Group activity recognition using belief propagation for wearable devices

Gordon, Dawud; Scholz, Markus; Beigl, Michael

doi:10.1145/2634317.2634329

Cited by 12 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also DBAD reduces privacy concerns as data is only shared in an aggregated form (models). It is also a useful tool for supporting group activity recognition where the behavior of the group can be identified once the constituents are known [10]. Applications are also foreseen in emergency situations, where groups display affiliative behaviors and should be treated as a single unit [17].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Group affiliation detection using model divergence for wearable devices

Gordon¹,

Wirz

Roggen

et al. 2014

Proceedings of the 2014 ACM International Symposium on Wearable Computers

Self Cite

View full text Add to dashboard Cite

Methods for recognizing group affiliations using mobile devices have been proposed using centralized instances to aggregate and evaluate data. However centralized systems do not scale well and fail when the network is congested. We present a method for distributed, peer-to-peer (P2P) recognition of group affiliations in multi-group environments, using the divergence of mobile phone sensor data distributions as an indicator of similarity. The method assesses pairwise similarity between individuals using model parameters instead of sensor observations, and then interprets that information in a distributed manner. An experiment was conducted with 10 individuals in different group configurations to compare P2P and conventional centralized approaches. Although the output of the proposed method fluctuates, we can still correctly detect 93% of group affiliations by applying a filter. We foresee applications in mobile social networking, life logging, smart environments, crowd situations and possibly crowd emergencies.

show abstract

Section: Discussionmentioning

confidence: 99%

“…$15.00. http://dx.doi.org/10.1145/2634317.2634319 groups in some fashion [10]. Before an understanding of the group's context can be reached, group and individual affiliations must be identified through the precess of group affiliation detection (GAD).…”

Section: Introductionmentioning

confidence: 99%

Group affiliation detection using model divergence for wearable devices

Gordon¹,

Wirz

Roggen

et al. 2014

Proceedings of the 2014 ACM International Symposium on Wearable Computers

Self Cite

View full text Add to dashboard Cite

show abstract

“…the "multiple occupancy" problem within the smart home activity recognition domain [3]). The idea of recognising group activities using wearable sensors was recently explored in the doctoral thesis of Dawud Gordon [4]. Gordon showed that by sensing the physical movements of multiple individuals, the emergent behaviour of a group could be predicted (e.g.…”

mentioning

confidence: 99%

“…Gordon showed that by sensing the physical movements of multiple individuals, the emergent behaviour of a group could be predicted (e.g. certain team sports like football, or volleyball) [5].…”

mentioning

confidence: 99%

“…b) Inertial Sensing: Body-worn, inertial sensing is increasingly used as an alternative to vision and is primarily used to detect individual activities like walking, running, and various hand gestures (Bulling et al provide a good tutorial on the topic [10]). But beyond the work of Gordon, inertial sensing has not been well studied for group activies [4]. c) Sound interactions: The PhD thesis of Sumit Basu explored individual speaker detection in groups.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Detecting physical collaborations in a group task using body-worn microphones and accelerometers

Ward

Pirkl

Hevesi

et al. 2017

2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)

View full text Add to dashboard Cite

Abstract-This paper presents a method of using wearable accelerometers and microphones to detect instances of ad-hoc physical collaborations between members of a group. 4 people are instructed to construct a large video wall and must cooperate to complete the task. The task is loosely structured with minimal outside assistance to better reflect the ad-hoc nature of many real world construction scenarios. Audio data, recorded from chestworn microphones, is used to reveal information on collocation, i.e. whether or not participants are near one another. Movement data, recorded using 3-axis accelerometers worn on each person's head and wrists, is used to provide information on correlated movements, such as when participants help one another to lift a heavy object. Collocation and correlated movement information is then combined to determine who is working together at any given time. The work shows how data from commonly available sensors can be combined across multiple people using a simple, low power algorithm to detect a range of physical collaborations.

show abstract

A Correlation-based Real-time Segmentation Scheme for Multi-user Collaborative Activities

Kim

Lee

2022

2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)

View full text Add to dashboard Cite

Group activity recognition using belief propagation for wearable devices

Cited by 12 publications

References 18 publications

Group affiliation detection using model divergence for wearable devices

Group affiliation detection using model divergence for wearable devices

Detecting physical collaborations in a group task using body-worn microphones and accelerometers

A Correlation-based Real-time Segmentation Scheme for Multi-user Collaborative Activities

Contact Info

Product

Resources

About