A mango picking vision algorithm on instance segmentation and key point detection from RGB images in an open orchard

The vision system of a fruit picking robot must perform two difficult tasks, the accurate pixel-wise instance segmentation of fruit and the correct detection of picking points. Due to the unsatisfactory performance of the vision system on these tasks, the picking performance of the robot is insuffic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biosystems engineering Jg. 206; S. 32 - 54
Hauptverfasser: Zheng, Chan, Chen, Pengfei, Pang, Jing, Yang, Xiaofan, Chen, Changxin, Tu, Shuqin, Xue, Yueju
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.06.2021
Schlagworte:
ISSN:1537-5110, 1537-5129
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The vision system of a fruit picking robot must perform two difficult tasks, the accurate pixel-wise instance segmentation of fruit and the correct detection of picking points. Due to the unsatisfactory performance of the vision system on these tasks, the picking performance of the robot is insufficient and its application is not prevalent. In this study, performing fruit instance segmentation and the localization of picking points, a vision algorithm using RGB images was designed in a deep learning framework for a potential visual system of mango picking robots. The algorithm not only performed these two tasks successfully, but also integrated them into an end-to-end network, in which parallel branches performed the two tasks simultaneously. The average precision (at IoU of 0.75) and the average recall of instance segmentation reached 0.947 and 0.929 respectively, and the best precision and recall of picking-point detection reached 0.984 and 0.908 respectively. In addition, the tasks face various illumination and background interference in outdoor orchards, along with complex problems in terms of occlusion, overlap and object scale. In this study, the performance of the vision system was analysed in detail on several datasets and subsets of the various complex conditions, and the major factors that affect the performance were discussed. The results demonstrated that this system was robust against various illuminations and complex backgrounds, and yielded satisfactory segmentation and picking-point detection performances for minor and medium occlusion or overlap, and for medium and large mangoes. The model visualization and the influence analysis of model training demonstrated the training process and modelling effect of the deep learning network. •Designed an end-to-end vision system for a mango picking robot.•Instance segmentation and pick point detection are performed simultaneously.•It is robust to various illumination and background interference scenarios.•Good performances in minor and medium occlusion, various overlap and object scale.
AbstractList The vision system of a fruit picking robot must perform two difficult tasks, the accurate pixel-wise instance segmentation of fruit and the correct detection of picking points. Due to the unsatisfactory performance of the vision system on these tasks, the picking performance of the robot is insufficient and its application is not prevalent. In this study, performing fruit instance segmentation and the localization of picking points, a vision algorithm using RGB images was designed in a deep learning framework for a potential visual system of mango picking robots. The algorithm not only performed these two tasks successfully, but also integrated them into an end-to-end network, in which parallel branches performed the two tasks simultaneously. The average precision (at IoU of 0.75) and the average recall of instance segmentation reached 0.947 and 0.929 respectively, and the best precision and recall of picking-point detection reached 0.984 and 0.908 respectively. In addition, the tasks face various illumination and background interference in outdoor orchards, along with complex problems in terms of occlusion, overlap and object scale. In this study, the performance of the vision system was analysed in detail on several datasets and subsets of the various complex conditions, and the major factors that affect the performance were discussed. The results demonstrated that this system was robust against various illuminations and complex backgrounds, and yielded satisfactory segmentation and picking-point detection performances for minor and medium occlusion or overlap, and for medium and large mangoes. The model visualization and the influence analysis of model training demonstrated the training process and modelling effect of the deep learning network.
The vision system of a fruit picking robot must perform two difficult tasks, the accurate pixel-wise instance segmentation of fruit and the correct detection of picking points. Due to the unsatisfactory performance of the vision system on these tasks, the picking performance of the robot is insufficient and its application is not prevalent. In this study, performing fruit instance segmentation and the localization of picking points, a vision algorithm using RGB images was designed in a deep learning framework for a potential visual system of mango picking robots. The algorithm not only performed these two tasks successfully, but also integrated them into an end-to-end network, in which parallel branches performed the two tasks simultaneously. The average precision (at IoU of 0.75) and the average recall of instance segmentation reached 0.947 and 0.929 respectively, and the best precision and recall of picking-point detection reached 0.984 and 0.908 respectively. In addition, the tasks face various illumination and background interference in outdoor orchards, along with complex problems in terms of occlusion, overlap and object scale. In this study, the performance of the vision system was analysed in detail on several datasets and subsets of the various complex conditions, and the major factors that affect the performance were discussed. The results demonstrated that this system was robust against various illuminations and complex backgrounds, and yielded satisfactory segmentation and picking-point detection performances for minor and medium occlusion or overlap, and for medium and large mangoes. The model visualization and the influence analysis of model training demonstrated the training process and modelling effect of the deep learning network. •Designed an end-to-end vision system for a mango picking robot.•Instance segmentation and pick point detection are performed simultaneously.•It is robust to various illumination and background interference scenarios.•Good performances in minor and medium occlusion, various overlap and object scale.
