A Review of 3D Pose Estimation from a Monocular Image Sequence

D pose estimation is an important part of 3D motion estimation, which is useful for visualized operation and control. The paper classified approaches of 3D pose estimation from a monocular image sequence into three types: feature-based approach, optical-flow-based approach and model-based approach. In feature-based approaches, 3D motion are estimated by observing a set of 2D features, such as points, lines, junctions and corners, over two or more images. On the contrary, optical- flow-based approaches estimate instantaneous 3D motion from image plane velocity. Both of them can complete the estimation without any a priori knowledge of the object, but the computation is complex and time-consuming. Mode-based approach avoids the burden of computation, but relies on the a priori knowledge of the object. Current research status of each approach is reviewed. Comparison of these three approaches and developing trends of 3D pose estimation are discussed in the conclusion.

[1]  Björn Barrois,et al.  3D Pose Estimation Based on Multiple Monocular Cues , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  John S. Zelek,et al.  A Factorized Recursive Estimation of Structure and Motion from Image Velocities , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[3]  I. Pitas,et al.  Hierarchical Face Clustering using SIFT Image Features , 2007, 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing.

[4]  Daoying Pi,et al.  Particle Filter Based Pose and Motion Estimation with Non-Gaussian Noise , 2006, 2006 IEEE International Conference on Industrial Technology.

[5]  Heihachiro Kamimura,et al.  Motion Estimation to a Failed Satellite on Orbit using Stereo Vision and 3D Model Matching , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[6]  X. Rong Li,et al.  Feature Association for Object Tracking , 2006, 2006 9th International Conference on Information Fusion.

[7]  Hongsheng Zhang,et al.  EKF-Based Recursive Dual Estimation of Structure & Motion from Stereo Data , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[8]  Andrew Calway,et al.  Recursive estimation of 3D motion and surface structure from local affine flow parameters , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Amarnath Banerjee,et al.  Pattern tracking and 3-D motion reconstruction of a rigid body from a 2-D image sequence , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[10]  Vincenzo Lippiello,et al.  Visual motion estimation of 3D objects: an adaptive extended Kalman filter approach , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[11]  Takami Matsuo,et al.  Adaptive estimation of 3-D motion parameters and optical flow , 2003, Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694).

[12]  Y. Perret,et al.  Estimation of 3D real motion: a model based approach , 2002, IEEE International Conference on Systems, Man and Cybernetics.

[13]  Sang Uk Lee,et al.  A new robust 3D motion estimation under perspective projection , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[14]  L. Vese,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[15]  Steven D. Blostein,et al.  Three-dimensional trajectory estimation from image position and velocity , 2000, IEEE Trans. Aerosp. Electron. Syst..

[16]  Jezekiel Ben-Arie,et al.  Estimation of 3-D motion using eigen-normalization and expansion matching , 2000, IEEE Trans. Image Process..

[17]  Naoki Mukawa,et al.  Optical-Model-Based Analysis of Consecutive Images , 1997, Comput. Vis. Image Underst..

[18]  Jorge L. C. Sanz,et al.  Optical flow computation using extended constraints , 1996, IEEE Trans. Image Process..

[19]  S. D. Blostein,et al.  The use of image plane velocity measurements in recursive 3-D motion estimation from a monocular image sequence , 1994, 1994 Proceedings of Canadian Conference on Electrical and Computer Engineering.

[20]  Hassan Mostafavi,et al.  Rigid-body attitude estimation from a single view , 1993, Optics & Photonics.

[21]  Narendra Ahuja,et al.  Matching Two Perspective Views , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  R. Chellappa,et al.  Recursive 3-D motion estimation from a monocular image sequence , 1990 .

[23]  Y. Kay,et al.  A Kalman filter approach for accurate 3D motion estimation from a sequence of stereo images , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[24]  Thomas S. Huang,et al.  A linear algorithm for motion estimation using straight line correspondences , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[25]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[26]  Zhang Ming-xiu,et al.  Head Detecting and Tracking Based on Hough Transform , 2008 .

[27]  V. Jilkov,et al.  International Conference on Information Fusion ( FUSION ) Enhanced Image Feature Extraction for Object Tracking * , 2006 .

[28]  Zhang Zuxun.  Airplane Pose Measurement from Image Sequences , 2004 .

[29]  Zhang Xiao,et al.  3D Motion Estimation from Image Corners , 2003 .

[30]  Yu Qi,et al.  Approach of determination of object's 3D pose from mono-view , 2002 .

[31]  Yannick Berthoumieu,et al.  Optical flow estimation using forward-backward constraint equation , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[32]  Michal Irani,et al.  Multi-frame optical flow estimation using subspace constraints , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[33]  Jake K. Aggarwal,et al.  On the computation of motion from sequences of images-A review , 1988, Proc. IEEE.