A Detailed Rubric for Motion Segmentation

TL;DR

This paper provides a precise definition of motion segmentation in computer vision and introduces updated datasets aligned with this definition to facilitate more consistent and meaningful comparisons of segmentation methods.

Contribution

It offers a detailed, formal definition of motion segmentation and presents new versions of three datasets compatible with this definition.

Findings

Clarified the problem scope of motion segmentation.

Revised three datasets to match the new definition.

Facilitates more consistent evaluation of segmentation algorithms.

Abstract

Motion segmentation is currently an active area of research in computer Vision. The task of comparing different methods of motion segmentation is complicated by the fact that researchers may use subtly different definitions of the problem. Questions such as "Which objects are moving?", "What is background?", and "How can we use motion of the camera to segment objects, whether they are static or moving?" are clearly related to each other, but lead to different algorithms, and imply different versions of the ground truth. This report has two goals. The first is to offer a precise definition of motion segmentation so that the intent of an algorithm is as well-defined as possible. The second is to report on new versions of three previously existing data sets that are compatible with this definition. We hope that this more detailed definition, and the three data sets that go with it, will allow more meaningful comparisons of certain motion segmentation methods.