IEEE Transactions on Pattern Analysis and Machine Intelligence
A simplified linear optic-flow motion algorithm
Computer Vision, Graphics, and Image Processing
Motion Field and Optical Flow: Qualitative Properties
IEEE Transactions on Pattern Analysis and Machine Intelligence
Subspace methods for recovering rigid motion I: algorithm and implementation
International Journal of Computer Vision
3-D interpretation of optical flow by renormalization
International Journal of Computer Vision
Linear subspace methods for recovering translational direction
Proceedings of the 1991 York conference on Spacial vision in humans and robots
A guided tour of computer vision
A guided tour of computer vision
The computation of optical flow
ACM Computing Surveys (CSUR)
Introductory Techniques for 3-D Computer Vision
Introductory Techniques for 3-D Computer Vision
Optimal Motion and Structure Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computing camera heading: a study
Computing camera heading: a study
Fixation as a Mechanism for Stabilization of Short Image Sequences
International Journal of Computer Vision
Optimal instantaneous rigid motion estimation insensitive to local minima
Computer Vision and Image Understanding
On the Consistency of the Normalized Eight-Point Algorithm
Journal of Mathematical Imaging and Vision
Inverse perspective mapping and optic flow: A calibration method and a quantitative analysis
Image and Vision Computing
A two-level real-time vision machine combining coarse- and fine-grained parallelism
Journal of Real-Time Image Processing
A review and evaluation of methods estimating ego-motion
Computer Vision and Image Understanding
| Hi-index | 0.00 |
Instantaneous camera motion estimation is an important research topic in computer vision. Although in theory more than five points uniquely determine the solution in an ideal situation, in practice one can usually obtain better estimates by using more image velocity measurements because of the noise present in the velocity measurements. However, the usefulness of using a large number of observations has never been analyzed in detail. In this paper, we formulate this problem in the statistical estimation framework. We show that under certain noise models, consistency of motion estimation can be established: that is, arbitrarily accurate estimates of motion parameters are possible with more and more observations. This claim does not simply follow from the general consistency result for maximum likelihood estimates. Some experiments will be provided to verify our theory. Our analysis and experiments also indicate that many previously proposed algorithms are inconsistent under even very simple noise models.