Sciweavers

BMVC
2010
13 years 6 months ago
Epipolar Constraints for Multiscale Matching
Many recent keypoint detectors associate a local scale (for multiscale detectors) or even a full affine frame (for affine-invariant detectors) to each detected keypoint. Although ...
Bill Triggs, Pashmina Bendale
PAMI
2007
187views more  PAMI 2007»
13 years 11 months ago
Detecting Motion Regions in the Presence of a Strong Parallax from a Moving Camera by Multiview Geometric Constraints
—We present a method for detecting motion regions in video sequences observed by a moving camera in the presence of a strong parallax due to static 3D structures. The proposed me...
Chang Yuan, Gérard G. Medioni, Jinman Kang,...
IJCV
2007
138views more  IJCV 2007»
13 years 11 months ago
Correspondence-free Structure from Motion
We present a novel approach for the estimation of 3D-motion directly from two images using the Radon transform. The feasibility of any camera motion is computed by integrating over...
Ameesh Makadia, Christopher Geyer, Kostas Daniilid...
IROS
2009
IEEE
189views Robotics» more  IROS 2009»
14 years 6 months ago
Moving object detection by multi-view geometric techniques from a single camera mounted robot
— The ability to detect, and track multiple moving objects like person and other robots, is an important prerequisite for mobile robots working in dynamic indoor environments. We...
Abhijit Kundu, Madhava M. Krishna, Jayanthi Sivasw...
ICIP
2003
IEEE
15 years 1 months ago
Three-view camera calibration using geometric algebra
In a former work of ours [I], we proposed a new way to express and interpret the epipolar constraint using Geometric Algebra, and we derived from it a novel and efficient2view cam...
Andrea Dell'Acqua, Augusto Sarti, Stefano Tubaro
CVPR
2005
IEEE
15 years 1 months ago
Radon-Based Structure from Motion without Correspondences
We present a novel approach for the estimation of 3Dmotion directly from two images using the Radon transform. We assume a similarity function defined on the crossproduct of two i...
Ameesh Makadia, Christopher Geyer, Shankar Sastry,...