Model-based recognition in robot vision
ACM Computing Surveys (CSUR)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fundamentals of statistical signal processing: estimation theory
Fundamentals of statistical signal processing: estimation theory
Machine vision
Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
Detection, Estimation, and Modulation Theory: Radar-Sonar Signal Processing and Gaussian Signals in Noise
Robot Vision
Introductory Techniques for 3-D Computer Vision
Introductory Techniques for 3-D Computer Vision
Digital Picture Processing
Computer Vision
Fast object recognition in noisy images using simulated annealing
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Information-Conserving Object Recognition
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Automatic 3D Registration of Lung Surfaces in Computed Tomography Scans
MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
On the Topology and Geometry of Spaces of Affine Shapes
Journal of Mathematical Imaging and Vision
Speed supervisor for intelligent vehicles
EUROCAST'07 Proceedings of the 11th international conference on Computer aided systems theory
Video stabilization for a hand-held camera based on 3D motion model
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Hi-index | 0.00 |
The problem of recognizing objects subject to affine transformation in images is examined from a physical perspective using the theory of statistical estimation. Focusing first on objects that occlude zero-mean scenes with additive noise, we derive the Cramer-Rao lower bound on the mean-square error in an estimate of the six-dimensional parameter vector that describes an object subject to affine transformation and so generalize the bound on one-dimensional position error previously obtained in radar and sonar pattern recognition. We then derive two useful descriptors from the object's Fisher information that are independent of noise level. The first is a generalized coherence scale that has great practical value because it corresponds to the width of the object's autocorrelation peak under affine transformation and so provides a physical measure of the extent to which an object can be resolved under affine parameterization. The second is a scalar measure of an object's complexity that is invariant under affine transformation and can be used to quantitatively describe the ambiguity level of a general 6-dimensional affine recognition problem. This measure of complexity has a strong inverse relationship to the level of recognition ambiguity. We then develop a method for recognizing objects subject to affine transformation imaged in thousands of complex real-world scenes. Our method exploits the resolution gain made available by the brightness contrast between the object perimeter and the scene it partially occludes. The level of recognition ambiguity is shown to decrease exponentially with increasing object and scene complexity. Ambiguity is then avoided by conditioning the permissible range of template complexity above a priori thresholds. Our method is statistically optimal for recognizing objects that occlude scenes with zero-mean background.