A framework for evaluating motion segmentation algorithms

Abstract

There have been many proposals for algorithms segmenting human whole-body motion in the literature. However, the wide range of use cases, datasets, and quality measures that were used for the evaluation render the comparison of algorithms challenging. In this paper, we introduce a framework that puts motion segmentation algorithms on a unified testing ground and provides a possibility to allow comparing them. The testing ground features both a set of quality measures known from the literature and a novel approach tailored to the evaluation of motion segmentation algorithms, termed Integrated Kernel approach. Datasets of motion recordings, provided with a ground truth, are included as well. They are labelled in a new way, which hierarchically organises the ground truth, to cover different use cases that segmentation algorithms can possess. The framework and datasets are publicly available and are intended to represent a service for the community regarding the comparison and evaluation of existing and new motion segmentation algorithms.

Temporal Human Action Segmentation via Dynamic Clustering

“…Evaluation Metric. The performance of all algorithms are evaluated based on precision-recall values [3], in which the true positive is commonly defined based on a region matching without considering the labels [12,16].…”

Segmentation boundaries in accelerometer data of arm motion induced by music: Online computation and perceptual assessment

“…To that extent, it must be acknowledged firstly, that human perception of bodily movement is highly subjective (Bläsing, 2015;Kahol, Tripathi, & Panchanathan, 2004;Zacks, Kumar, Abrams, & Mehta, 2009) and is hierarchically structured such that short patterns are grouped into larger ones (Bernard, Dobermann, Vögele, Krüger, Kohlhammer, & Fellner, 2017;Dreher, Kulp, Mandery, Wächter, & Asfour, 2017;Krüger, Kragic, Ude, & Geib, 2007;Lin, Karg, & Kulić, 2016). Also, it must be taken into consideration that dance patterns may or may be not repetitive.…”