Spatiotemporal k-means

TL;DR

Spatiotemporal clustering of moving objects is addressed by STkM, which unifies space and time into a single objective to identify dynamic clusters whose identity remains static while their location and content change. The method enables tracking across multiple timescales with minimal parameter tuning and no post-processing. The paper provides a theoretical generating model for spatiotemporal data and proves STkM’s efficacy within that framework, followed by empirical validation on a collective animal behavior benchmark where it outperforms baselines in the low-data regime. It also demonstrates extensions to unsupervised region-of-interest detection and tracking in videos, highlighting practical applicability in data-scarce settings.

Abstract

Spatiotemporal data is increasingly available due to emerging sensor and data acquisition technologies that track moving objects. Spatiotemporal clustering addresses the need to efficiently discover patterns and trends in moving object behavior without human supervision. One application of interest is the discovery of moving clusters, where clusters have a static identity, but their location and content can change over time. We propose a two phase spatiotemporal clustering method called spatiotemporal k-means (STkM) that is able to analyze the multi-scale relationships within spatiotemporal data. By optimizing an objective function that is unified over space and time, the method can track dynamic clusters at both short and long timescales with minimal parameter tuning and no post-processing. We begin by proposing a theoretical generating model for spatiotemporal data and prove the efficacy of STkM in this setting. We then evaluate STkM on a recently developed collective animal behavior benchmark dataset and show that STkM outperforms baseline methods in the low-data limit, which is a critical regime of consideration in many emerging applications. Finally, we showcase how STkM can be extended to more complex machine learning tasks, particularly unsupervised region of interest detection and tracking in videos.