HMM-based Activity Recognition with a Ceiling RGB-D Camera

Automated recognition of Activities of Daily Living allows to identify possible health problems and apply corrective strategies in Ambient Assisted Living (AAL). Activities of Daily Living analysis can provide very useful information for elder care and long-term care services. This paper presents an automated RGB-D video analysis system that recognises human ADLs activities, related to classical daily actions. The main goal is to predict the probability of an analysed subject action. Thus, the abnormal behaviour can be detected. The activity detection and recognition is performed using an affordable RGB-D camera. Human activities, despite their unstructured nature, tend to have a natural hierarchical structure; for instance, generally making a coffee involves a three-step process of turning on the coffee machine, putting sugar in cup and opening the fridge for milk. Action sequence recognition is then handled using a discriminative Hidden Markov Model (HMM). RADiaL, a dataset with RGB-D images and 3D position of each person for training as well as evaluating the HMM, has been built and made publicly available.

• Publication year

  2017

• Venue

  International Conference on Pattern Recognition Applications and Methods

• Publication date

  2017-02-24

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.5220/0006202305670574
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning Temporal Context for Activity Recognition

  2016cited by this paper
• Robust and affordable retail customer profiling by vision and radio beacon sensor fusion

  2016cited by this paper
• Human activity analysis for in-home fall risk assessment

  2015cited by this paper
• A Continuous Learning Framework for Activity Recognition Using Deep Hybrid Feature Models

  2015cited by this paper
• Applying a 3D qualitative trajectory calculus to human action recognition using depth cameras

  2015cited by this paper
• Shopper Analytics: A Customer Activity Recognition System Using a Distributed RGB-D Camera Network

  2014cited by this paper
• Human Activity Recognition for Domestic Robots

  2013cited by this paper
• Infinite Latent Conditional Random Fields for Modeling Environments through Humans

  2013cited by this paper
• Weakly Supervised Learning of Interactions between Humans and Objects

  2012cited by this paper
• Detecting activities of daily living in first-person camera views

  2012cited by this paper
• Max-Margin Early Event Detectors

  2012cited by this paper
• Learning human activities and object affordances from RGB-D videos

  2012cited by this paper
• Human activity prediction: Early recognition of ongoing activities from streaming videos

  2011cited by this paper
• Human Activity Detection from RGBD Images

  2011cited by this paper
• Action recognition from a distributed representation of pose and appearance

  2011cited by this paper
• Hierarchical Space-Time Model Enabling Efficient Search for Human Actions

  2009cited by this paper
• Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos

  2009cited by this paper
• Pattern mining for routine behaviour discovery in pervasive healthcare environments

  2008cited by this paper
• An Adaptive Sensor Mining Framework for Pervasive Computing Applications

  2008cited by this paper
• Recognizing human actions using multiple features

  2008cited by this paper
• A Scalable Approach to Activity Recognition based on Object Use

  2007cited by this paper
• [Methodological problems in clinical and epidemiological research on ageing].

  2005cited by this paper
• A Comparison of HMMs and Dynamic Bayesian Networks for Recognizing Office Activities

  2005cited by this paper
• Activity summarisation and fall detection in a supportive home environment

  2004cited by this paper
• Vision-Based Human Tracking and Activity Recognition

  2003cited by this paper
• A tutorial on hidden Markov models and selected applications in speech recognition

  1989cited by this paper
• An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process

  1972cited by this paper

• A review on the use of top-view surveillance videos for pedestrian detection, tracking and behavior recognition across public spaces.

  2025cites this paper
• A hybrid deep learning model for UWB radar-based human activity recognition

  2024cites this paper
• Using Convolutional Neural Networks with Multiple Thermal Sensors for Unobtrusive Pose Recognition

  2020cites this paper
• SARM: Salah Activities Recognition Model Based on Smartphone

  2019cites this paper
• Fusing Thermopile Infrared Sensor Data for Single Component Activity Recognition within a Smart Environment

  2019cites this paper
• Video Activity Recognition: State-of-the-Art

  2019cites this paper
• A Statistical and Deep Learning Approach for Human Activity Recognition

  2019cites this paper
• Human Activity Recognition Using Accelerometer, Gyroscope and Magnetometer Sensors: Deep Neural Network Approaches

  2019cites this paper
• Evidence theory‐based framework for improving automation in home automation system

  2018cites this paper
• People Detection and Tracking from an RGB-D Camera in Top-View Configuration: Review of Challenges and Applications

  2017cites this paper
• Entropy-based abnormal activity detection fusing RGB-D and domotic sensors

  2017cites this paper
• Modelling and Forecasting Customer Navigation in Intelligent Retail Environments

  2017cites this paper