On Evaluating Metrics For Video Segmentation Algorithms
Evaluation is a central issue in the design, implementation, and performance assessment of all systems. Recently, a number of metrics have been proposed to assess the performance of segmentation algorithms for image and video data. This paper provides an overview of state of the art metrics proposed so-far, and introduces a new and efficient such metric. Doing so, subjective experiments are carried out to derive a perceptual metric. As a result, it also provides a comparison of performance of segmentation assessment metrics for different video object segmentation techniques.