Predicting Sagittal Plane Lifting Postures From Image Bounding Box Dimensions

Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift orig...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Human factors Ročník 61; číslo 1; s. 64 - 77
Hlavní autoři:	Greene, Runyu L., Hu, Yu Hen, Difranco, Nicholas, Wang, Xuan, Lu, Ming-Lun, Bao, Stephen, Lin, Jia-Hua, Radwin, Robert G.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Los Angeles, CA SAGE Publications 01.02.2019 Human Factors and Ergonomics Society
Témata:	Algorithms Anthropometry Biomechanical Phenomena Body measurements Cameras Classification Computer vision Decision Trees Hoisting Humans Image classification Lifting Manikins Obstructions Posture - physiology Regression analysis Reproducibility of Results Smartphones Task Performance and Analysis Video data work physiology job risk assessment gait anthropometry posture low back biomechanical models spine manual materials handling biomechanics
ISSN:	0018-7208, 1547-8181, 1547-8181
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination. Background: Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle. Methods: Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures. Results: The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing. Conclusions: The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes. Applications: It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners.
AbstractList	A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an "elastic" rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination.OBJECTIVEA method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an "elastic" rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination.Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle.BACKGROUNDCurrent marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle.Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures.METHODSMannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures.The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing.RESULTSThe resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing.The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes.CONCLUSIONSThe tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes.It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners.APPLICATIONSIt is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners. Objective:A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination.Background:Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle.Methods:Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures.Results:The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing.Conclusions:The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes.Applications:It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners. A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an "elastic" rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination. Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle. Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures. The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing. The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes. It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners. Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination. Background: Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle. Methods: Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures. Results: The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing. Conclusions: The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes. Applications: It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners.
