Registering Reconstructions of the Two Sides of Fruit Tree Rows

Pravakar Roy; Wenbo Dong; Volkan Isler

doi:10.1109/IROS.2018.8594167

Registering Reconstructions of the Two Sides of Fruit Tree Rows

Pravakar Roy, Wenbo Dong, Volkan Isler

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Scopus citations

Abstract

We consider the problem of building accurate three dimensional (3D)reconstructions of orchard rows. This problem arises in many applications including yield mapping and measuring traits (e.g. trunk diameters)for phenotyping. While 3D reconstructions of side views can be obtained using standard methods, merging the two side-views is difficult due to the lack of overlap between the two partial reconstructions. We present a novel method that utilizes global features to constrain the solution. Specifically, we use information from the silhouettes and the ground plane for alignment. The method is evaluated using multiple simulated and real datasets. For additional information and demonstration of experimental results please see https://www.youtube.com/watch?v=6mGMF2gFv4M.

Original language	English (US)
Title of host publication	2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7697-7702
Number of pages	6
ISBN (Electronic)	9781538680940
DOIs	https://doi.org/10.1109/IROS.2018.8594167
State	Published - Dec 27 2018
Event	2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018 - Madrid, Spain Duration: Oct 1 2018 → Oct 5 2018

Publication series

Name	IEEE International Conference on Intelligent Robots and Systems
ISSN (Print)	2153-0858
ISSN (Electronic)	2153-0866

Conference

Conference	2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018
Country/Territory	Spain
City	Madrid
Period	10/1/18 → 10/5/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Access

10.1109/IROS.2018.8594167

OpenUrl availability

Full text

Cite this

Roy, P., Dong, W., & Isler, V. (2018). Registering Reconstructions of the Two Sides of Fruit Tree Rows. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018 (pp. 7697-7702). Article 8594167 (IEEE International Conference on Intelligent Robots and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2018.8594167

Registering Reconstructions of the Two Sides of Fruit Tree Rows. / Roy, Pravakar; Dong, Wenbo; Isler, Volkan.
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 7697-7702 8594167 (IEEE International Conference on Intelligent Robots and Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Roy, P, Dong, W & Isler, V 2018, Registering Reconstructions of the Two Sides of Fruit Tree Rows. in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018., 8594167, IEEE International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers Inc., pp. 7697-7702, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018, Madrid, Spain, 10/1/18. https://doi.org/10.1109/IROS.2018.8594167

@inproceedings{f1002d527a104c7eba9ddeaac24fc79c,

title = "Registering Reconstructions of the Two Sides of Fruit Tree Rows",

abstract = "We consider the problem of building accurate three dimensional (3D)reconstructions of orchard rows. This problem arises in many applications including yield mapping and measuring traits (e.g. trunk diameters)for phenotyping. While 3D reconstructions of side views can be obtained using standard methods, merging the two side-views is difficult due to the lack of overlap between the two partial reconstructions. We present a novel method that utilizes global features to constrain the solution. Specifically, we use information from the silhouettes and the ground plane for alignment. The method is evaluated using multiple simulated and real datasets. For additional information and demonstration of experimental results please see https://www.youtube.com/watch?v=6mGMF2gFv4M.",

author = "Pravakar Roy and Wenbo Dong and Volkan Isler",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018 ; Conference date: 01-10-2018 Through 05-10-2018",

year = "2018",

month = dec,

day = "27",

doi = "10.1109/IROS.2018.8594167",

language = "English (US)",

series = "IEEE International Conference on Intelligent Robots and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7697--7702",

booktitle = "2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018",

}

TY - GEN

T1 - Registering Reconstructions of the Two Sides of Fruit Tree Rows

AU - Roy, Pravakar

AU - Dong, Wenbo

AU - Isler, Volkan

PY - 2018/12/27

Y1 - 2018/12/27

N2 - We consider the problem of building accurate three dimensional (3D)reconstructions of orchard rows. This problem arises in many applications including yield mapping and measuring traits (e.g. trunk diameters)for phenotyping. While 3D reconstructions of side views can be obtained using standard methods, merging the two side-views is difficult due to the lack of overlap between the two partial reconstructions. We present a novel method that utilizes global features to constrain the solution. Specifically, we use information from the silhouettes and the ground plane for alignment. The method is evaluated using multiple simulated and real datasets. For additional information and demonstration of experimental results please see https://www.youtube.com/watch?v=6mGMF2gFv4M.

AB - We consider the problem of building accurate three dimensional (3D)reconstructions of orchard rows. This problem arises in many applications including yield mapping and measuring traits (e.g. trunk diameters)for phenotyping. While 3D reconstructions of side views can be obtained using standard methods, merging the two side-views is difficult due to the lack of overlap between the two partial reconstructions. We present a novel method that utilizes global features to constrain the solution. Specifically, we use information from the silhouettes and the ground plane for alignment. The method is evaluated using multiple simulated and real datasets. For additional information and demonstration of experimental results please see https://www.youtube.com/watch?v=6mGMF2gFv4M.

UR - http://www.scopus.com/inward/record.url?scp=85062971731&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062971731&partnerID=8YFLogxK

U2 - 10.1109/IROS.2018.8594167

DO - 10.1109/IROS.2018.8594167

M3 - Conference contribution

AN - SCOPUS:85062971731

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 7697

EP - 7702

BT - 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018

Y2 - 1 October 2018 through 5 October 2018

ER -

Registering Reconstructions of the Two Sides of Fruit Tree Rows

Abstract

Publication series

Conference

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this