Author Chen, Changxin
Zheng, Chan
Tu, Shuqin
Chen, Pengfei
Pang, Jing
Yang, Xiaofan
Xue, Yueju
Author_xml – sequence: 1
  givenname: Chan
  surname: Zheng
  fullname: Zheng, Chan
  organization: College of Mathematics and Informatics, South China Agricultural University, China
– sequence: 2
  givenname: Pengfei
  surname: Chen
  fullname: Chen, Pengfei
  organization: College of Electronic Engineering, South China Agricultural University, China
– sequence: 3
  givenname: Jing
  surname: Pang
  fullname: Pang, Jing
  organization: College of Electronic Engineering, South China Agricultural University, China
– sequence: 4
  givenname: Xiaofan
  surname: Yang
  fullname: Yang, Xiaofan
  organization: College of Electronic Engineering, South China Agricultural University, China
– sequence: 5
  givenname: Changxin
  surname: Chen
  fullname: Chen, Changxin
  organization: College of Electronic Engineering, South China Agricultural University, China
– sequence: 6
  givenname: Shuqin
  surname: Tu
  fullname: Tu, Shuqin
  organization: College of Mathematics and Informatics, South China Agricultural University, China
– sequence: 7
  givenname: Yueju
  surname: Xue
  fullname: Xue, Yueju
  email: xueyueju@163.com
  organization: College of Electronic Engineering, South China Agricultural University, China
BookMark eNqNkEtLAzEUhYMoaKv_IeDGTcdkMo8Mrqr4goIgug5pcmeaOpOMSRT6742tCLrq5r4458D9JujQOgsInVOSUUKry3W2NC5sQoQhgO2ynOQ0IywjND9AJ7Rk9aykeXP4O1NyjCYhrAmhZV1UJyjO8SBt5_Bo1JuxHf40wTiLZd85b-JqwGkxNkRpFeAA3QA2yriVWI3fYINHZ2zEGiKo7b31bsDP99fYDLKDkNxJit0IqXi1kl6foqNW9gHOfvoUvd7dvtw8zBZP948388VMsYrEWbnkLWkq1tZEqkrXLZNLXtMmp7JK79CmqDjlTOuyLXhZ1CBbpjknTJWaNbBkU3Sxyx29e_-AEMVggoK-lxbcRxB5mRd5UTDOk3S-kyrvQvDQCmV2f0YvTS8oEd_ExVr8IS6-iQvCRCKeMq7-ZYw-MfCbPd23OzckIp8GvAjKQKKujU9khXZmr5wv6qCpwg
CitedBy_id crossref_primary_10_1016_j_compag_2025_109937
crossref_primary_10_3390_s23020752
crossref_primary_10_1016_j_compag_2025_110246
crossref_primary_10_1016_j_ifacol_2022_05_029
crossref_primary_10_1016_j_compag_2024_109492
crossref_primary_10_1016_j_compag_2024_109216
crossref_primary_10_3233_IDA_220449
crossref_primary_10_1016_j_compag_2022_106789
crossref_primary_10_1016_j_compag_2023_107635
crossref_primary_10_3390_horticulturae11070858
crossref_primary_10_1016_j_compag_2025_110814
crossref_primary_10_3233_JIFS_223510
crossref_primary_10_3390_e25020298
crossref_primary_10_1016_j_compag_2022_107582
crossref_primary_10_1109_JSEN_2024_3485912
crossref_primary_10_1016_j_engappai_2022_104739
crossref_primary_10_3390_agronomy13092237
crossref_primary_10_35633_inmateh_76_51
crossref_primary_10_1016_j_biosystemseng_2025_01_007
crossref_primary_10_3390_agronomy12071520
crossref_primary_10_1016_j_biosystemseng_2023_12_017
crossref_primary_10_1016_j_atech_2025_101146
crossref_primary_10_1155_2021_7351470
crossref_primary_10_1016_j_compag_2023_107682
crossref_primary_10_3390_s23083803
crossref_primary_10_1016_j_biosystemseng_2023_09_014
crossref_primary_10_1016_j_compag_2024_108994
crossref_primary_10_1080_23311916_2024_2403706
crossref_primary_10_3389_fpls_2025_1646871
crossref_primary_10_1007_s10044_024_01222_x
crossref_primary_10_1007_s11554_024_01459_z
crossref_primary_10_1007_s11119_022_09913_3
crossref_primary_10_1016_j_biosystemseng_2024_09_015
crossref_primary_10_1016_j_atech_2025_100995
crossref_primary_10_1186_s13007_024_01293_1
crossref_primary_10_1016_j_aiia_2025_05_002
crossref_primary_10_1016_j_compag_2024_108620
crossref_primary_10_1016_j_compag_2024_109512
crossref_primary_10_1002_rob_22074
crossref_primary_10_1016_j_compag_2022_106843
crossref_primary_10_1515_comp_2022_0262
crossref_primary_10_1177_09544062221128443
crossref_primary_10_1016_j_compag_2025_110913
crossref_primary_10_1016_j_compag_2022_106791
crossref_primary_10_3390_s23041787
crossref_primary_10_3390_s24123858
crossref_primary_10_1016_j_biosystemseng_2022_08_013
crossref_primary_10_1007_s00530_024_01472_z
crossref_primary_10_1016_j_compag_2025_110637
crossref_primary_10_1016_j_asoc_2025_112971
crossref_primary_10_3389_fpls_2024_1460060
crossref_primary_10_1016_j_biosystemseng_2024_07_019
crossref_primary_10_3390_agriculture13081568
crossref_primary_10_1038_s41598_025_05113_x
crossref_primary_10_3390_agronomy13071891
crossref_primary_10_3390_agronomy14061325
crossref_primary_10_1007_s11119_022_09972_6
crossref_primary_10_3390_agriculture12101556
crossref_primary_10_1002_rob_22580
crossref_primary_10_1002_rob_22263
Cites_doi 10.1002/rob.21525
10.1109/ACCESS.2019.2917620
10.1023/B:VISI.0000029664.99615.94
10.3390/s16081222
10.1002/rob.21715
10.1007/978-3-319-10602-1_48
10.1016/j.compag.2018.06.007
10.1016/j.compag.2018.12.041
10.1016/j.biosystemseng.2017.11.005
10.1002/rob.21876
10.3390/s19204599
10.1016/j.compag.2018.02.016
10.3390/s18040969
10.13031/aea.32.10701
10.1016/j.compag.2016.06.022
10.1016/j.compag.2015.05.021
10.1007/s11119-019-09642-0
10.3390/s17040905
10.1016/j.engappai.2018.09.011
10.1504/IJCVR.2012.046419
10.1016/j.compind.2018.03.017
10.1016/j.compag.2019.01.012
10.1016/j.biosystemseng.2019.03.007
10.1016/j.compag.2019.04.017
10.1002/rob.21902
10.1016/j.compag.2012.11.009
10.1016/j.biosystemseng.2016.08.026
10.1002/rob.21699
10.1016/j.scienta.2019.01.033
10.1002/rob.21889
ContentType Journal Article
Copyright 2021 IAgrE
Copyright_xml – notice: 2021 IAgrE
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.biosystemseng.2021.03.012
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Agriculture
EISSN 1537-5129
EndPage 54
ExternalDocumentID 10_1016_j_biosystemseng_2021_03_012
S1537511021000738
GroupedDBID --K
--M
.~1
0R~
1B1
1RT
1~.
