Dog's life: Wearable activity recognition for dogs

Cassim Ladha, Nils Hammerla, Emma Hughes, Patrick Olivier, Thomas Plötz

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Health and well-being of dogs, either domesticated pets or service animals, are major concerns that are taken seriously for ethical, emotional, and financial reasons. Welfare assessments in dogs rely on objective observations of both frequency and variability of individual behaviour traits, which is often difficult to obtain in a dog's everyday life. In this paper we have identified a set of activities, which are linked to behaviour traits that are relevant for a dog's wellbeing. We developed a collar-worn accelerometry platform that records dog behaviours in naturalistic environments. A statistical classification framework is used for recognising dog activities. In an experimental evaluation we analysed the naturalistic behaviour of 18 dogs and were able to recognise a total of 17 different activities with approximately 70% classification accuracy. The presented system is the first of its kind that allows for robust and detailed analysis of dog activities in naturalistic environments.

Original languageEnglish
Title of host publicationUbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Pages415-418
Number of pages4
DOIs
Publication statusPublished - 15 Oct 2013
EventUbiquitous Computing 2013 - Zurich, Switzerland
Duration: 8 Sep 201312 Sep 2013

Conference

ConferenceUbiquitous Computing 2013
Abbreviated titleUbiComp 2013
CountrySwitzerland
CityZurich
Period8/09/1312/09/13

Keywords

  • Activity recognition
  • Animal wellbeing
  • Dog
  • Wearable computing

Cite this

Ladha, C., Hammerla, N., Hughes, E., Olivier, P., & Plötz, T. (2013). Dog's life: Wearable activity recognition for dogs. In UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 415-418) https://doi.org/10.1145/2493432.2493519
Ladha, Cassim ; Hammerla, Nils ; Hughes, Emma ; Olivier, Patrick ; Plötz, Thomas. / Dog's life : Wearable activity recognition for dogs. UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2013. pp. 415-418
@inproceedings{1716ea98fdc44d5d86ec774a5bffc480,
title = "Dog's life: Wearable activity recognition for dogs",
abstract = "Health and well-being of dogs, either domesticated pets or service animals, are major concerns that are taken seriously for ethical, emotional, and financial reasons. Welfare assessments in dogs rely on objective observations of both frequency and variability of individual behaviour traits, which is often difficult to obtain in a dog's everyday life. In this paper we have identified a set of activities, which are linked to behaviour traits that are relevant for a dog's wellbeing. We developed a collar-worn accelerometry platform that records dog behaviours in naturalistic environments. A statistical classification framework is used for recognising dog activities. In an experimental evaluation we analysed the naturalistic behaviour of 18 dogs and were able to recognise a total of 17 different activities with approximately 70{\%} classification accuracy. The presented system is the first of its kind that allows for robust and detailed analysis of dog activities in naturalistic environments.",
keywords = "Activity recognition, Animal wellbeing, Dog, Wearable computing",
author = "Cassim Ladha and Nils Hammerla and Emma Hughes and Patrick Olivier and Thomas Pl{\"o}tz",
year = "2013",
month = "10",
day = "15",
doi = "10.1145/2493432.2493519",
language = "English",
isbn = "9781450317702",
pages = "415--418",
booktitle = "UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing",

}

Ladha, C, Hammerla, N, Hughes, E, Olivier, P & Plötz, T 2013, Dog's life: Wearable activity recognition for dogs. in UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. pp. 415-418, Ubiquitous Computing 2013, Zurich, Switzerland, 8/09/13. https://doi.org/10.1145/2493432.2493519

Dog's life : Wearable activity recognition for dogs. / Ladha, Cassim; Hammerla, Nils; Hughes, Emma; Olivier, Patrick; Plötz, Thomas.

UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2013. p. 415-418.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Dog's life

T2 - Wearable activity recognition for dogs

AU - Ladha, Cassim

AU - Hammerla, Nils

AU - Hughes, Emma

AU - Olivier, Patrick

AU - Plötz, Thomas

PY - 2013/10/15

Y1 - 2013/10/15

N2 - Health and well-being of dogs, either domesticated pets or service animals, are major concerns that are taken seriously for ethical, emotional, and financial reasons. Welfare assessments in dogs rely on objective observations of both frequency and variability of individual behaviour traits, which is often difficult to obtain in a dog's everyday life. In this paper we have identified a set of activities, which are linked to behaviour traits that are relevant for a dog's wellbeing. We developed a collar-worn accelerometry platform that records dog behaviours in naturalistic environments. A statistical classification framework is used for recognising dog activities. In an experimental evaluation we analysed the naturalistic behaviour of 18 dogs and were able to recognise a total of 17 different activities with approximately 70% classification accuracy. The presented system is the first of its kind that allows for robust and detailed analysis of dog activities in naturalistic environments.

AB - Health and well-being of dogs, either domesticated pets or service animals, are major concerns that are taken seriously for ethical, emotional, and financial reasons. Welfare assessments in dogs rely on objective observations of both frequency and variability of individual behaviour traits, which is often difficult to obtain in a dog's everyday life. In this paper we have identified a set of activities, which are linked to behaviour traits that are relevant for a dog's wellbeing. We developed a collar-worn accelerometry platform that records dog behaviours in naturalistic environments. A statistical classification framework is used for recognising dog activities. In an experimental evaluation we analysed the naturalistic behaviour of 18 dogs and were able to recognise a total of 17 different activities with approximately 70% classification accuracy. The presented system is the first of its kind that allows for robust and detailed analysis of dog activities in naturalistic environments.

KW - Activity recognition

KW - Animal wellbeing

KW - Dog

KW - Wearable computing

UR - http://www.scopus.com/inward/record.url?scp=84885201896&partnerID=8YFLogxK

U2 - 10.1145/2493432.2493519

DO - 10.1145/2493432.2493519

M3 - Conference Paper

SN - 9781450317702

SP - 415

EP - 418

BT - UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing

ER -

Ladha C, Hammerla N, Hughes E, Olivier P, Plötz T. Dog's life: Wearable activity recognition for dogs. In UbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2013. p. 415-418 https://doi.org/10.1145/2493432.2493519