In this correspondence, the application of covariance techniques to surface representation of 3-D objects is discussed and such ways of computing surface geometry are compared with traditional methods using Differential Geometry. It is shown how the covariance method provides surface descriptors that are invariant to rigid motions without explicitly using surface parameterizations or derivatives. Analogous covariance operators for both the Gauss and Weingarten maps are defined and a range image segmentation technique is presented that labels pixels as jump or crease discontinuities or planar, parabolic or curved region types. © 1994 IEE
In many applications, such as computer vision, medical imaging, scene forming, and motion animation,...
Early image understanding seeks to derive analytic representations from image data. This thesis pres...
This paper addresses the problem of parametric representation and estimation of complex planar curve...
In this paper, the concepts of differential geometry traditionally applied to the segmentation of ra...
Abstract-Computer vision systems attempt to recover useful infor-mation about the three-dimensional ...
This paper continues our work on visual representation s of three-dimensional surfaces [Brady and ...
The approach of devising robust surface methods applicable to arbitrarily located data was taken by ...
A new technique for computing the differential invariants of a surface from 3D sample points and nor...
Perception of surfaces plays a fundamental role in three-dimensional object recognition and image un...
A method for segmenting range images into homogeneous regions is presented. The resulting regions ar...
The need for three-dimensional (3-D) computer vision in robot control, measurement of object geometr...
Range images contain important shape information about 3-dimensional objects. This dissertation addr...
By exploiting the relationship which exists between the Gaussian image and gradient space, the two r...
Abstract. We describe a new region descriptor and apply it to two problems, object detection and tex...
Visualizing the dynamics of n-dimensional graphics is made possible by high speed, high quality comp...
In many applications, such as computer vision, medical imaging, scene forming, and motion animation,...
Early image understanding seeks to derive analytic representations from image data. This thesis pres...
This paper addresses the problem of parametric representation and estimation of complex planar curve...
In this paper, the concepts of differential geometry traditionally applied to the segmentation of ra...
Abstract-Computer vision systems attempt to recover useful infor-mation about the three-dimensional ...
This paper continues our work on visual representation s of three-dimensional surfaces [Brady and ...
The approach of devising robust surface methods applicable to arbitrarily located data was taken by ...
A new technique for computing the differential invariants of a surface from 3D sample points and nor...
Perception of surfaces plays a fundamental role in three-dimensional object recognition and image un...
A method for segmenting range images into homogeneous regions is presented. The resulting regions ar...
The need for three-dimensional (3-D) computer vision in robot control, measurement of object geometr...
Range images contain important shape information about 3-dimensional objects. This dissertation addr...
By exploiting the relationship which exists between the Gaussian image and gradient space, the two r...
Abstract. We describe a new region descriptor and apply it to two problems, object detection and tex...
Visualizing the dynamics of n-dimensional graphics is made possible by high speed, high quality comp...
In many applications, such as computer vision, medical imaging, scene forming, and motion animation,...
Early image understanding seeks to derive analytic representations from image data. This thesis pres...
This paper addresses the problem of parametric representation and estimation of complex planar curve...