1~5
23N
4.4
457
4G.
53G
5GY
5VS
6J9
7-5
71M
8P~
AABVA
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALCJ
AALRI
AAOAW
AAQFI
AATLK
AAXUO
ABFNM
ABFRF
ABGRD
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ADBBV
ADEZE
ADMUD
ADQTV
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AEQOU
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHJVU
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BJAXD
BKOJK
BLXMC
CAG
CBWCG
COF
CS3
DM4
DU5
EBS
EFBJH
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
JJJVA
K-O
KOM
LG5
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSA
SST
SSZ
T5K
UHS
UNMZH
~G-
~KM
9DU
AAHBH
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
7S9
L.6
ID FETCH-LOGICAL-c360t-5b8f0963f70ac6d7f3ab871921a653719468183dd5f48547eaf3d8803c5d39eb3
ISICitedReferencesCount 73
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000651462400004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1537-5110
IngestDate Sat Sep 27 20:07:48 EDT 2025
Tue Nov 18 22:04:49 EST 2025
Sat Nov 29 07:03:46 EST 2025
Fri Feb 23 02:45:39 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Instance segmentation
Fruit picking robot
Occlusion and overlap
End-to-end framework
Picking-point detection
Complex scene
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c360t-5b8f0963f70ac6d7f3ab871921a653719468183dd5f48547eaf3d8803c5d39eb3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2524244388
PQPubID 24069
PageCount 23
ParticipantIDs proquest_miscellaneous_2524244388
crossref_citationtrail_10_1016_j_biosystemseng_2021_03_012
crossref_primary_10_1016_j_biosystemseng_2021_03_012
elsevier_sciencedirect_doi_10_1016_j_biosystemseng_2021_03_012
PublicationCentury 2000
PublicationDate June 2021
2021-06-00
20210601
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: June 2021
PublicationDecade 2020
PublicationTitle Biosystems engineering
PublicationYear 2021
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Häni, Roy, Isler (bib11) 2018
Koirala, Walsh, Wang, McCarthy (bib20) 2019; 162
Bac, van Henten, Hemming, Edan (bib1) 2014; 31
He, Zhang, Ren, Sun (bib14) 2016
Liu, Anguelov, Erhan, Szegedy, Reed (bib26) 2015
Litz (bib25) 2009
Payne, Walsh, Subedi, Jarvis (bib34) 2013; 91
Luo, Tang, Zou, Ye, Feng, Li (bib31) 2016; 151
Bargoti, Underwood (bib2) 2017
Liu, Chen, Aditya, Sivakumar, Dcunha, Qu, Kumar (bib27) 2018
Zhao, Gong, Huang, Liu (bib52) 2016; 127
Rahnemoonfar, Sheppard (bib35) 2017; 17
Kang, Chen (bib17) 2019; 19
Ren, He, Girshick, Sun (bib38) 2015
Chen, Skandan, Dcunha, Das, Okon, Qu, Kumar (bib5) 2017
Gong, Zhong, Hu (bib54) 2019; 7
He, Gkioxari, Dollár, Girshick (bib13) 2017
Gutiérrez, Wendel, Underwood (bib10) 2019; 157
Dalal, Triggs (bib6) 2005
Kestur, Meduri, Narasipura (bib19) 2019; 77
Roy, Isler (bib40) 2017
Xiong, Ge, Grimstad, From (bib46) 2020; 37
Williams, Jones, Nejati, Seabright, Bell, Penhall, MacDonald (bib45) 2019; 181
Xiong, Lin, Liu, He, Tang, Yang (bib48) 2018; 166
Redmon, Farhadi (bib37) 2018
Bargoti, Underwood (bib3) 2017; 34
Koirala, Walsh, Wang, McCarthy (bib21) 2019
Edan, Han, Kondo (bib8) 2009
Zou, Ye, Luo, Xiong, Luo, Wang (bib53) 2016; 32
Roy, Dong, Isler (bib39) 2018
Sa, Ge, Dayoub, Upcroft, Perez, McCool (bib41) 2016; 16
Ntsoane, Zude-Sasse, Mahajan, Sivakumar (bib33) 2019; 249
Redmon, Divvala, Girshick, Farhadi (bib36) 2015
Bay, Tuytelaars, Van Gool (bib4) 2006
Gongal, Amatya, Karkee, Zhang, Lewis (bib9) 2015; 116
Lin, Dollár, Girshick, He, Hariharan, Belongie (bib22) 2017
Xiong, He, Lin, Liu, Bu, Yang, Zou (bib47) 2018; 151
Kamilaris, Prenafeta-Boldú (bib16) 2018; 147
Häni, Roy, Isler (bib12) 2020; 37
Li, Qi, Dai, Ji, Wei (bib24) 2017
Newell, Yang, Deng (bib32) 2016
Long, Shelhamer, Darrell (bib28) 2015
Lin, Maire, Belongie, Hays, Perona, Ramanan, Zitnick (bib23) 2014; 8693
Kapach, Barnea, Mairon, Edan, Ben-Shahar (bib18) 2012; 3
Szegedy, Ioffe, Vanhoucke, Alemi (bib43) 2017
Lowe (bib29) 2004; 60
Tian, Yang, Wang, Wang, Li, Liang (bib44) 2019; 157
Silwal, Davidson, Karkee, Mo, Zhang, Lewis (bib42) 2017; 34
Xiong, Liu, Lin, Bu, He, Yang (bib49) 2018; 18
Luo, Tang, Lu, Chen, Zhang, Zou (bib30) 2018; 99
Zhang, Kjellstrom, Mandt (bib51) 2017
Yan, Xiong, Lin (bib50) 2018
Dong, Roy, Isler (bib7) 2020; 37
Huang, Wane, Parsons (bib15) 2017
Häni (10.1016/j.biosystemseng.2021.03.012_bib12) 2020; 37
Ntsoane (10.1016/j.biosystemseng.2021.03.012_bib33) 2019; 249
Kapach (10.1016/j.biosystemseng.2021.03.012_bib18) 2012; 3
Bay (10.1016/j.biosystemseng.2021.03.012_bib4) 2006
Williams (10.1016/j.biosystemseng.2021.03.012_bib45) 2019; 181
Roy (10.1016/j.biosystemseng.2021.03.012_bib39) 2018
Lin (10.1016/j.biosystemseng.2021.03.012_bib22) 2017
Liu (10.1016/j.biosystemseng.2021.03.012_bib27) 2018
Ren (10.1016/j.biosystemseng.2021.03.012_bib38) 2015
Gutiérrez (10.1016/j.biosystemseng.2021.03.012_bib10) 2019; 157
Newell (10.1016/j.biosystemseng.2021.03.012_bib32) 2016
Gong (10.1016/j.biosystemseng.2021.03.012_bib54) 2019; 7
Chen (10.1016/j.biosystemseng.2021.03.012_bib5) 2017
Zou (10.1016/j.biosystemseng.2021.03.012_bib53) 2016; 32
Dalal (10.1016/j.biosystemseng.2021.03.012_bib6) 2005
Xiong (10.1016/j.biosystemseng.2021.03.012_bib49) 2018; 18
