Automatic cattle location tracking using image processing

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Behavioural scientists track animal behaviour patterns through the construction of ethograms which detail the activities of cattle over time. To achieve this, scientists currently view video footage from multiple cameras located in and around a pen, which houses the animals, to extract their location and determine their activity. This is a time consuming, laborious task, which could be automated. In this paper we extend the well-known Real-Time Compressive Tracking algorithm to automatically determine the location of dairy and beef cows from multiple video cameras in the pen. Several optimisations are introduced to improve algorithm accuracy. An automatic approach for updating the bounding box which discourages the algorithm from learning the background is presented. We also dynamically weight the location estimates from multiple cameras using boosting to avoid errors introduced by occlusion and by the tracked animal moving in and out of the field of view.

Conference

Conference23rd European Signal Processing Conference, 2015 (EUSIPCO 2015)
Abbreviated titleEUSIPCO 2015
CountryFrance
CityNice
Period31/08/154/09/15

Fingerprint

Animals
Image processing
Cameras
Light pens
Beef
Dairies
Video cameras

Keywords

  • location tracking
  • image processing
  • animal behaviour patterns
  • animal tracking

Cite this

Dao, T-K., Le, T-L., Harle, D., Murray, P., Tachtatzis, C., Marshall, S., ... Andonovic, I. (2015). Automatic cattle location tracking using image processing. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.
Dao, Trung-Kien ; Le, Thi-Lan ; Harle, David ; Murray, Paul ; Tachtatzis, Christos ; Marshall, Stephen ; Michie, Craig ; Andonovic, Ivan. / Automatic cattle location tracking using image processing. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.5 p.
@conference{bf1c493f79ee4996a2aa00b63240b510,
title = "Automatic cattle location tracking using image processing",
abstract = "Behavioural scientists track animal behaviour patterns through the construction of ethograms which detail the activities of cattle over time. To achieve this, scientists currently view video footage from multiple cameras located in and around a pen, which houses the animals, to extract their location and determine their activity. This is a time consuming, laborious task, which could be automated. In this paper we extend the well-known Real-Time Compressive Tracking algorithm to automatically determine the location of dairy and beef cows from multiple video cameras in the pen. Several optimisations are introduced to improve algorithm accuracy. An automatic approach for updating the bounding box which discourages the algorithm from learning the background is presented. We also dynamically weight the location estimates from multiple cameras using boosting to avoid errors introduced by occlusion and by the tracked animal moving in and out of the field of view.",
keywords = "location tracking, image processing, animal behaviour patterns, animal tracking",
author = "Trung-Kien Dao and Thi-Lan Le and David Harle and Paul Murray and Christos Tachtatzis and Stephen Marshall and Craig Michie and Ivan Andonovic",
note = "First published in the Proceedings of the 23rd European Signal Processing Conference (EUSIPCO-2015) in 2015, published by EURASIP.; 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), EUSIPCO 2015 ; Conference date: 31-08-2015 Through 04-09-2015",
year = "2015",
month = "8",
language = "English",

}

Dao, T-K, Le, T-L, Harle, D, Murray, P, Tachtatzis, C, Marshall, S, Michie, C & Andonovic, I 2015, 'Automatic cattle location tracking using image processing' Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France, 31/08/15 - 4/09/15, .

Automatic cattle location tracking using image processing. / Dao, Trung-Kien; Le, Thi-Lan; Harle, David; Murray, Paul; Tachtatzis, Christos; Marshall, Stephen; Michie, Craig; Andonovic, Ivan.

2015. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Automatic cattle location tracking using image processing

AU - Dao, Trung-Kien

AU - Le, Thi-Lan

AU - Harle, David

AU - Murray, Paul

AU - Tachtatzis, Christos

AU - Marshall, Stephen

AU - Michie, Craig

AU - Andonovic, Ivan

N1 - First published in the Proceedings of the 23rd European Signal Processing Conference (EUSIPCO-2015) in 2015, published by EURASIP.

PY - 2015/8

Y1 - 2015/8

N2 - Behavioural scientists track animal behaviour patterns through the construction of ethograms which detail the activities of cattle over time. To achieve this, scientists currently view video footage from multiple cameras located in and around a pen, which houses the animals, to extract their location and determine their activity. This is a time consuming, laborious task, which could be automated. In this paper we extend the well-known Real-Time Compressive Tracking algorithm to automatically determine the location of dairy and beef cows from multiple video cameras in the pen. Several optimisations are introduced to improve algorithm accuracy. An automatic approach for updating the bounding box which discourages the algorithm from learning the background is presented. We also dynamically weight the location estimates from multiple cameras using boosting to avoid errors introduced by occlusion and by the tracked animal moving in and out of the field of view.

AB - Behavioural scientists track animal behaviour patterns through the construction of ethograms which detail the activities of cattle over time. To achieve this, scientists currently view video footage from multiple cameras located in and around a pen, which houses the animals, to extract their location and determine their activity. This is a time consuming, laborious task, which could be automated. In this paper we extend the well-known Real-Time Compressive Tracking algorithm to automatically determine the location of dairy and beef cows from multiple video cameras in the pen. Several optimisations are introduced to improve algorithm accuracy. An automatic approach for updating the bounding box which discourages the algorithm from learning the background is presented. We also dynamically weight the location estimates from multiple cameras using boosting to avoid errors introduced by occlusion and by the tracked animal moving in and out of the field of view.

KW - location tracking

KW - image processing

KW - animal behaviour patterns

KW - animal tracking

UR - http://www.eusipco2015.org/

UR - http://www.eurasip.org/

M3 - Paper

ER -

Dao T-K, Le T-L, Harle D, Murray P, Tachtatzis C, Marshall S et al. Automatic cattle location tracking using image processing. 2015. Paper presented at 23rd European Signal Processing Conference, 2015 (EUSIPCO 2015), Nice, France.