Author	Bao, Stephen Lu, Ming-Lun Greene, Runyu L. Hu, Yu Hen Wang, Xuan Difranco, Nicholas Radwin, Robert G. Lin, Jia-Hua
Author_xml	– sequence: 1 givenname: Runyu L. surname: Greene fullname: Greene, Runyu L. – sequence: 2 givenname: Yu Hen surname: Hu fullname: Hu, Yu Hen – sequence: 3 givenname: Nicholas surname: Difranco fullname: Difranco, Nicholas – sequence: 4 givenname: Xuan surname: Wang fullname: Wang, Xuan organization: University of Wisconsin-Madison, USA – sequence: 5 givenname: Ming-Lun surname: Lu fullname: Lu, Ming-Lun organization: National Institute for Occupational Safety and Health, Cincinnati, Ohio, USA – sequence: 6 givenname: Stephen surname: Bao fullname: Bao, Stephen – sequence: 7 givenname: Jia-Hua surname: Lin fullname: Lin, Jia-Hua organization: Washington Department of Labor and Industries, Olympia, USA – sequence: 8 givenname: Robert G. orcidid: 0000-0002-7973-0641 surname: Radwin fullname: Radwin, Robert G. email: rradwin@wisc.edu organization: University of Wisconsin-Madison, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/30091947$$D View this record in MEDLINE/PubMed
BookMark	eNp9kctr3DAQxkXZ0Gwe956KoZdenEi2HvaxSZsHbMhCkrMYy-NFwba2kgzpf1-5m1BYSC4SzPf7hm9mjshidCMS8oXRM8aUOqeUVaqgVXprVkr1iSyZ4CpPBbYgy1nOZ_2QHIXwTCmVdSk-k8OS0prVXC3J3dpja0204yZ7gI2NEfps3cOI2cp2_8prF-LkMWRX3g3Z7QAbzC7cNLazeOFesp92wDFYN4YTctBBH_D09T8mT1e_Hi9v8tX99e3lj1VuuBQxbxqFIBg3ErgwZVMB1EKAqKFAUzBgClpFUVWm43XbSgllh1zQCitKBcXymHzf9d1693vCEPVgg8F-zu2moNPISlQVr4uEfttDn93kx5ROF0yyouRSiUR9faWmZsBWb70dwP_Rb4tKgNwBxrsQPHba2AgxDR092F4zqueL6P2LJCPdM771_sCS7ywhrfp_3Hf5v2FDl1Q
CitedBy_id	crossref_primary_10_1177_1071181319631115 crossref_primary_10_3390_diagnostics14060576 crossref_primary_10_1016_j_apergo_2025_104513 crossref_primary_10_1177_1071181321651211 crossref_primary_10_1177_1071181320641205 crossref_primary_10_1109_LRA_2021_3084881 crossref_primary_10_1016_j_apergo_2021_103574 crossref_primary_10_1177_0018720820958840 crossref_primary_10_1177_1071181320641230 crossref_primary_10_1016_j_matpr_2021_02_283 crossref_primary_10_1109_THMS_2022_3148339
Cites_doi	10.1097/00007632-199206000-00006 10.1518/155723408X342844 10.2105/AJPH.91.7.1069 10.1177/0018720812458121 10.1061/41182(416)47 10.1186/2052-4374-26-15 10.1016/S0169-8141(02)00174-9 10.1016/0021-9290(96)00028-0 10.1016/j.apergo.2017.02.020 10.2105/AJPH.89.7.1036 10.1080/00140139.2016.1146347 10.1007/s11042-016-3469-0 10.1186/1471-2474-10-15 10.1016/j.apergo.2005.01.007 10.1177/0018720813513608 10.1016/0021-9290(85)90012-0 10.4271/2007-01-2480 10.1016/j.apergo.2016.10.015 10.1518/001872097778940632 10.1061/9780784479827.082 10.1109/10.412663 10.1109/CVPR.2007.383298 10.1080/00140130600555938 10.1002/ajim.20750 10.1016/j.apergo.2017.01.007 10.1097/00007632-199304000-00015 10.1080/00140139508925111 10.1093/occmed/49.3.155 10.1109/FG.2018.00078 10.1016/j.jbiomech.2018.01.012
ContentType	Journal Article
Copyright	2018, Human Factors and Ergonomics Society
Copyright_xml	– notice: 2018, Human Factors and Ergonomics Society
