Unsupervised daily routine modelling from a depth sensor using top-down and bottom-up hierarchies

Xu, Yangdi; Bull, David; Damen, Dima

doi:10.1109/acpr.2015.7486465

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They allow us to accumulate statistics about speed of motion and hence to infer important clinical measurements in the wild. Some example studies that we have carried out so far are recognising actions [21], and quality and intensity of movement [22], and identifying typical indoor activities of daily living and routine modeling [26], amongst others. To overcome the unreliability of skeleton data, provided by the OpenNI tracker, for non-frontal views we have designed a new depth based pose estimation system that can support a large range of views [10].…”

Section: Sphere Vision Based Applicationsmentioning

confidence: 99%

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Hall

Hannuna

Camplani

et al. 2016

2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)

View full text Add to dashboard Cite

Section: Sphere Vision Based Applicationsmentioning

confidence: 99%

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Hall

Hannuna

Camplani

et al. 2016

2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)

View full text Add to dashboard Cite

Enhancing Kitchen Activity Recognition: A Benchmark Study of the Rostock KTA Dataset

Zolfaghari,

Stoev,

Yordanova

2024

IEEE Access

View full text Add to dashboard Cite

With the global population aging, the demand for technologies facilitating independent living, especially for those with cognitive impairments, is increasing. This paper addresses this need by conducting a comprehensive evaluation of the Rostock Kitchen Task Assessment dataset, a pivotal resource in kitchen task activity recognition. Our study begins with an in-depth introduction, emphasizing the increasing prevalence of neurodegenerative disorders and the crucial role of assistive technologies. Our contributions encompass a systematic literature review, design and implementation of a working prototype of our envisioned system, refinement of the Rostock Kitchen Task Assessment dataset, creation of a semantically annotated dataset, extraction of statistical features, comparative analysis, and rigorous model performance assessment. The core of our work is the thorough evaluation and benchmarking of different activity recognition approaches using the aforementioned Rostock Kitchen Task Assessment dataset. Our experimental results demonstrate that despite encountering an imbalance problem in the dataset, the fusion of the Hidden Markov Model and Random Forest leads to superior results, achieving a weightedaveraged F 1 -score of 74.10% for all available activities and 81.40% for the most common actions in the Rostock Kitchen Task Assessment dataset. Moreover, through systematic analysis, we identify strengths and suggest potential refinements, thereby advancing the field of kitchen activity recognition. This offers valuable insights for researchers and practitioners in assistive and remote care technologies.

show abstract

Unsupervised Long-Term Routine Modelling Using Dynamic Bayesian Networks

Bull

Damen

2017

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

Self Cite

View full text Add to dashboard Cite

Routine can be defined as the frequent and regular activity patterns over a specified timescale (e.g. daily/weekly routine). In this work, we capture routine patterns for a single person from long-term visual data using a Dynamic Bayesian Network (DBN). Assuming a person always performs purposeful activities at corresponding locations; spatial, pose and time-of-day information are used as sources of input for routine modelling. We assess variations of the independence assumptions within the DBN model among selected features. Unlike traditional models that are supervisedly trained, we automatically select the number of hidden states for fully unsupervised discovery of a single person's indoor routine. We emphasize unsupervised learning as it is practically unrealistic to obtain ground-truth labels for long term behaviours. The datasets used in this work are long term recordings of non-scripted activities in their native environments, each lasting for six days. The first captures the routine of three individuals in an office kitchen; the second is recorded in a residential kitchen. We evaluate the routine by comparing to ground-truth when present, using exhaustive search to relate discovered patterns to ground-truth ones. We also propose a graphical visualisation to represent and qualitatively evaluate the discovered routine.

show abstract

Unsupervised daily routine modelling from a depth sensor using top-down and bottom-up hierarchies

Cited by 3 publications

References 14 publications

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Designing a Video Monitoring System for AAL applications: the SPHERE Case Study

Enhancing Kitchen Activity Recognition: A Benchmark Study of the Rostock KTA Dataset

Unsupervised Long-Term Routine Modelling Using Dynamic Bayesian Networks

Contact Info

Product

Resources

About