Li (10.1016/j.biosystemseng.2021.03.012_bib24) 2017
Bargoti (10.1016/j.biosystemseng.2021.03.012_bib3) 2017; 34
Gongal (10.1016/j.biosystemseng.2021.03.012_bib9) 2015; 116
Luo (10.1016/j.biosystemseng.2021.03.012_bib31) 2016; 151
Xiong (10.1016/j.biosystemseng.2021.03.012_bib47) 2018; 151
Koirala (10.1016/j.biosystemseng.2021.03.012_bib21) 2019
Kamilaris (10.1016/j.biosystemseng.2021.03.012_bib16) 2018; 147
Lin (10.1016/j.biosystemseng.2021.03.012_bib23) 2014; 8693
Koirala (10.1016/j.biosystemseng.2021.03.012_bib20) 2019; 162
Silwal (10.1016/j.biosystemseng.2021.03.012_bib42) 2017; 34
Redmon (10.1016/j.biosystemseng.2021.03.012_bib37) 2018
Roy (10.1016/j.biosystemseng.2021.03.012_bib40) 2017
He (10.1016/j.biosystemseng.2021.03.012_bib14) 2016
Long (10.1016/j.biosystemseng.2021.03.012_bib28) 2015
Kestur (10.1016/j.biosystemseng.2021.03.012_bib19) 2019; 77
Dong (10.1016/j.biosystemseng.2021.03.012_bib7) 2020; 37
Edan (10.1016/j.biosystemseng.2021.03.012_bib8) 2009
Luo (10.1016/j.biosystemseng.2021.03.012_bib30) 2018; 99
Zhao (10.1016/j.biosystemseng.2021.03.012_bib52) 2016; 127
Redmon (10.1016/j.biosystemseng.2021.03.012_bib36) 2015
Liu (10.1016/j.biosystemseng.2021.03.012_bib26) 2015
Bac (10.1016/j.biosystemseng.2021.03.012_bib1) 2014; 31
Kang (10.1016/j.biosystemseng.2021.03.012_bib17) 2019; 19
Sa (10.1016/j.biosystemseng.2021.03.012_bib41) 2016; 16
Szegedy (10.1016/j.biosystemseng.2021.03.012_bib43) 2017
Xiong (10.1016/j.biosystemseng.2021.03.012_bib48) 2018; 166
Tian (10.1016/j.biosystemseng.2021.03.012_bib44) 2019; 157
Litz (10.1016/j.biosystemseng.2021.03.012_bib25) 2009
Lowe (10.1016/j.biosystemseng.2021.03.012_bib29) 2004; 60
Bargoti (10.1016/j.biosystemseng.2021.03.012_bib2) 2017
Huang (10.1016/j.biosystemseng.2021.03.012_bib15) 2017
Rahnemoonfar (10.1016/j.biosystemseng.2021.03.012_bib35) 2017; 17
He (10.1016/j.biosystemseng.2021.03.012_bib13) 2017
Yan (10.1016/j.biosystemseng.2021.03.012_bib50) 2018
Zhang (10.1016/j.biosystemseng.2021.03.012_bib51) 2017
Xiong (10.1016/j.biosystemseng.2021.03.012_bib46) 2020; 37
Payne (10.1016/j.biosystemseng.2021.03.012_bib34) 2013; 91
Häni (10.1016/j.biosystemseng.2021.03.012_bib11) 2018
References_xml – year: 2015
  ident: bib38
  article-title: Faster R-CNN: Towards real-time object detection with region proposal networks
  publication-title: Paper presented at the advances in neural information processing systems (NIPS)
– volume: 37
  start-page: 263
  year: 2020
  end-page: 282
  ident: bib12
  article-title: A comparative study of fruit detection and counting methods for yield mapping in apple orchards
  publication-title: Journal of Field Robotics
– volume: 162
  start-page: 219
  year: 2019
  end-page: 234
  ident: bib20
  article-title: Deep learning – method overview and review of use for fruit detection and yield estimation
  publication-title: Computers and Electronics in Agriculture
– volume: 99
  start-page: 130
  year: 2018
  end-page: 139
  ident: bib30
  article-title: A vision methodology for harvesting robot to detect cutting points on peduncles of double overlapping grape clusters in a vineyard
  publication-title: Computers in Industry
– year: 2018
  ident: bib50
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
  publication-title: Paper presented at the thirty-second AAAI conference on artificial intelligence
– year: 2006
  ident: bib4
  article-title: Surf: Speeded up robust features
– volume: 116
  start-page: 8
  year: 2015
  end-page: 19
  ident: bib9
  article-title: Sensors and systems for fruit detection and localization: A review
  publication-title: Computers and Electronics in Agriculture
– year: 2009
  ident: bib8
  article-title: Automation in agriculture
– volume: 16
  start-page: 1222
  year: 2016
  ident: bib41
  article-title: DeepFruits: A fruit detection system using deep neural networks
  publication-title: Sensors
– volume: 18
  start-page: 969
  year: 2018
  ident: bib49
  article-title: Green grape detection and picking-point calculation in a night-time natural environment using a charge-coupled device (CCD) vision sensor with artificial illumination
  publication-title: Sensors
– year: 2019
  ident: bib21
  article-title: Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ‘MangoYOLO’
  publication-title: Precision Agriculture
– year: 2017
  ident: bib13
  article-title: Mask r-cnn
– volume: 17
  start-page: 905
  year: 2017
  ident: bib35
  article-title: Deep count: Fruit counting based on deep simulated learning
  publication-title: Sensors
– year: 2017
  ident: bib51
  article-title: Determinantal point processes for mini-batch diversification
  publication-title: Paper presented at the Uncertainty in Artificial Intelligence
– year: 2017
  ident: bib22
  article-title: Feature pyramid networks for object detection
  publication-title: Paper presented at the proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 60
  start-page: 91
  year: 2004
  end-page: 110
  ident: bib29
  article-title: Distinctive image features from scale-invariant keypoints
  publication-title: International Journal of Computer Vision
– volume: 31