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QF 7QQ 7SC 7SE 7SP 7SR 7T2 7TA 7TB 7TK 7U5 8BQ 8FD C1K F28 FR3 H8D H8G JG9 JQ2 K9. KR7 L7M L~C L~D 7X8
DOI	10.1177/0018720818791367
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aluminium Industry Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Health and Safety Science Abstracts (Full archive) Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database Environmental Sciences and Pollution Management ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Copper Technical Reference Library Materials Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Health & Medical Complete (Alumni) Materials Business File Environmental Sciences and Pollution Management Aerospace Database Copper Technical Reference Library Engineered Materials Abstracts Health & Safety Science Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Materials Research Database MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Psychology
EISSN	1547-8181
EndPage	77
ExternalDocumentID	30091947 10_1177_0018720818791367 10.1177_0018720818791367
Genre	Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural
GrantInformation_xml	– fundername: National Institute for Occupational Safety and Health grantid: R01OH011024 funderid: https://doi.org/10.13039/100000125
GroupedDBID	--- -TM -TN -~X .2G .2L .2N .55 .DC .GJ 01A 09Z 0R~ 1~K 29I 2FS 31W 31X 31Z 36B 3EH 4.4 53G 54M 5GY 5VS 7X2 7X7 7XC 85S 88E 88I 8AF 8CJ 8FE 8FG 8FH 8FI 8FJ 8G5 8R4 8R5 AABOD AACKU AACTG AADIR AADUE AAGGD AAGLT AAJOX AAJPV AAKTJ AAMFR AANSI AAPEO AAQDB AAQXI AARIX AATAA AATBZ AAWLO AAWTL AAYJJ AAYTG ABAWP ABCCA ABCJG ABDMP ABDPE ABDWY ABEIX ABFWQ ABFXH ABGFU ABHKI ABIDT ABIVO ABJCF ABKRH ABLUO ABPNF ABQKF ABQPY ABQXT ABRHV ABUJY ABUWG ABYTW ACABN ACAEP ACDXX ACFUR ACFZE ACGBL ACGFS ACGOD ACHQT ACIWK ACJER ACLZU ACOFE ACOXC ACPRK ACROE ACRPL ACSIQ ACUAV ACUFS ACUIR ACXKE ADBBV ADDLC ADEBD ADEIA ADMHG ADNMO ADNON ADNWM ADPEE ADRRZ ADSTG ADTBJ ADTOS ADUKL ADVBO ADXHL ADYCS AEDFJ AEDXQ AEILP AENEX AEOBU AEONT AEPTA AEQLS AESMA AESZF AEUHG AEUYN AEVPJ AEWDL AEWHI AEXNY AFEET AFFNX AFKBI AFKRA AFKRG AFMOU AFQAA AFRAH AFUIA AFWMB AGDVU AGKLV AGNHF AGNWV AGQPQ AGWFA AHDMH AHHFK AHMBA AHOJL AHWHD AI. AIZZC AJEFB AJUXI AJUZI ALEEW ALFTD ALIPV ALMA_UNASSIGNED_HOLDINGS ANDLU AQUVI ARTOV ASPBG ATCPS AUTPY AUVAJ AVQMV AVWKF AYAKG AYPQM AZFZN AZQEC B8T B8Z B94 BBNVY BBRGL BCR BCU BDDNI BDZRT BEC BENPR BES BGLVJ BHPHI BKOMP BKSAR BLC BMVBW BPACV BPHCQ BVXVI BYIEH CAG CBRKF CCGJY CCPQU CEADM CFDXU COF CORYS D1J D1K DD0 DD~ DE- DG~ DH. DO- DOPDO DU5 DV7 DV8 DWQXO D~Y EBS EJD F5P FAC FAS FEDTE FHBDP FJW FYUFA GNUQQ GROUPED_SAGE_PREMIER_JOURNAL_COLLECTION GUQSH H13 HCIFZ HF~ HMCUK HVGLF HZ~ IAO ICD ICJ IEA IGS IHR IOF IPO IPY ITC J8X K.F K50 K6- KQ4 L6V LK5 LK8 LPU M0K M0T M1D M1P M2M M2O M2P M2Q M7P M7R M7S N9A O9- OHT P.B P2P PADUT PATMY PCBAR PEA PHGZM PHGZT PMKZF PQQKQ PROAC PSQYO PSYQQ PTHSS PYCSY Q1R Q2X Q7O Q7P Q7V Q7X Q82 Q83 ROL S01 S0X SAUOL SCNPE SFC SGU SGV SGZ SJFOW SPV SSDHQ TN5 U5U UAP UBX UHB UKHRP UPT VH1 WH7 X7M XH6 XOL XZL YNY ZGI ZPLXX ZPPRI ZRKOI ZXP ~02 ~32 0SE AAEJI AAPII AAYXX ABUAX ACCVC AFFHD AJGYC AJHME AJVBE AMNSR CITATION PEJEM PJZUB PPXIY PQGLB .4S 3V. AAMGE ABDEX ACTQU AEUIJ AIOMO CGR CUY CVF ECM EDH EIF EMOBN M4V NPM PKN QN7 VQA YIN Z5M 7QF 7QQ 7SC 7SE 7SP 7SR 7T2 7TA 7TB 7TK 7U5 8BQ 8FD C1K F28 FR3 H8D H8G JG9 JQ2 K9. KR7 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c465t-bb7ea514c6a45c3b8aa955a59a2ec21a17ad70e78cf49dd66a3fe4508e80050e3
