Beef cattle instance segmentation using fully convolutional neural network

Aram Ter-Sarkisov; John Kelleher; Bernadette Earley; Michael Keane; Robert Ross

Beef cattle instance segmentation using fully convolutional neural network

Aram Ter-Sarkisov
, John Kelleher
, Bernadette Earley
, Michael Keane
, Robert Ross

School of Computer Science

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

Abstract

In this paper we present a novel instance segmentation algorithm that extends a fully convolutional network to learn to label objects separately without prediction of regions of interest. We trained the new algorithm on a challenging CCTV recording of beef cattle, as well as benchmark MS COCO and Pascal VOC datasets. Extensive experimentation showed that our approach outperforms the state-of-the-art solutions by up to 8% on our data.

Original language	English
Publication status	Published - 2019
Event	29th British Machine Vision Conference, BMVC 2018 - Newcastle, United Kingdom Duration: 3 Sep 2018 → 6 Sep 2018

Conference

Conference	29th British Machine Vision Conference, BMVC 2018
Country/Territory	United Kingdom
City	Newcastle
Period	3/09/18 → 6/09/18

Cite this

@conference{9b6ea1c844c34868b5e42fcad32ba4fe,

title = "Beef cattle instance segmentation using fully convolutional neural network",

abstract = "In this paper we present a novel instance segmentation algorithm that extends a fully convolutional network to learn to label objects separately without prediction of regions of interest. We trained the new algorithm on a challenging CCTV recording of beef cattle, as well as benchmark MS COCO and Pascal VOC datasets. Extensive experimentation showed that our approach outperforms the state-of-the-art solutions by up to 8\% on our data.",

author = "Aram Ter-Sarkisov and John Kelleher and Bernadette Earley and Michael Keane and Robert Ross",

note = "Publisher Copyright: {\textcopyright} 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.; 29th British Machine Vision Conference, BMVC 2018 ; Conference date: 03-09-2018 Through 06-09-2018",

year = "2019",

language = "English",

}

TY - CONF

T1 - Beef cattle instance segmentation using fully convolutional neural network

AU - Ter-Sarkisov, Aram

AU - Kelleher, John

AU - Earley, Bernadette

AU - Keane, Michael

AU - Ross, Robert

PY - 2019

Y1 - 2019

N2 - In this paper we present a novel instance segmentation algorithm that extends a fully convolutional network to learn to label objects separately without prediction of regions of interest. We trained the new algorithm on a challenging CCTV recording of beef cattle, as well as benchmark MS COCO and Pascal VOC datasets. Extensive experimentation showed that our approach outperforms the state-of-the-art solutions by up to 8% on our data.

AB - In this paper we present a novel instance segmentation algorithm that extends a fully convolutional network to learn to label objects separately without prediction of regions of interest. We trained the new algorithm on a challenging CCTV recording of beef cattle, as well as benchmark MS COCO and Pascal VOC datasets. Extensive experimentation showed that our approach outperforms the state-of-the-art solutions by up to 8% on our data.

UR - https://www.scopus.com/pages/publications/85084014895

M3 - Paper

AN - SCOPUS:85084014895

T2 - 29th British Machine Vision Conference, BMVC 2018

Y2 - 3 September 2018 through 6 September 2018

ER -

Beef cattle instance segmentation using fully convolutional neural network

Abstract

Conference

Fingerprint

Cite this