  start-page: 888
  year: 2014
  end-page: 911
  ident: bib1
  article-title: Harvesting robots for high-value crops: State-of-the-art review and challenges ahead
  publication-title: Journal of Field Robotics
– volume: 34
  start-page: 1039
  year: 2017
  end-page: 1060
  ident: bib3
  article-title: Image segmentation for fruit detection and yield estimation in apple orchards
  publication-title: Journal of Field Robotics
– volume: 37
  start-page: 97
  year: 2020
  end-page: 121
  ident: bib7
  article-title: Semantic mapping for orchard environments by merging two-sides reconstructions of tree rows
  publication-title: Journal of Field Robotics
– volume: 77
  start-page: 59
  year: 2019
  end-page: 69
  ident: bib19
  article-title: MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard
  publication-title: Engineering Applications of Artificial Intelligence
– volume: 37
  start-page: 202
  year: 2020
  end-page: 224
  ident: bib46
  article-title: An autonomous strawberry-harvesting robot: Design, development, integration, and field evaluation
  publication-title: Journal of Field Robotics
– volume: 151
  start-page: 226
  year: 2018
  end-page: 237
  ident: bib47
  article-title: Visual positioning technology of picking robots for dynamic litchi clusters with disturbance
  publication-title: Computers and Electronics in Agriculture
– year: 2009
  ident: bib25
  article-title: The mango: Botany, production and uses
– year: 2017
  ident: bib40
  article-title: Vision-based apple counting and yield estimation
  publication-title: Paper presented at the 2016 international symposium on experimental robotics, cham
– year: 2005
  ident: bib6
  article-title: Histograms of oriented gradients for human detection. Paper presented at the Computer Vision and Pattern Recognition, 2005. CVPR 2005
  publication-title: IEEE Computer Society Conference on
– volume: 157
  start-page: 417
  year: 2019
  end-page: 426
  ident: bib44
  article-title: Apple detection during different growth stages in orchards using the improved YOLO-V3 model
  publication-title: Computers and Electronics in Agriculture
– volume: 32
  start-page: 5
  year: 2016
  end-page: 18
  ident: bib53
  article-title: Fault-tolerant design of a limited universal fruit-picking end-effector based on vision-positioning error
  publication-title: Applied Engineering in Agriculture
– volume: 3
  start-page: 4
  year: 2012
  end-page: 34
  ident: bib18
  article-title: Computer vision for fruit harvesting robots – state of the art and challenges ahead
  publication-title: International Journal of Computational Vision and Robotics
– year: 2015
  ident: bib28
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: Paper presented at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
– volume: 181
  start-page: 140
  year: 2019
  end-page: 156
  ident: bib45
  article-title: Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms
  publication-title: Biosystems Engineering
– year: 2017
  ident: bib43
  article-title: Inception-v4, inception-resnet and the impact of residual connections on learning
  publication-title: Paper presented at the thirty-first AAAI conference on artificial intelligence
– volume: 34
  start-page: 1140
  year: 2017
  end-page: 1159
  ident: bib42
  article-title: Design, integration, and field evaluation of a robotic apple harvester
  publication-title: Journal of Field Robotics
– year: 2016
  ident: bib32
  article-title: Stacked hourglass networks for human pose estimation
– volume: 166
  start-page: 44
  year: 2018
  end-page: 57
  ident: bib48
  article-title: The recognition of litchi clusters and the calculation of picking point in a nocturnal natural environment
  publication-title: Biosystems Engineering
– year: 2018
  ident: bib11
  article-title: Apple counting using convolutional neural networks
  publication-title: Paper presented at the 2018 IEEE/RSJ international conference on intelligent robots and systems (IROS)
– year: 2017
  ident: bib5
  article-title: Counting apples and oranges with deep learning: A data driven approach
– year: 2015
  ident: bib36
  article-title: You only look once: Unified, real-time object detection
– volume: 151
  start-page: 90
  year: 2016
  end-page: 104
  ident: bib31
  article-title: Vision-based extraction of spatial information in grape clusters for harvesting robots
  publication-title: Biosystems Engineering
– year: 2017
  ident: bib2
  article-title: Deep fruit detection in orchards
  publication-title: Paper presented at the 2017 IEEE International Conference on robotics and automation (ICRA)
– year: 2016
  ident: bib14
  article-title: Deep residual learning for image recognition
  publication-title: Paper presented at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
– volume: 157
  start-page: 126
  year: 2019
  end-page: 135
  ident: bib10
  article-title: Ground based hyperspectral imaging for extensive mango yield estimation
  publication-title: Computers and Electronics in Agriculture
– start-page: 4438
  year: 2017
  end-page: 4446
  ident: bib24
  article-title: Fully convolutional instance-aware semantic segmentation
