Feature Set Selection and Optimal Classifier for Human Activity Recognition

Lösch, Martin; Schmidt-Rohr, Sven R.; Knoop, Steffen; Vacek, Stefan; Dillmann, Rüdiger

doi:10.1109/roman.2007.4415232

Cited by 24 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But in contrast to the work in [2,3,4,5,6,7] our approach assumes data being measured at one point of the body. Our IMU is worn on the belt, close to the centre of gravity of the human body.…”

Section: Approachmentioning

confidence: 99%

Bayesian recognition of motion related activities with inertial sensors

Frank

Nadales

Robertson

et al. 2010

Proceedings of the 12th ACM International Conference Adjunct Papers on Ubiquitous Computing - Adjunct

View full text Add to dashboard Cite

This work presents the design and evaluation of an activity recognition system for seven important motion related activities. The only sensor used is an Inertial Measurement Unit (IMU) worn on the belt. For classification, we applied Bayesian techniques, based on relevant features of the IMU raw data which are calculated in real time. Based on a complete labelled data set, i.e. supervised by an observing human judge, a K2 learning algorithm by Cooper and Herskovits was used to construct the Bayesian Network (BN) of the features. Our comparison of dynamic and static inference algorithms, based on the evaluation of the labelled data sets recorded from 16 male and female subjects show that a Hidden Markov Model (HMM) based on a learnt BN provides the best results.

show abstract

Section: Approachmentioning

confidence: 99%

Bayesian recognition of motion related activities with inertial sensors

Frank

Nadales

Robertson

et al. 2010

Proceedings of the 12th ACM International Conference Adjunct Papers on Ubiquitous Computing - Adjunct

View full text Add to dashboard Cite

show abstract

“…After automatic selection of relevant features, e.g. joint velocities, joint angles or relative positions of body parts, a support vector machine can be trained on the feature space and then be used for activity classification during runtime [3]. For RAD.Action, the recognizable activities have to match robot execution skills in the world domain, while for HID.BodyConfiguration the same activities can be recognized by the robot using exactly the same process for state classification during autonomous mission execution.…”

Section: A Observation Setupmentioning

confidence: 99%

Learning flexible, multi-modal human-robot interaction by observing human-human-interaction

Schmidt-Rohr

Lösch

Dillmann

2010

19th International Symposium in Robot and Human Interactive Communication

View full text Add to dashboard Cite

This paper presents a technique to learn flexible action selection in autonomous, multi-modal human-robot interaction (HRI) from observing multi-modal human-human interaction (HHI). A model is generated using the proposed technique with symbolic states and actions, representing the scope of the observed mission. Variations in human behavior can be learned as stochastic action effects while execution time perception noise is taken into account, using likelihood models. During execution, the model is used for dynamic action selection in HRI situations. The model as well as the evaluation system integrate the interaction elements of spoken dialog, human body configuration and exchanged objects. The technique is evaluated on a multi-modal service robot which is both able to observe the demonstration of two humans as well as execute the generated mission autonomously.

show abstract

“…Relevance criteria select features of the body model configuration which are used to label symbolic human activities [16]. Each likely activity is labeled with a certain probability, thus this skill delivers a set of discrete probabilities over known symbolic activities: p(act 1 ), ..., p(act n ) On the action side, speech synthesis enables robot utterances and arm-hand movements enable robot gestures.…”

Section: A Skillsmentioning

confidence: 99%

Programming by demonstration of probabilistic decision making on a multi-modal service robot

Schmidt-Rohr¹,

Lösch²,

Jäkel³

et al. 2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

In this paper we propose a process which is able to generate abstract service robot mission representations, utilized during execution for autonomous, probabilistic decision making, by observing human demonstrations. The observation process is based on the same perceptive components as used by the robot during execution, recording dialog between humans, human motion as well as objects poses. This leads to a natural, practical learning process, avoiding extra demonstration centers or kinesthetic teaching. By generating mission models for probabilistic decision making as Partially observable Markov decision processes, the robot is able to deal with uncertain and dynamic environments, as encountered in real world settings during execution. Service robot missions in a cafeteria setting, including the modalities of mobility, natural human-robot interaction and object grasping, have been learned and executed by this system.

show abstract

Feature Set Selection and Optimal Classifier for Human Activity Recognition

Cited by 24 publications

References 10 publications

Bayesian recognition of motion related activities with inertial sensors

Bayesian recognition of motion related activities with inertial sensors

Learning flexible, multi-modal human-robot interaction by observing human-human-interaction

Programming by demonstration of probabilistic decision making on a multi-modal service robot

Contact Info

Product

Resources

About