RGB-D Segmentation of Poultry Entrails

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

3 Citations (Scopus)
268 Downloads (Pure)

Abstract

This paper presents an approach for automatic visual inspection of chicken entrails in RGB-D data. The point cloud is first over-segmented into supervoxels based on color, spatial and geometric information. Color, position and texture features are extracted from each of the resulting supervoxels and passed to a Random Forest classifier, which classifies the supervoxels as either belonging to heart, lung, liver or misc. The dataset consists of 150 individual entrails, with 30 of these being reserved for evaluation. Segmentation performance is evaluated on a voxel-by-voxel basis, achieving an average Jaccard index of 61.5% across the four classes of organs. This is a 5.9% increase over the 58.1% achieved with features derived purely from 2D.
Original languageEnglish
Title of host publicationIX International Conference on Articulated Motion and Deformable Objects
PublisherSpringer
Publication date2016
Pages168-174
ISBN (Print)978-3-319-41778-3
DOIs
Publication statusPublished - 2016
EventIX Conference on Articulated Motion and Deformable Objects - Mallorca, Spain
Duration: 13 Jul 201615 Jul 2016
http://amdo2016.uib.es/

Conference

ConferenceIX Conference on Articulated Motion and Deformable Objects
CountrySpain
CityMallorca
Period13/07/201615/07/2016
Internet address
SeriesLecture Notes in Computer Science
Volume9756
ISSN0302-9743

Fingerprint

Poultry
Color
Liver
Classifiers
Textures
Inspection

Cite this

Philipsen, M. P., Jørgensen, A., Guerrero, S. E., & Moeslund, T. B. (2016). RGB-D Segmentation of Poultry Entrails. In IX International Conference on Articulated Motion and Deformable Objects (pp. 168-174). Springer. Lecture Notes in Computer Science, Vol.. 9756 https://doi.org/10.1007/978-3-319-41778-3_17
Philipsen, Mark Philip ; Jørgensen, Anders ; Guerrero, Sergio Escalera ; Moeslund, Thomas B. / RGB-D Segmentation of Poultry Entrails. IX International Conference on Articulated Motion and Deformable Objects. Springer, 2016. pp. 168-174 (Lecture Notes in Computer Science, Vol. 9756).
@inproceedings{5ee8749f56854958ace0fa91e91ab878,
title = "RGB-D Segmentation of Poultry Entrails",
abstract = "This paper presents an approach for automatic visual inspection of chicken entrails in RGB-D data. The point cloud is first over-segmented into supervoxels based on color, spatial and geometric information. Color, position and texture features are extracted from each of the resulting supervoxels and passed to a Random Forest classifier, which classifies the supervoxels as either belonging to heart, lung, liver or misc. The dataset consists of 150 individual entrails, with 30 of these being reserved for evaluation. Segmentation performance is evaluated on a voxel-by-voxel basis, achieving an average Jaccard index of 61.5{\%} across the four classes of organs. This is a 5.9{\%} increase over the 58.1{\%} achieved with features derived purely from 2D.",
author = "Philipsen, {Mark Philip} and Anders J{\o}rgensen and Guerrero, {Sergio Escalera} and Moeslund, {Thomas B.}",
year = "2016",
doi = "10.1007/978-3-319-41778-3_17",
language = "English",
isbn = "978-3-319-41778-3",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "168--174",
booktitle = "IX International Conference on Articulated Motion and Deformable Objects",
address = "Germany",

}

Philipsen, MP, Jørgensen, A, Guerrero, SE & Moeslund, TB 2016, RGB-D Segmentation of Poultry Entrails. in IX International Conference on Articulated Motion and Deformable Objects. Springer, Lecture Notes in Computer Science, vol. 9756, pp. 168-174, IX Conference on Articulated Motion and Deformable Objects, Mallorca, Spain, 13/07/2016. https://doi.org/10.1007/978-3-319-41778-3_17

RGB-D Segmentation of Poultry Entrails. / Philipsen, Mark Philip; Jørgensen, Anders; Guerrero, Sergio Escalera; Moeslund, Thomas B.

IX International Conference on Articulated Motion and Deformable Objects. Springer, 2016. p. 168-174 (Lecture Notes in Computer Science, Vol. 9756).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - RGB-D Segmentation of Poultry Entrails

AU - Philipsen, Mark Philip

AU - Jørgensen, Anders

AU - Guerrero, Sergio Escalera

AU - Moeslund, Thomas B.

PY - 2016

Y1 - 2016

N2 - This paper presents an approach for automatic visual inspection of chicken entrails in RGB-D data. The point cloud is first over-segmented into supervoxels based on color, spatial and geometric information. Color, position and texture features are extracted from each of the resulting supervoxels and passed to a Random Forest classifier, which classifies the supervoxels as either belonging to heart, lung, liver or misc. The dataset consists of 150 individual entrails, with 30 of these being reserved for evaluation. Segmentation performance is evaluated on a voxel-by-voxel basis, achieving an average Jaccard index of 61.5% across the four classes of organs. This is a 5.9% increase over the 58.1% achieved with features derived purely from 2D.

AB - This paper presents an approach for automatic visual inspection of chicken entrails in RGB-D data. The point cloud is first over-segmented into supervoxels based on color, spatial and geometric information. Color, position and texture features are extracted from each of the resulting supervoxels and passed to a Random Forest classifier, which classifies the supervoxels as either belonging to heart, lung, liver or misc. The dataset consists of 150 individual entrails, with 30 of these being reserved for evaluation. Segmentation performance is evaluated on a voxel-by-voxel basis, achieving an average Jaccard index of 61.5% across the four classes of organs. This is a 5.9% increase over the 58.1% achieved with features derived purely from 2D.

U2 - 10.1007/978-3-319-41778-3_17

DO - 10.1007/978-3-319-41778-3_17

M3 - Article in proceeding

SN - 978-3-319-41778-3

T3 - Lecture Notes in Computer Science

SP - 168

EP - 174

BT - IX International Conference on Articulated Motion and Deformable Objects

PB - Springer

ER -

Philipsen MP, Jørgensen A, Guerrero SE, Moeslund TB. RGB-D Segmentation of Poultry Entrails. In IX International Conference on Articulated Motion and Deformable Objects. Springer. 2016. p. 168-174. (Lecture Notes in Computer Science, Vol. 9756). https://doi.org/10.1007/978-3-319-41778-3_17