Performance metrics for activity recognition

TLDR

The article introduces and evaluates comprehensive performance metrics and visualisations for continuous activity recognition. The authors develop frame‑based visualisations with class‑skew invariant metrics and a complete set of event‑based metrics, then compare them to standard metrics on three published experiments. The study finds that standard metrics miss artefacts such as fragmentation, merging, and timing offsets, whereas the proposed metrics yield clear, unambiguous performance explanations.

Abstract

In this article, we introduce and evaluate a comprehensive set of performance metrics and visualisations for continuous activity recognition (AR). We demonstrate how standard evaluation methods, often borrowed from related pattern recognition problems, fail to capture common artefacts found in continuous AR—specifically event fragmentation, event merging and timing offsets. We support our assertion with an analysis on a set of recently published AR papers. Building on an earlier initial work on the topic, we develop a frame-based visualisation and corresponding set of class-skew invariant metrics for the one class versus all evaluation. These are complemented by a new complete set of event-based metrics that allow a quick graphical representation of system performance—showing events that are correct, inserted, deleted, fragmented, merged and those which are both fragmented and merged. We evaluate the utility of our approach through comparison with standard metrics on data from three different published experiments. This shows that where event- and frame-based precision and recall lead to an ambiguous interpretation of results in some cases, the proposed metrics provide a consistently unambiguous explanation.