Detecting Human Behavior Models From Multimodal Observation in a Smart Home

Brdiczka, Oliver; Langet, Matthieu; Maisonnasse, Jérôme; Crowley, James L.

doi:10.1109/tase.2008.2004965

Cited by 110 publications

(39 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Context "is the key for interaction without distraction" [25,26]. Brdiczka et al [26] stated that "context describes features of the environment" where the activity takes place. The role of a context-aware house is that the system builds and stores a model describing the environments and the occupants' activities and behaviour.…”

Section: Context Awarenessmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

Sánchez

Pfeiffer

Skeie

2017

JSAN

View full text Add to dashboard Cite

Smart Houses are a prominent field of research referring to environments adapted to assist people in their everyday life. Older people and people with disabilities would benefit the most from the use of Smart Houses because they provide the opportunity for them to stay in their home for as long as possible. In this review, the developments achieved in the field of Smart Houses for the last 16 years are described. The concept of Smart Houses, the most used analysis methods, and current challenges in Smart Houses are presented. A brief introduction of the analysis methods is given, and their implementation is also reported.

show abstract

Section: Context Awarenessmentioning

confidence: 99%

“…Brdiczka et al [26] implemented the concept of context awareness to model human behaviour. Cameras and audio sensors were used to collect data and then Markov models were used to learn the user's behaviour.…”

Section: Markov Modelmentioning

confidence: 99%

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

Sánchez

Pfeiffer

Skeie

2017

JSAN

View full text Add to dashboard Cite

show abstract

“…A naive 3D human representation approach is based on the human centroid trajectory in 3D space [10]. Although this representation provides a compact description of humans in a large space, it cannot be used to represent fine-grained human behaviors with limb motions.…”

Section: A Human Representation In 3d Spacementioning

confidence: 99%

Adaptive human-centered representation for activity recognition of multiple individuals from 3D point cloud sequences

Zhang

Reardon

Zhang

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-Activity recognition of multi-individuals (ARMI) within a group, which is essential to practical human-centered robotics applications such as childhood education, is a particularly challenging and previously not well studied problem. We present a novel adaptive human-centered (AdHuC) representation based on local spatio-temporal features (LST) to address ARMI in a sequence of 3D point clouds. Our human-centered detector constructs affiliation regions to associate LST features with humans by mining depth data and using a cascade of rejectors to localize humans in 3D space. Then, features are detected within each affiliation region, which avoids extracting irrelevant features from dynamic background clutter and addresses moving cameras on mobile robots. Our feature descriptor is able to adapt its support region to linear perspective view variations and encode multi-channel information (i.e., color and depth) to construct the final representation. Empirical studies validate that the AdHuC representation obtains promising performance on ARMI using an Meka humanoid robot to play multi-people Simon Says games. Experiments on benchmark datasets further demonstrate that our adaptive human-centered representation outperforms previous approaches for activity recognition from color-depth data.

show abstract

“…A simple technique is to apply a 3D centroid trajectory as features to identify human activities in 3D visual data, in which a human is represented as a point that indicates the 3D location of the human in the visual data [3]. In general, the feature of centroid trajectory is suitable for representing a human that occupies a small region in an image.…”

Section: Related Workmentioning

confidence: 99%

4-dimensional local spatio-temporal features for human activity recognition

Zhang

Parker

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Recognizing human activities from common color image sequences faces many challenges, such as complex backgrounds, camera motion, and illumination changes. In this paper, we propose a new 4-dimensional (4D) local spatio-temporal feature that combines both intensity and depth information. The feature detector applies separate filters along the 3D spatial dimensions and the 1D temporal dimension to detect a feature point. The feature descriptor then computes and concatenates the intensity and depth gradients within a 4D hyper cuboid, which is centered at the detected feature point, as a feature. For recognizing human activities, Latent Dirichlet Allocation with Gibbs sampling is used as the classifier. Experiments are performed on a newly created database that contains six human activities, each with 33 samples with complex variations. Experimental results demonstrate the promising performance of the proposed features for the task of human activity recognition.

show abstract

Detecting Human Behavior Models From Multimodal Observation in a Smart Home

Cited by 110 publications

References 20 publications

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

Adaptive human-centered representation for activity recognition of multiple individuals from 3D point cloud sequences

4-dimensional local spatio-temporal features for human activity recognition

Contact Info

Product

Resources

About