A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments

Otto Brookes; Tilo Burghardt

A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments

Research output: Contribution to conference › Conference Paper › peer-review

80 Downloads (Pure)

Abstract

We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas (Gorilla gorilla gorilla) at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection- association and identity voting across short tracklets yields an improved robust performance at 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations.

Original language	English
Publication status	Published - 11 Jan 2021
Event	International Conference on Pattern Recognition (ICPR) Workshop on Visual Observation and Analysis of Vertebrate And Insect Behavior - Milan, Italy Duration: 10 Jan 2021 → 15 Jan 2021 Conference number: 25 https://www.micc.unifi.it/icpr2020/

Conference

Conference	International Conference on Pattern Recognition (ICPR) Workshop on Visual Observation and Analysis of Vertebrate And Insect Behavior
Abbreviated title	VAIB
Country/Territory	Italy
City	Milan
Period	10/01/21 → 15/01/21
Internet address	https://www.micc.unifi.it/icpr2020/

Access to Document

Full-text PDF (author’s accepted manuscript)Accepted author manuscript, 2.14 MB

Handle.net

Persistent link

Cite this

@conference{5d40fa341c2e4ab3b0631eb4af1ee776,

title = "A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments",

abstract = "We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas (Gorilla gorilla gorilla) at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection- association and identity voting across short tracklets yields an improved robust performance at 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations.",

author = "Otto Brookes and Tilo Burghardt",

year = "2021",

month = jan,

day = "11",

language = "English",

note = " International Conference on Pattern Recognition (ICPR) Workshop on Visual Observation and Analysis of Vertebrate And Insect Behavior , VAIB ; Conference date: 10-01-2021 Through 15-01-2021",

url = "https://www.micc.unifi.it/icpr2020/",

}

A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments. / Brookes, Otto ; Burghardt, Tilo.
2021. Paper presented at International Conference on Pattern Recognition (ICPR) Workshop on Visual Observation and Analysis of Vertebrate And Insect Behavior , Milan, Italy.

Research output: Contribution to conference › Conference Paper › peer-review

TY - CONF

T1 - A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments

AU - Brookes, Otto

AU - Burghardt, Tilo

N1 - Conference code: 25

PY - 2021/1/11

Y1 - 2021/1/11

N2 - We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas (Gorilla gorilla gorilla) at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection- association and identity voting across short tracklets yields an improved robust performance at 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations.

AB - We put forward a video dataset with 5k+ facial bounding box annotations across a troop of 7 western lowland gorillas (Gorilla gorilla gorilla) at Bristol Zoo Gardens. Training on this dataset, we implement and evaluate a standard deep learning pipeline on the task of facially recognising individual gorillas in a zoo environment. We show that a basic YOLOv3-powered application is able to perform identifications at 92% mAP when utilising single frames only. Tracking-by-detection- association and identity voting across short tracklets yields an improved robust performance at 97% mAP. To facilitate easy utilisation for enriching the research capabilities of zoo environments, we publish the code, video dataset, weights, and ground-truth annotations.

UR - https://arxiv.org/abs/2012.04689

M3 - Conference Paper

T2 - International Conference on Pattern Recognition (ICPR) Workshop on Visual Observation and Analysis of Vertebrate And Insect Behavior

Y2 - 10 January 2021 through 15 January 2021

ER -

A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments

Abstract

Conference

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this