A dataset for complex activity recognition withmicro and macro activities in a cooking scenario

TL;DR

This paper introduces a new sensor-based dataset for complex activity recognition in cooking, capturing both macro (recipes) and micro (steps) activities with multiple sensing systems, facilitating advanced research.

Contribution

The paper presents a novel dataset with multi-sensor recordings labeled for both macro and micro activities in cooking, enabling detailed activity analysis and recognition.

Findings

Baseline classification results demonstrate the dataset's utility.

Multi-sensor data improves activity recognition accuracy.

Dataset supports development of advanced activity recognition methods.

Abstract

Complex activity recognition can benefit from understanding the steps that compose them. Current datasets, however, are annotated with one label only, hindering research in this direction. In this paper, we describe a new dataset for sensor-based activity recognition featuring macro and micro activities in a cooking scenario. Three sensing systems measured simultaneously, namely a motion capture system, tracking 25 points on the body; two smartphone accelerometers, one on the hip and the other one on the forearm; and two smartwatches one on each wrist. The dataset is labeled for both the recipes (macro activities) and the steps (micro activities). We summarize the results of a baseline classification using traditional activity recognition pipelines. The dataset is designed to be easily used to test and develop activity recognition approaches.