Title :
Segmentation and factorization-based motion and structure estimation for long image sequences
Author :
Debrunner, Christian ; Ahuja, Narendra
Author_Institution :
Lockheed Martin Corp., Denver, CO, USA
fDate :
2/1/1998 12:00:00 AM
Abstract :
This paper presents a computer algorithm which, given a dense temporal sequence of intensity images of multiple moving objects, can separate the images into regions showing distinct objects and, for those objects which are rotating, calculate the three-dimensional structure and motion
Keywords :
computer vision; image segmentation; image sequences; matrix algebra; motion estimation; optical tracking; 3D structure estimation; computer vision; factorization; image segmentation; image sequences; motion estimation; point tracking; trajectory detection; Computer vision; Image segmentation; Image sequences; Motion analysis; Motion estimation; Motion segmentation; Object detection; Partitioning algorithms; Testing; Trajectory;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