  publication-title: 30th IEEE Conference on Computer Vision and Pattern Recognition (Cvpr 2017)
– year: 2018
  ident: bib39
  article-title: Registering reconstructions of the two sides of fruit tree rows
  publication-title: Paper presented at the 2018 IEEE/RSJ international conference on intelligent robots and systems (IROS)
– volume: 7
  start-page: 64323
  year: 2019
  end-page: 64350
  ident: bib54
  article-title: Diversity in machine learning
  publication-title: IEEE Access
– volume: 249
  start-page: 77
  year: 2019
  end-page: 85
  ident: bib33
  article-title: Quality assesment and postharvest technology of mango: A review of its current status and future perspectives
  publication-title: Scientia Horticulturae
– year: 2018
  ident: bib37
  article-title: Yolov3: An incremental improvement
– volume: 19
  start-page: 4599
  year: 2019
  ident: bib17
  article-title: Fruit detection and segmentation for apple harvesting using visual sensor in orchards
  publication-title: Sensors
– volume: 8693
  start-page: 740
  year: 2014
  end-page: 755
  ident: bib23
  article-title: Microsoft COCO: Common objects in Context
  publication-title: Computer Vision - Eccv 2014, Pt V
– volume: 91
  start-page: 57
  year: 2013
  end-page: 64
  ident: bib34
  article-title: Estimation of mango crop yield using image analysis – segmentation method
  publication-title: Computers and Electronics in Agriculture
– year: 2017
  ident: bib15
  article-title: Towards automated strawberry harvesting: Identifying the picking point
– year: 2018
  ident: bib27
  article-title: Robust fruit counting: Combining deep learning, tracking, and structure from motion
  publication-title: Paper presented at the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
– volume: 127
  start-page: 311
  year: 2016
  end-page: 323
  ident: bib52
  article-title: A review of key techniques of vision-based control for harvesting robot
  publication-title: Computers and Electronics in Agriculture
– volume: 147
  start-page: 70
  year: 2018
  end-page: 90
  ident: bib16
  article-title: Deep learning in agriculture: A survey
  publication-title: Computers and Electronics in Agriculture
– year: 2015
  ident: bib26
  article-title: SSD: Single Shot MultiBox detector
– volume: 31
  start-page: 888
  issue: 6
  year: 2014
  ident: 10.1016/j.biosystemseng.2021.03.012_bib1
  article-title: Harvesting robots for high-value crops: State-of-the-art review and challenges ahead
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21525
– volume: 7
  start-page: 64323
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib54
  article-title: Diversity in machine learning
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2917620
– volume: 60
  start-page: 91
  issue: 2
  year: 2004
  ident: 10.1016/j.biosystemseng.2021.03.012_bib29
  article-title: Distinctive image features from scale-invariant keypoints
  publication-title: International Journal of Computer Vision
  doi: 10.1023/B:VISI.0000029664.99615.94
– volume: 16
  start-page: 1222
  issue: 8
  year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib41
  article-title: DeepFruits: A fruit detection system using deep neural networks
  publication-title: Sensors
  doi: 10.3390/s16081222
– volume: 34
  start-page: 1140
  issue: 6
  year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib42
  article-title: Design, integration, and field evaluation of a robotic apple harvester
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21715
– volume: 8693
  start-page: 740
  year: 2014
  ident: 10.1016/j.biosystemseng.2021.03.012_bib23
  article-title: Microsoft COCO: Common objects in Context
  publication-title: Computer Vision - Eccv 2014, Pt V
  doi: 10.1007/978-3-319-10602-1_48
– volume: 151
  start-page: 226
  year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib47
  article-title: Visual positioning technology of picking robots for dynamic litchi clusters with disturbance
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2018.06.007
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib51
  article-title: Determinantal point processes for mini-batch diversification
– year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib14
  article-title: Deep residual learning for image recognition
– volume: 157
  start-page: 126
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib10
  article-title: Ground based hyperspectral imaging for extensive mango yield estimation
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2018.12.041
– volume: 166
  start-page: 44
  year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib48
  article-title: The recognition of litchi clusters and the calculation of picking point in a nocturnal natural environment
  publication-title: Biosystems Engineering
  doi: 10.1016/j.biosystemseng.2017.11.005
– volume: 37
  start-page: 97
  year: 2020
  ident: 10.1016/j.biosystemseng.2021.03.012_bib7
  article-title: Semantic mapping for orchard environments by merging two-sides reconstructions of tree rows
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21876
– volume: 19
  start-page: 4599
