Automated Recognition of Social Behavior in Rats: The Role of Feature Quality

M.T. Lorbach; R.W. Poppe; Elsbeth van Dam; Lucas Noldus; R.C. Veltkamp

doi:10.1007/978-3-319-23234-8_52

Automated Recognition of Social Behavior in Rats: The Role of Feature Quality

M.T. Lorbach, R.W. Poppe, Elsbeth van Dam, Lucas Noldus, R.C. Veltkamp

Noldus Information Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We investigate how video-based recognition of rat social behavior is affected by the quality of the tracking data and the derived feature set. We look at the impact of two common tracking errors – animal misidentification and inaccurate localization of body parts. We further examine how the complexity of representing the articulated body in the features influences the recognition accuracy. Our analyses show that correct identification of the rats is required to accurately recognize their interactions. Precise localization of multiple body points is beneficial for recognizing interactions that are described by a distinct pose. Including pose features only leads to improvement if the tracking algorithm can provide that data reliably

Original language	English
Title of host publication	Image Analysis and Processing — ICIAP 2015
Subtitle of host publication	18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings
Publisher	Springer
Pages	565-574
Volume	2
ISBN (Electronic)	978-3-319-23234-8
ISBN (Print)	978-3-319-23233-1
DOIs	https://doi.org/10.1007/978-3-319-23234-8_52
Publication status	Published - 2015
Event	International Conference on Image Analysis and Processing (ICIAP 2015) - Genoa, Italy Duration: 7 Sept 2015 → 11 Sept 2015

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer International Publishing
Volume	9280
ISSN (Print)	0302-9743

Conference

Conference	International Conference on Image Analysis and Processing (ICIAP 2015)
Country/Territory	Italy
City	Genoa
Period	7/09/15 → 11/09/15

Keywords

Rat tracking
Rat behavior
Behavior classification
Social behavior
Action recognition
Tracking quality

Access to Document

10.1007/978-3-319-23234-8_52

poppeAccepted author manuscript, 1.09 MB

Cite this

Lorbach, M. T., Poppe, R. W., van Dam, E., Noldus, L., & Veltkamp, R. C. (2015). Automated Recognition of Social Behavior in Rats: The Role of Feature Quality. In Image Analysis and Processing — ICIAP 2015 : 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings (Vol. 2, pp. 565-574). (Lecture Notes in Computer Science ; Vol. 9280). Springer. https://doi.org/10.1007/978-3-319-23234-8_52

@inproceedings{ccafae9bae964fd4ab96c0754b44102e,

title = "Automated Recognition of Social Behavior in Rats: The Role of Feature Quality",

abstract = "We investigate how video-based recognition of rat social behavior is affected by the quality of the tracking data and the derived feature set. We look at the impact of two common tracking errors – animal misidentification and inaccurate localization of body parts. We further examine how the complexity of representing the articulated body in the features influences the recognition accuracy. Our analyses show that correct identification of the rats is required to accurately recognize their interactions. Precise localization of multiple body points is beneficial for recognizing interactions that are described by a distinct pose. Including pose features only leads to improvement if the tracking algorithm can provide that data reliably",

keywords = "Rat tracking, Rat behavior, Behavior classification, Social behavior, Action recognition, Tracking quality",

author = "M.T. Lorbach and R.W. Poppe and {van Dam}, Elsbeth and Lucas Noldus and R.C. Veltkamp",

year = "2015",

doi = "10.1007/978-3-319-23234-8_52",

language = "English",

isbn = "978-3-319-23233-1",

volume = "2",

series = "Lecture Notes in Computer Science ",

publisher = "Springer",

pages = "565--574",

booktitle = "Image Analysis and Processing — ICIAP 2015",

note = "International Conference on Image Analysis and Processing (ICIAP 2015) ; Conference date: 07-09-2015 Through 11-09-2015",

}

Lorbach, MT, Poppe, RW, van Dam, E, Noldus, L & Veltkamp, RC 2015, Automated Recognition of Social Behavior in Rats: The Role of Feature Quality. in Image Analysis and Processing — ICIAP 2015 : 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings. vol. 2, Lecture Notes in Computer Science , vol. 9280, Springer, pp. 565-574, International Conference on Image Analysis and Processing (ICIAP 2015), Genoa, Italy, 7/09/15. https://doi.org/10.1007/978-3-319-23234-8_52

Automated Recognition of Social Behavior in Rats: The Role of Feature Quality. / Lorbach, M.T.; Poppe, R.W.; van Dam, Elsbeth et al.
Image Analysis and Processing — ICIAP 2015 : 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings. Vol. 2 Springer, 2015. p. 565-574 (Lecture Notes in Computer Science ; Vol. 9280).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Automated Recognition of Social Behavior in Rats: The Role of Feature Quality

AU - Lorbach, M.T.

AU - Poppe, R.W.

AU - van Dam, Elsbeth

AU - Noldus, Lucas

AU - Veltkamp, R.C.

PY - 2015

Y1 - 2015

N2 - We investigate how video-based recognition of rat social behavior is affected by the quality of the tracking data and the derived feature set. We look at the impact of two common tracking errors – animal misidentification and inaccurate localization of body parts. We further examine how the complexity of representing the articulated body in the features influences the recognition accuracy. Our analyses show that correct identification of the rats is required to accurately recognize their interactions. Precise localization of multiple body points is beneficial for recognizing interactions that are described by a distinct pose. Including pose features only leads to improvement if the tracking algorithm can provide that data reliably

AB - We investigate how video-based recognition of rat social behavior is affected by the quality of the tracking data and the derived feature set. We look at the impact of two common tracking errors – animal misidentification and inaccurate localization of body parts. We further examine how the complexity of representing the articulated body in the features influences the recognition accuracy. Our analyses show that correct identification of the rats is required to accurately recognize their interactions. Precise localization of multiple body points is beneficial for recognizing interactions that are described by a distinct pose. Including pose features only leads to improvement if the tracking algorithm can provide that data reliably

KW - Rat tracking

KW - Rat behavior

KW - Behavior classification

KW - Social behavior

KW - Action recognition

KW - Tracking quality

U2 - 10.1007/978-3-319-23234-8_52

DO - 10.1007/978-3-319-23234-8_52

M3 - Conference contribution

SN - 978-3-319-23233-1

VL - 2

T3 - Lecture Notes in Computer Science

SP - 565

EP - 574

BT - Image Analysis and Processing — ICIAP 2015

PB - Springer

T2 - International Conference on Image Analysis and Processing (ICIAP 2015)

Y2 - 7 September 2015 through 11 September 2015

ER -

Lorbach MT, Poppe RW, van Dam E, Noldus L, Veltkamp RC. Automated Recognition of Social Behavior in Rats: The Role of Feature Quality. In Image Analysis and Processing — ICIAP 2015 : 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings. Vol. 2. Springer. 2015. p. 565-574. (Lecture Notes in Computer Science ). doi: 10.1007/978-3-319-23234-8_52

Automated Recognition of Social Behavior in Rats: The Role of Feature Quality

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this