Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference

Will  Andrew; Colin Greatwood; Tilo Burghardt

doi:10.1109/IROS40897.2019.8968555

Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference

Will Andrew, Colin Greatwood, Tilo Burghardt

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

45 Citations (Scopus)

366 Downloads (Pure)

Abstract

This paper describes a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation. The system is able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. We propose an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft:
(1) a YOLOv2-based species detector,
(2) a dual-stream deep network delivering exploratory agency, and
(3) an InceptionV3-based biometric long-term recurrent convolutional network for individual animal identification.
We evaluate the performance of each of the components offline, and also online via real-world field tests comprising 147 minutes of autonomous low altitude flight in a farm environment over a dispersed herd of 17 heifer dairy cows. We report error free identification performance on this online experiment. The presented proof-of-concept system is the first of its kind. It represents a practical step towards autonomous biometric identification of individual animals from the air in open pasture environments for tag-less AI support in farming and ecology.

Original language	English
Title of host publication	2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	7
ISBN (Electronic)	978-1-7281-4004-9
DOIs	https://doi.org/10.1109/IROS40897.2019.8968555
Publication status	Published - 27 Jan 2020
Event	IEEE/RSJ International Conference on Intelligent Robots and Systems - The Venetian Macao, Macau, China Duration: 3 Nov 2019 → 8 Nov 2019 https://www.iros2019.org

Publication series

Name	IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher	IEEE
ISSN (Electronic)	2153-0866

Conference

Conference	IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated title	iROS 2019
Country/Territory	China
City	Macau
Period	3/11/19 → 8/11/19
Internet address	https://www.iros2019.org

Access to Document

10.1109/IROS40897.2019.8968555

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/8968555. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 5.83 MB

Handle.net

Persistent link

Visual Biometric Processes for Collective Identification of Individual Friesian Cattle
Andrew, W. (Author), Burghardt, T. (Supervisor), Greatwood, C. (Supervisor) & Richards, A. (Supervisor), 7 May 2019
Student thesis: Doctoral Thesis › Doctor of Philosophy (PhD)

File

Dr Tilo Burghardt
- tb2935bristol.acuk
- School of Computer Science - Associate Professor of Computer Science
- Visual Information Laboratory
- Intelligent Systems Laboratory
Person: Academic , Member

Cite this

Andrew, W., Greatwood, C., & Burghardt, T. (2020). Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IROS40897.2019.8968555

Andrew, Will ; Greatwood, Colin ; Burghardt, Tilo. / Aerial Animal Biometrics : Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE), 2020. (IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)).

@inproceedings{6d9affad83ea4c548fa71eb833cf3116,

title = "Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference",

abstract = "This paper describes a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation. The system is able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. We propose an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft: (1) a YOLOv2-based species detector, (2) a dual-stream deep network delivering exploratory agency, and (3) an InceptionV3-based biometric long-term recurrent convolutional network for individual animal identification. We evaluate the performance of each of the components offline, and also online via real-world field tests comprising 147 minutes of autonomous low altitude flight in a farm environment over a dispersed herd of 17 heifer dairy cows. We report error free identification performance on this online experiment. The presented proof-of-concept system is the first of its kind. It represents a practical step towards autonomous biometric identification of individual animals from the air in open pasture environments for tag-less AI support in farming and ecology.",

author = "Will Andrew and Colin Greatwood and Tilo Burghardt",

year = "2020",

month = jan,

day = "27",

doi = "10.1109/IROS40897.2019.8968555",

language = "English",

series = "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

address = "United States",

note = "IEEE/RSJ International Conference on Intelligent Robots and Systems, iROS 2019 ; Conference date: 03-11-2019 Through 08-11-2019",

url = "https://www.iros2019.org",

}

Andrew, W, Greatwood, C & Burghardt, T 2020, Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference. in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Institute of Electrical and Electronics Engineers (IEEE), IEEE/RSJ International Conference on Intelligent Robots and Systems, Macau, China, 3/11/19. https://doi.org/10.1109/IROS40897.2019.8968555

Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference. / Andrew, Will ; Greatwood, Colin; Burghardt, Tilo.
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE), 2020. (IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Aerial Animal Biometrics

T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems

AU - Andrew, Will

AU - Greatwood, Colin

AU - Burghardt, Tilo

PY - 2020/1/27

Y1 - 2020/1/27

N2 - This paper describes a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation. The system is able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. We propose an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft: (1) a YOLOv2-based species detector, (2) a dual-stream deep network delivering exploratory agency, and (3) an InceptionV3-based biometric long-term recurrent convolutional network for individual animal identification. We evaluate the performance of each of the components offline, and also online via real-world field tests comprising 147 minutes of autonomous low altitude flight in a farm environment over a dispersed herd of 17 heifer dairy cows. We report error free identification performance on this online experiment. The presented proof-of-concept system is the first of its kind. It represents a practical step towards autonomous biometric identification of individual animals from the air in open pasture environments for tag-less AI support in farming and ecology.

AB - This paper describes a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation. The system is able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. We propose an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft: (1) a YOLOv2-based species detector, (2) a dual-stream deep network delivering exploratory agency, and (3) an InceptionV3-based biometric long-term recurrent convolutional network for individual animal identification. We evaluate the performance of each of the components offline, and also online via real-world field tests comprising 147 minutes of autonomous low altitude flight in a farm environment over a dispersed herd of 17 heifer dairy cows. We report error free identification performance on this online experiment. The presented proof-of-concept system is the first of its kind. It represents a practical step towards autonomous biometric identification of individual animals from the air in open pasture environments for tag-less AI support in farming and ecology.

U2 - 10.1109/IROS40897.2019.8968555

DO - 10.1109/IROS40897.2019.8968555

M3 - Conference Contribution (Conference Proceeding)

T3 - IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

BT - 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 3 November 2019 through 8 November 2019

ER -

Andrew W, Greatwood C, Burghardt T. Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Institute of Electrical and Electronics Engineers (IEEE). 2020. (IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)). doi: 10.1109/IROS40897.2019.8968555

Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Student theses

Visual Biometric Processes for Collective Identification of Individual Friesian Cattle

Profiles

Dr Tilo Burghardt

Cite this