  issue: 20
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib17
  article-title: Fruit detection and segmentation for apple harvesting using visual sensor in orchards
  publication-title: Sensors
  doi: 10.3390/s19204599
– volume: 147
  start-page: 70
  year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib16
  article-title: Deep learning in agriculture: A survey
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2018.02.016
– year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib39
  article-title: Registering reconstructions of the two sides of fruit tree rows
– year: 2015
  ident: 10.1016/j.biosystemseng.2021.03.012_bib38
  article-title: Faster R-CNN: Towards real-time object detection with region proposal networks
– volume: 18
  start-page: 969
  issue: 4
  year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib49
  article-title: Green grape detection and picking-point calculation in a night-time natural environment using a charge-coupled device (CCD) vision sensor with artificial illumination
  publication-title: Sensors
  doi: 10.3390/s18040969
– volume: 32
  start-page: 5
  issue: 1
  year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib53
  article-title: Fault-tolerant design of a limited universal fruit-picking end-effector based on vision-positioning error
  publication-title: Applied Engineering in Agriculture
  doi: 10.13031/aea.32.10701
– year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib50
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib40
  article-title: Vision-based apple counting and yield estimation
– volume: 127
  start-page: 311
  year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib52
  article-title: A review of key techniques of vision-based control for harvesting robot
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2016.06.022
– volume: 116
  start-page: 8
  year: 2015
  ident: 10.1016/j.biosystemseng.2021.03.012_bib9
  article-title: Sensors and systems for fruit detection and localization: A review
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2015.05.021
– year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib21
  article-title: Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ‘MangoYOLO’
  publication-title: Precision Agriculture
  doi: 10.1007/s11119-019-09642-0
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib13
– start-page: 4438
  year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib24
  article-title: Fully convolutional instance-aware semantic segmentation
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib22
  article-title: Feature pyramid networks for object detection
– year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib32
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib5
– year: 2005
  ident: 10.1016/j.biosystemseng.2021.03.012_bib6
  article-title: Histograms of oriented gradients for human detection. Paper presented at the Computer Vision and Pattern Recognition, 2005. CVPR 2005
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib43
  article-title: Inception-v4, inception-resnet and the impact of residual connections on learning
– volume: 17
  start-page: 905
  issue: 4
  year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib35
  article-title: Deep count: Fruit counting based on deep simulated learning
  publication-title: Sensors
  doi: 10.3390/s17040905
– year: 2009
  ident: 10.1016/j.biosystemseng.2021.03.012_bib25
– year: 2015
  ident: 10.1016/j.biosystemseng.2021.03.012_bib36
– volume: 77
  start-page: 59
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib19
  article-title: MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard
  publication-title: Engineering Applications of Artificial Intelligence
  doi: 10.1016/j.engappai.2018.09.011
– year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib27
  article-title: Robust fruit counting: Combining deep learning, tracking, and structure from motion
– volume: 3
  start-page: 4
  issue: 1/2
  year: 2012
  ident: 10.1016/j.biosystemseng.2021.03.012_bib18
  article-title: Computer vision for fruit harvesting robots – state of the art and challenges ahead
  publication-title: International Journal of Computational Vision and Robotics
  doi: 10.1504/IJCVR.2012.046419
– year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib11
  article-title: Apple counting using convolutional neural networks
– volume: 99
  start-page: 130
  year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib30
  article-title: A vision methodology for harvesting robot to detect cutting points on peduncles of double overlapping grape clusters in a vineyard
  publication-title: Computers in Industry
  doi: 10.1016/j.compind.2018.03.017
– volume: 157
  start-page: 417
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib44
  article-title: Apple detection during different growth stages in orchards using the improved YOLO-V3 model
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2019.01.012
– year: 2018
  ident: 10.1016/j.biosystemseng.2021.03.012_bib37
– volume: 181
  start-page: 140
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib45
