Optimizing of searching co-motion point-pairs for statistical camera calibration

In the paper we introduce an algorithm for matching partially overlapping image-pairs where the object of interest is in motion, even if the motion is discontinuous and in an unstructured environment. In our previous work [10] we have shown that by using co-motion statistics matching of overlapping views can be done and then the projective geometry can be estimated. Here we will show how to optimize searching for concurrently moving pixels. The robust algorithm we describe here finds point correspondences in two images by using entropybased thresholding and without searching for any structures and without the need for tracking continuous motion. Our method makes it possible to (re)calibrate multicamera systems without human assistance. Keywords-camera calibration, image registration, co-motions

• Type: Conference
• Year: 2005
• Where: ICIP
• Authors: Csaba Benedek, Laszlo Havasi, Tamás Szirányi, Zoltán Szlávik
• Keywords: Co-motion Statistics, Continuous Motion, ICIP 2005, Image Processing, Multicamera Systems, Projective Geometry, Robust Algorithm