Detecting 3-D motion field from range image sequences

Chaudhury, K.; Mehrotra, R.; Srinivasan, C. R.

doi:10.1109/3477.752806

Cited by 6 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These correspondences can be considered both local (cf. [1]), or global by solving a total least squares framework [8]. The resulting flow field of the latter method is dense, yet the complexity is high and real-time computation is not feasible with current hardware.…”

Section: Related Workmentioning

confidence: 99%

Fast Motion Estimation on Range Image Sequences acquired with a 3-D Camera

Matzka¹,

Pétillot²,

Wallace³

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

This paper presents a computationally efficient approach to estimate translational 3-D motion from range images sequences, that is adapted from a 2-D motion estimation algorithm. An implementation of the algorithm is evaluated for computational efficiency as well as robustness in the presence of noise for both synthetic and real-life range data acquired with a PMD device, a high-speed low-resolution 3-D camera.

show abstract

Section: Related Workmentioning

confidence: 99%

Fast Motion Estimation on Range Image Sequences acquired with a 3-D Camera

Matzka¹,

Pétillot²,

Wallace³

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

show abstract

“…Computer vision-based motion analysis has been the subject for numerous research activities [1–15] for several decades. Optical flow- and feature-based techniques can be identified as the two most popular approaches employed in estimating motion parameters in a video stream.…”

Section: Introductionmentioning

confidence: 99%

Convergence of Object Focused Simultaneous Estimation of Optical Flow and State Dynamics

Bauer

Pathirana

Ekanayake

et al. 2014

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The purpose of this study is to prove the convergence of the simultaneous estimation of the optical flow and object state (SEOS) method. The SEOS method utilizes dynamic object parameter information when calculating optical flow in tracking a moving object within a video stream. Optical flow estimation for the SEOS method requires the minimization of an error function containing the object's physical parameter data. When this function is discretized, the Euler-Lagrange equations form a system of linear equations. The system is arranged such that its property matrix is positive definite symmetric, proving the convergence of the Gauss-Seidel iterative methods. The system of linear equations produced by SEOS can alternatively be resolved by Jacobi iterative schemes. The positive definite symmetric property is not sufficient for Jacobi convergence. The convergence of SEOS for a block diagonal Jacobi is proved by analysing the Euclidean norm of the Jacobi matrix. In this paper, we also investigate the use of SEOS for tracking individual objects within a video sequence. The illustrations provided show the effectiveness of SEOS for localizing objects within a video sequence and generating optical flow results.

show abstract