Efficient Unsupervised Temporal Segmentation of Motion Data

Abstract

Abstract-We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence. We use neighbourhood graphs for the partitioning and the similarity information in the graph is further exploited to cluster the motion primitives into larger entities of semantic significance. The method requires no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique to make the segmentation more robust to noise, as well as a notion of motion symmetry for more refined primitive detection. We test our method on several sensor modalities, including markered and markerless motion capture as well as on electromyograph and accelerometer recordings. The results highlight our system's capabilities for both segmentation and for analysis of the finer structures of motion data, all in a completely unsupervised manner.

A framework for evaluating motion segmentation algorithms

“…There are many more algorithms that adapt entirely different approaches, but also segment motion recordings in [23]- [27].…”

Enhancing Temporal Segmentation by Nonlocal Self-Similarity

“…Event segmentation is crucial not only to video understanding but also to video browsing, indexing and summarization. Additionally, the temporal segmentation of human motion into actions is central to the understanding and building of computational models of human motion and activity recognition [6,7]. Beside image data, time series segmentation is a core problem in data mining and machine learning with applications in several domains ranging from land cover changes tracking from remotely-sensed data [8,9] to health monitoring with wearable sensor data streams [10,11], to name but a few.…”

Accurate online alignment of human motor performances

“…However, numerous state-of-theart algorithms for movement analysis and synthesis were originally developed to work offline. Many of them require a temporal alignment of an input motion with a reference trajectory as preliminary step [Giese and Poggio 2000;Krüger et al 2017;Min and Chai 2012]. This alignment is frequently achieved via Dynamic Time Warping (DTW).…”