Objective evaluation of video segmentation quality

TLDR

Video segmentation is essential for object‑based coding and description, yet evaluating its quality is necessary for algorithm selection and parameter tuning, and while subjective testing is costly, objective evaluation methods exist but have received less research attention. This paper addresses video segmentation quality evaluation by proposing methodologies and objective metrics for individual objects and entire segmentation partitions. The authors develop both stand‑alone and relative evaluation metrics to handle scenarios with or without a reference segmentation.

Abstract

Video segmentation assumes a major role in the context of object-based coding and description applications. Evaluating the adequacy of a segmentation result for a given application is a requisite both to allow the appropriate selection of segmentation algorithms as well as to adjust their parameters for optimal performance. Subjective testing, the current practice for the evaluation of video segmentation quality, is an expensive and time-consuming process. Objective segmentation quality evaluation techniques can alternatively be used; however, it is recognized that, so far, much less research effort has been devoted to this subject than to the development of segmentation algorithms. This paper discusses the problem of video segmentation quality evaluation, proposing evaluation methodologies and objective segmentation quality metrics for individual objects as well as for complete segmentation partitions. Both stand alone and relative evaluation metrics are developed to cover the cases for which a reference segmentation is missing or available for comparison.