Title :
Three-dimensional scene flow
Author :
Vedula, Srinivas ; Rander, Peter ; Collins, R. ; Kanade, Takeo
fDate :
3/1/2005 12:00:00 AM
Abstract :
Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only the normal flow can be computed directly from the image measurements, without some form of smoothing or regularization. In this paper, we begin by showing that the same fundamental limitation applies to scene flow; however, many cameras are used to image the scene. There are then two choices when computing scene flow: 1) perform the regularization in the images or 2) perform the regularization on the surface of the object in the scene. In this paper, we choose to compute scene flow using regularization in the images. We describe three algorithms, the first two for computing scene flow from optical flows and the third for constraining scene structure from the inconsistencies in multiple optical flows.
Keywords :
cameras; computational geometry; image motion analysis; image sequences; cameras; computational geometry; image measurements; image regularization; multiple optical flows; scene structure constraint; three dimensional motion; three dimensional scene flow computing; Cameras; Computer vision; Deformable models; Fluid flow measurement; Image motion analysis; Layout; Motion estimation; Optical computing; Reflectivity; Smoothing methods; Index Terms- Scene flow; normal flow; optical flow; the brightness constancy constraint; three-dimensional dense nonrigid motion; three-dimensional normal flow.; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Graphics; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Movement; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Photogrammetry; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Video Recording;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2005.63