Key-Pose Prediction in Cyclic Human Motion

TL;DR

This paper presents a method for detecting key-poses in cyclic human motion, specifically in swimming, using poselet-based models and maximum likelihood estimation to improve detection accuracy and robustness.

Contribution

The paper introduces a novel approach combining poselet support poses with maximum likelihood modeling for key-pose prediction in cyclic motion.

Findings

High-precision key-pose detection achieved

Model robustness demonstrated across different support poses

Performance improved with additional camera views

Abstract

In this paper we study the problem of estimating innercyclic time intervals within repetitive motion sequences of top-class swimmers in a swimming channel. Interval limits are given by temporal occurrences of key-poses, i.e. distinctive postures of the body. A key-pose is defined by means of only one or two specific features of the complete posture. It is often difficult to detect such subtle features directly. We therefore propose the following method: Given that we observe the swimmer from the side, we build a pictorial structure of poselets to robustly identify random support poses within the regular motion of a swimmer. We formulate a maximum likelihood model which predicts a key-pose given the occurrences of multiple support poses within one stroke. The maximum likelihood can be extended with prior knowledge about the temporal location of a key-pose in order to improve the prediction recall. We experimentally show that our models reliably and robustly detect key-poses with a high precision and that their performance can be improved by extending the framework with additional camera views.