Sciweavers

RAS
2007
132views more  RAS 2007»
13 years 7 months ago
Virtual sensors for human concepts - Building detection by an outdoor mobile robot
Abstract— In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We suggest to use a virtual sensor (one or several physic...
Martin Persson, Tom Duckett, Achim J. Lilienthal
PAMI
2007
155views more  PAMI 2007»
13 years 7 months ago
Localization of Shapes Using Statistical Models and Stochastic Optimization
—In this paper, we present a new model for deformations of shapes. A pseudolikelihood is based on the statistical distribution of the gradient vector field of the gray level. The...
François Destrempes, Max Mignotte, Jean-Fra...
WCE
2007
13 years 8 months ago
Applying EM Algorithm for Segmentation of Textured Images
— Texture analysis plays an increasingly important role in computer vision. Since the textural properties of images appear to carry useful information for discrimination purposes...
K. Revathy, V. S. Roshni
SCALESPACE
1997
Springer
13 years 11 months ago
From High Energy Physics to Low Level Vision
A geometric framework for image scale space, enhancement, and segmentation is presented. We consider intensity images as surfaces in the (x I) space. The image is thereby a 2D surf...
Ron Kimmel, Nir A. Sochen, Ravi Malladi
ICDAR
2003
IEEE
14 years 22 days ago
Writer Identification from Gray Level Distribution
When identifying a writer from a handwritten text, most often, either some characteristic patterns or some shape parameters are extracted. They are assumed to be specific of the w...
M. Wirotius, Audrey Seropian, Nicole Vincent
SCALESPACE
2007
Springer
14 years 1 months ago
Faithful Recovery of Vector Valued Functions from Incomplete Data
On March 11, 1944, the famous Eremitani Church in Padua (Italy) was destroyed in an Allied bombing along with the inestimable frescoes by Andrea Mantegna et al. contained in the Ov...
Massimo Fornasier
ICIP
1997
IEEE
14 years 9 months ago
Detecting and Solving Template Ambiguities in Motion Segmentation
When the color or gray level of a moving object is very similar to that of the background, motion-based segmentation methods fail. This leads to ambiguous templates for the moving...
José M. F. Moura, Pedro M. Q. Aguiar