Abstract Recently, it has been shown that invariants on motions can be extracted from sequential images and these can be applied for recognizing dynamic events from images viewed from arbitrary viewpoints. These invariants are called space-time invariants since they are defined in space and time. Unfortunately, the existing space-time invariants are limited for planar motions viewed from affine cameras. In this paper, we propose a method for computing space-time invariants on general 3D motions viewed from projective cameras. Furthermore, we show that by using the epipolar geometry derived from the mutual projection of cameras, the stability of space-time invariants can be improved drastically. The extracted invariants are applied for distinguishing non-rigid 3D motions from video sequences viewed from arbitrary viewpoints.
Space-Time Invariants for 3D Motions from Projective Cameras
Computer Vision – ACCV 2006 ; 7 ; 811-821
Lecture Notes in Computer Science ; 3852 , 7
2006-01-01
11 pages
Article/Chapter (Book)
Electronic Resource
English
Space-Time Invariants for 3D Motions from Projective Cameras
British Library Conference Proceedings | 2006
|Finding Geometric Invariants From Time-Based Invariants for Spherical and Spatial Motions
Online Contents | 2005
|Geometric invariants for rational polynomial cameras
IEEE | 2000
|Geometric Invariants for Rational Polynomial Cameras
British Library Conference Proceedings | 2000
|Pi-Tag: a fast image-space marker design based on projective invariants
British Library Online Contents | 2013
|