more robust against blurring than the conventional feature- and appearance-based methods.

[1]  Myo Taeg Lim,et al.  Horizon group shift FIR filter: Alternative nonlinear filter using finite recent measurements , 2014 .

[2]  Peng Shi,et al.  Two-Dimensional Dissipative Control and Filtering for Roesser Model , 2015, IEEE Transactions on Automatic Control.

[3]  W. H. Kwon,et al.  FIR filters and recursive forms for continuous time-invariant state-space models , 1987 .

[4]  Bin Fang,et al.  Sift features based object tracking with discrete wavelet transform , 2009, 2009 International Conference on Wavelet Analysis and Pattern Recognition.

[5]  Xin Chen,et al.  Real-time Visual Object Tracking via CamShift-Based Robust Framework , 2012 .

[6]  Myo Taeg Lim,et al.  New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter , 2015 .

[7]  Gibson,et al.  A steady-state optimal control problem , 1976 .

[8]  Myo-Taeg Lim,et al.  Multi-target FIR tracking algorithm for Markov jump linear systems based on true-target decision-making , 2015, Neurocomputing.

[9]  Myo Taeg Lim,et al.  Development of 3D camera-based robust bolt-hole detection system for bolting cabin , 2014 .

[10]  Gwi-Tae Park,et al.  Enhanced SIFT Descriptor Based on Modified Discrete Gaussian‐Hermite Moment , 2012 .

[11]  Chia-Wen Lin,et al.  A region-based object tracking scheme using Adaboost-based feature selection , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[12]  Wook Hyun Kwon,et al.  ${\cal H}_{\infty}$ Finite Memory Controls for Linear Discrete-Time State-Space Models , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[13]  Jan Flusser,et al.  Image features invariant with respect to blur , 1995, Pattern Recognit..

[14]  Thomas Becker,et al.  A novel edge detection method with application to the fat content prediction in marbled meat , 2011, Pattern Recognit..

[15]  Pheng-Ann Heng,et al.  Two-Stage Object Tracking Method Based on Kernel and Active Contour , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  Choon Ki Ahn,et al.  Robustness bound for receding horizon finite memory control: Lyapunov–Krasovskii approach , 2012, Int. J. Control.

[17]  Petr Dokládal,et al.  Contour-based object tracking with gradient-based contour attraction field , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Jong-Hann Jean,et al.  Robust Visual Servo Control of a Mobile Robot for Object Tracking Using Shape Parameters , 2012, IEEE Transactions on Control Systems Technology.

[19]  Choon Ki Ahn,et al.  Strictly passive FIR filtering for state-space models with external disturbance , 2012 .

[20]  Bo Hu,et al.  Robust Object Tracking Against Template Drift , 2007, 2007 IEEE International Conference on Image Processing.

[21]  Guoliang Fan,et al.  Adaptive Kalman Filtering for Histogram-Based Appearance Learning in Infrared Imagery , 2012, IEEE Transactions on Image Processing.

[22]  Roland Siegwart,et al.  Innovative design for wheeled locomotion in rough terrain , 2002, Robotics Auton. Syst..

[23]  Myo Taeg Lim,et al.  Time-domain filtering for estimation of linear systems with colored noises using recent finite measurements , 2013 .

[24]  Gwi-Tae Park,et al.  Ego-motion-compensated object recognition using type-2 fuzzy set for a moving robot , 2013, Neurocomputing.

[25]  Roland Siegwart,et al.  Mobility evaluation of wheeled all-terrain robots , 2010, Robotics Auton. Syst..

[26]  Wook Hyun Kwon,et al.  Optimal FIR filters for time-varying state-space models , 1990 .

[27]  Yongjin Kwon,et al.  Improvement of vision guided robotic accuracy using Kalman filter , 2013, Comput. Ind. Eng..

[28]  A. Jazwinski.  Limited memory optimal filtering , 1968 .

[29]  Choon Ki Ahn,et al.  A new solution to the induced l∞ finite impulse response filtering problem based on two matrix inequalities , 2014, Int. J. Control.

[30]  Robert C. Bolles,et al.  Outdoor Mapping and Navigation Using Stereo Vision , 2006, ISER.

[31]  W. Kwon,et al.  Receding Horizon Control: Model Predictive Control for State Models , 2005 .

[32]  Yao Lu,et al.  Optical Flow Based Urban Road Vehicle Tracking , 2013, 2013 Ninth International Conference on Computational Intelligence and Security.

[33]  John Norrish,et al.  Recent Progress on Programming Methods for Industrial Robots , 2010, ISR/ROBOTIK.

[34]  Zhi Liu,et al.  Mean shift blob tracking with kernel histogram filtering and hypothesis testing , 2005, Pattern Recognit. Lett..

[35]  Roman P. Pflugfelder,et al.  Consensus-based matching and tracking of keypoints for object tracking , 2014, IEEE Winter Conference on Applications of Computer Vision.

[36]  Heiko Hirschmüller,et al.  Stereo camera based navigation of mobile robots on rough terrain , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[37]  Rita Cucchiara,et al.  A Hough transform-based method for radial lens distortion correction , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[38]  Wook Hyun Kwon,et al.  $cal H_infty$FIR Filters for Linear Continuous-Time State–Space Systems , 2006, IEEE Signal Processing Letters.

[39]  Aparna Saha,et al.  Multi-object Tracking in Video Sequences Based on Background Subtraction and SIFT Feature Matching , 2009, 2009 Fourth International Conference on Computer Sciences and Convergence Information Technology.