  article-title: Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms
  publication-title: Biosystems Engineering
  doi: 10.1016/j.biosystemseng.2019.03.007
– volume: 162
  start-page: 219
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib20
  article-title: Deep learning – method overview and review of use for fruit detection and yield estimation
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2019.04.017
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib2
  article-title: Deep fruit detection in orchards
– year: 2006
  ident: 10.1016/j.biosystemseng.2021.03.012_bib4
– volume: 37
  start-page: 263
  issue: 2
  year: 2020
  ident: 10.1016/j.biosystemseng.2021.03.012_bib12
  article-title: A comparative study of fruit detection and counting methods for yield mapping in apple orchards
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21902
– volume: 91
  start-page: 57
  year: 2013
  ident: 10.1016/j.biosystemseng.2021.03.012_bib34
  article-title: Estimation of mango crop yield using image analysis – segmentation method
  publication-title: Computers and Electronics in Agriculture
  doi: 10.1016/j.compag.2012.11.009
– volume: 151
  start-page: 90
  year: 2016
  ident: 10.1016/j.biosystemseng.2021.03.012_bib31
  article-title: Vision-based extraction of spatial information in grape clusters for harvesting robots
  publication-title: Biosystems Engineering
  doi: 10.1016/j.biosystemseng.2016.08.026
– volume: 34
  start-page: 1039
  issue: 6
  year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib3
  article-title: Image segmentation for fruit detection and yield estimation in apple orchards
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21699
– year: 2009
  ident: 10.1016/j.biosystemseng.2021.03.012_bib8
– year: 2015
  ident: 10.1016/j.biosystemseng.2021.03.012_bib28
  article-title: Fully convolutional networks for semantic segmentation
– volume: 249
  start-page: 77
  year: 2019
  ident: 10.1016/j.biosystemseng.2021.03.012_bib33
  article-title: Quality assesment and postharvest technology of mango: A review of its current status and future perspectives
  publication-title: Scientia Horticulturae
  doi: 10.1016/j.scienta.2019.01.033
– volume: 37
  start-page: 202
  issue: 2
  year: 2020
  ident: 10.1016/j.biosystemseng.2021.03.012_bib46
  article-title: An autonomous strawberry-harvesting robot: Design, development, integration, and field evaluation
  publication-title: Journal of Field Robotics
  doi: 10.1002/rob.21889
– year: 2017
  ident: 10.1016/j.biosystemseng.2021.03.012_bib15
– year: 2015
  ident: 10.1016/j.biosystemseng.2021.03.012_bib26
SSID ssj0015746
Score 2.5787675
Snippet The vision system of a fruit picking robot must perform two difficult tasks, the accurate pixel-wise instance segmentation of fruit and the correct detection...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 32
SubjectTerms algorithms
Complex scene
data collection
End-to-end framework
Fruit picking robot
fruits
Instance segmentation
lighting
mangoes
Occlusion and overlap
orchards
Picking-point detection
vision
Title A mango picking vision algorithm on instance segmentation and key point detection from RGB images in an open orchard
URI https://dx.doi.org/10.1016/j.biosystemseng.2021.03.012
https://www.proquest.com/docview/2524244388
Volume 206
WOSCitedRecordID wos000651462400004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1537-5129
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0015746
  issn: 1537-5110
  databaseCode: AIEXJ
  dateStart: 20020101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Za9wwEBZLUkr7UHqS9EKlfTMOXste2X0ouCW9KCGUtGyfhGRLrsOubbxOyA_qD-3Iko-kBLaFwiLWsiXLns-j0WgOhF6l3A-oFNQF6VO4AAruci9WOmuqlwULT_pdHrLvX-jRUbRcxsez2a_eF-Z8RcsyuriI6_9KaqgDYmvX2b8g99ApVMB_IDqUQHYotyJ8oi1S88qpi1SrwR3jPe7wVV41Rftz7XTGjVoo1NFlZb623kfGKhm-aaeuirJ1MtlKk0e8c0H5-uGtU6x53hlwOTqhRS2haAa__GFruKhMeOiNI8dgh6OCWhruot0aRtsCw_yO4ZySxbitZc2FJ-1_2LplwStle7BKC39iXDXwWeqCrOdNGbHvTVmpVXuaSdkEmv6D3RvNw-mBGJ4Mxnmgb9hFrrUG2peCbF-Z_AaTxN7a7ZRd6ozpzphHmKdTWe_6NIyB_e8mnw6Xn4fdqpAaL7b-oW6il6Md4bVju04SuiITdILOyV10x65QcGKQdQ_NZHkf3U7yxkZpkXA0iWL5ALUJ7hCHLeKwQRweEIfhoEccniIOA-IwIA53iMMD4rBGHAbEYYM4aA2XYo04bBH3EH17f3jy7qNrk3m4KVl4rRuKSMFymSjq8XSRUUW4gMV67M_5At7bPA4WIDuSLAtVEIXAP7giGUwuJA0zEktBHqGdsirlHsKhIEpr4UCwgh9Vwg9TEUmfkFTNs7nYR6_7F8tSG-leJ1xZsS2IvI-CoXFtAr5s1-xNT0FmZVcjkzLA6nYdvOjpzoDD6207XsrqbMP8ULtwBSSKHv_b2J6gW-M3-BTttM2ZfIZupOdtsWmeWzD_BriZ1J0
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+mango+picking+vision+algorithm+on+instance+segmentation+and+key+point+detection+from+RGB+images+in+an+open+orchard&rft.jtitle=Biosystems+engineering&rft.au=Zheng%2C+Chan&rft.au=Chen%2C+Pengfei&rft.au=Pang%2C+Jing&rft.au=Yang%2C+Xiaofan&rft.date=2021-06-01&rft.issn=1537-5110&rft.volume=206&rft.spage=32&rft.epage=54&rft_id=info:doi/10.1016%2Fj.biosystemseng.2021.03.012&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_biosystemseng_2021_03_012
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1537-5110&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1537-5110&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1537-5110&client=summon