Shape-based segmentation of tomatoes for agriculture monitoring

Ujjwal Verma, Florence Rossant, Isabelle Bloch, Julien Orensanz, Denis Boisgontier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, we present a segmentation procedure based on a parametric active contour with shape constraint, in order to follow the growth of the tomatoes from the images acquired in the field. This is a challenging task because of the poor contrast in the images and the occlusions by the vegetation. In our sequential approach, considering one image per day, we assume that a segmentation of the tomatoes is available for the image acquired the previous day. An initial curve for the active contour model is computed by combining gradient information and region information. Then, an active contour with shape constraint is applied to provide an elliptic approximation of the tomato boundary. We performed a quantitative evaluation of our approach by comparing the results with the manual segmentation. Given the varying degree of occlusion in the images, the image data set was divided into three categories, based on the occlusion degree of the tomato in the processed image. For the cases with low occlusion, good results were obtained, with an average relative distance between the manual segmentation and the automatic segmentation of 2.73% (expressed as percentage of the size of tomato). For the images with significant amount of occlusion, a good segmentation was obtained on 44% of the images, where the average error was less than 10%.

Original languageEnglish
Title of host publicationICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods
PublisherSciTePress
Pages402-411
Number of pages10
ISBN (Print)9789897580185
Publication statusPublished - 2014
Event3rd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2014 - Angers, France
Duration: 06-03-201408-03-2014

Conference

Conference3rd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2014
CountryFrance
CityAngers
Period06-03-1408-03-14

Fingerprint

Agriculture
Monitoring

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Verma, U., Rossant, F., Bloch, I., Orensanz, J., & Boisgontier, D. (2014). Shape-based segmentation of tomatoes for agriculture monitoring. In ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods (pp. 402-411). SciTePress.
Verma, Ujjwal ; Rossant, Florence ; Bloch, Isabelle ; Orensanz, Julien ; Boisgontier, Denis. / Shape-based segmentation of tomatoes for agriculture monitoring. ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. SciTePress, 2014. pp. 402-411
@inproceedings{a8002495aeab4d7192809ec8e281635b,
title = "Shape-based segmentation of tomatoes for agriculture monitoring",
abstract = "In this paper, we present a segmentation procedure based on a parametric active contour with shape constraint, in order to follow the growth of the tomatoes from the images acquired in the field. This is a challenging task because of the poor contrast in the images and the occlusions by the vegetation. In our sequential approach, considering one image per day, we assume that a segmentation of the tomatoes is available for the image acquired the previous day. An initial curve for the active contour model is computed by combining gradient information and region information. Then, an active contour with shape constraint is applied to provide an elliptic approximation of the tomato boundary. We performed a quantitative evaluation of our approach by comparing the results with the manual segmentation. Given the varying degree of occlusion in the images, the image data set was divided into three categories, based on the occlusion degree of the tomato in the processed image. For the cases with low occlusion, good results were obtained, with an average relative distance between the manual segmentation and the automatic segmentation of 2.73{\%} (expressed as percentage of the size of tomato). For the images with significant amount of occlusion, a good segmentation was obtained on 44{\%} of the images, where the average error was less than 10{\%}.",
author = "Ujjwal Verma and Florence Rossant and Isabelle Bloch and Julien Orensanz and Denis Boisgontier",
year = "2014",
language = "English",
isbn = "9789897580185",
pages = "402--411",
booktitle = "ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",

}

Verma, U, Rossant, F, Bloch, I, Orensanz, J & Boisgontier, D 2014, Shape-based segmentation of tomatoes for agriculture monitoring. in ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. SciTePress, pp. 402-411, 3rd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2014, Angers, France, 06-03-14.

Shape-based segmentation of tomatoes for agriculture monitoring. / Verma, Ujjwal; Rossant, Florence; Bloch, Isabelle; Orensanz, Julien; Boisgontier, Denis.

ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. SciTePress, 2014. p. 402-411.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Shape-based segmentation of tomatoes for agriculture monitoring

AU - Verma, Ujjwal

AU - Rossant, Florence

AU - Bloch, Isabelle

AU - Orensanz, Julien

AU - Boisgontier, Denis

PY - 2014

Y1 - 2014

N2 - In this paper, we present a segmentation procedure based on a parametric active contour with shape constraint, in order to follow the growth of the tomatoes from the images acquired in the field. This is a challenging task because of the poor contrast in the images and the occlusions by the vegetation. In our sequential approach, considering one image per day, we assume that a segmentation of the tomatoes is available for the image acquired the previous day. An initial curve for the active contour model is computed by combining gradient information and region information. Then, an active contour with shape constraint is applied to provide an elliptic approximation of the tomato boundary. We performed a quantitative evaluation of our approach by comparing the results with the manual segmentation. Given the varying degree of occlusion in the images, the image data set was divided into three categories, based on the occlusion degree of the tomato in the processed image. For the cases with low occlusion, good results were obtained, with an average relative distance between the manual segmentation and the automatic segmentation of 2.73% (expressed as percentage of the size of tomato). For the images with significant amount of occlusion, a good segmentation was obtained on 44% of the images, where the average error was less than 10%.

AB - In this paper, we present a segmentation procedure based on a parametric active contour with shape constraint, in order to follow the growth of the tomatoes from the images acquired in the field. This is a challenging task because of the poor contrast in the images and the occlusions by the vegetation. In our sequential approach, considering one image per day, we assume that a segmentation of the tomatoes is available for the image acquired the previous day. An initial curve for the active contour model is computed by combining gradient information and region information. Then, an active contour with shape constraint is applied to provide an elliptic approximation of the tomato boundary. We performed a quantitative evaluation of our approach by comparing the results with the manual segmentation. Given the varying degree of occlusion in the images, the image data set was divided into three categories, based on the occlusion degree of the tomato in the processed image. For the cases with low occlusion, good results were obtained, with an average relative distance between the manual segmentation and the automatic segmentation of 2.73% (expressed as percentage of the size of tomato). For the images with significant amount of occlusion, a good segmentation was obtained on 44% of the images, where the average error was less than 10%.

UR - http://www.scopus.com/inward/record.url?scp=84902303163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902303163&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84902303163

SN - 9789897580185

SP - 402

EP - 411

BT - ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

PB - SciTePress

ER -

Verma U, Rossant F, Bloch I, Orensanz J, Boisgontier D. Shape-based segmentation of tomatoes for agriculture monitoring. In ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. SciTePress. 2014. p. 402-411