Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I am reading through http://www.scholarpedia.org/article/SIFT, and I need some help in a definition in this segment:
The SIFT descriptor has also been extended from grey-level to colour images and from 2-D spatial images to 2+1-D spatio-temporal video.
What is a 2+1-D spatial-temporal video?
It is simply a video.
They mean that the original technique was applied on grayscale images, which have 2 spatial dimensions; x and y.
It then was extended to be applied to colour images and then to temporal series of images, that is, videos. Videos have 3 dimensions; 2 spatial (x,y) and 1 temporal (time). They use 2+1 rather than 3 because 3D image usually refers to x/y/z rather than x/y/t