Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Human-Assisted Motion Annotation William T. Freeman1

Summary: Human-Assisted Motion Annotation
Ce Liu1
William T. Freeman1
Edward H. Adelson1
Yair Weiss1,2
The Hebrew University of Jerusalem
{celiu,billf,adelson}@csail.mit.edu yweiss@cs.huji.ac.il
(a) A frame of a video sequence (b) User-aided layer segmentation (c) User-annotated motion (d) Output of a flow algorithm [8]
Figure 1. We designed a system to allow the user to specify layer configurations and motion hints (b). Our system uses these hints to
calculate a dense flow field for each layer. We show that the flow (c) is repeatable and accurate. (d): The output of a representative optical
flow algorithm [8], trained on the Yosemite sequence, shows many differences from the labeled ground truth for this and other realistic
sequences we have labeled. This indicates the value of our database for training and evaluating optical flow algorithms.
Obtaining ground-truth motion for arbitrary, real-world
video sequences is a challenging but important task for both
algorithm evaluation and model design. Existing ground-
truth databases are either synthetic, such as the Yosemite
sequence, or limited to indoor, experimental setups, such


Source: Adelson, Edward - Computer Science and Artificial Intelligence Laboratory, Department of Brain and Cognitive Science, Massachusetts Institute of Technology (MIT)
Freeman, William T. - Computer Science and Artificial Intelligence Laboratory & Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)


Collections: Biology and Medicine; Computer Technologies and Information Sciences