IEDL.DBID	AEVPJ
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000454502100006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-7208 1547-8181
IngestDate	Sat Sep 27 23:15:37 EDT 2025 Tue Oct 07 05:51:06 EDT 2025 Wed Feb 19 02:31:01 EST 2025 Tue Nov 18 22:28:00 EST 2025 Sat Nov 29 08:16:54 EST 2025 Tue Jun 17 22:48:33 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	work physiology job risk assessment gait anthropometry posture low back biomechanical models spine manual materials handling biomechanics
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c465t-bb7ea514c6a45c3b8aa955a59a2ec21a17ad70e78cf49dd66a3fe4508e80050e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-7973-0641
OpenAccessLink	https://journals.sagepub.com/doi/pdf/10.1177/0018720818791367
PMID	30091947
PQID	2161234675
PQPubID	48481
PageCount	14
ParticipantIDs	proquest_miscellaneous_2087588492 proquest_journals_2161234675 pubmed_primary_30091947 crossref_citationtrail_10_1177_0018720818791367 crossref_primary_10_1177_0018720818791367 sage_journals_10_1177_0018720818791367
PublicationCentury	2000
PublicationDate	2019-02-01
PublicationDateYYYYMMDD	2019-02-01
PublicationDate_xml	– month: 02 year: 2019 text: 2019-02-01 day: 01
PublicationDecade	2010
PublicationPlace	Los Angeles, CA
PublicationPlace_xml	– name: Los Angeles, CA – name: United States – name: Santa Monica
PublicationTitle	Human factors
PublicationTitleAlternate	Hum Factors
PublicationYear	2019
Publisher	SAGE Publications Human Factors and Ergonomics Society
Publisher_xml	– name: SAGE Publications – name: Human Factors and Ergonomics Society
References	Hwang, Kim, Kim 2009; 10 Mehrizi, Peng, Xu, Zhan, Metaxas, Li 2018; 69 Mehrizi, Xu, Zhang, Pavlovic, Metaxas, Li 2017; 65 Akkas, Lee, Hu, Yen, Radwin 2016; 59 Myers, Baker, Li, Smith, Wiker, Liang, Johnson 1999; 89 Holmström, Lindell, Moritz 1992; 17 Chaffin 2008; 4 Marras, Lavender, Leurgans, Rajulu, Allread, Fathallah, Ferguson 1993; 18 Eriksen, Natvig, Bruusgaard 1999; 49 Kerr, Frank, Shannon, Norman, Wells, Neumann 2001; 91 Chen, Hu, Yen, Radwin 2013; 55 Marfia, Roccetti 2016; 76 Plantard, Shum, Le Pierres, Multon 2016; 65 Lu, Waters, Krieg, Werren 2014; 56 Lavender, Andersson, Schipplein, Fuentes 2003; 31 Greene, Azari, Hu, Radwin 2017; 65 Burgess-Limerick, Abernathy 1997; 39 Anderson, Chaffin, Herrin, Matthew 1985; 18 Spector, Lieblich, Bao, McQuade, Hughes 2014; 26 Dempsey, McGorry, Maynard 2005; 36 Marras, Lavender, Leurgans, Fathallah, Ferguson, Gary Allread, Rajulu 1995; 38 Yen, Radwin 1995; 42 Bao, Howard, Spielholz, Silverstein 2006; 49 da Costa, Vieira 2010; 53 Dysart, Woldstad 1996; 29 Barondess J. A. (bibr5-0018720818791367) 2001 bibr33-0018720818791367 bibr3-0018720818791367 bibr20-0018720818791367 bibr38-0018720818791367 Breiman L. (bibr8-0018720818791367) 1984 bibr29-0018720818791367 bibr42-0018720818791367 bibr25-0018720818791367 bibr7-0018720818791367 bibr12-0018720818791367 bibr15-0018720818791367 bibr32-0018720818791367 bibr6-0018720818791367 bibr24-0018720818791367 bibr37-0018720818791367 bibr2-0018720818791367 bibr28-0018720818791367 bibr41-0018720818791367 bibr11-0018720818791367 bibr14-0018720818791367 bibr22-0018720818791367 bibr44-0018720818791367 bibr35-0018720818791367 bibr19-0018720818791367 bibr31-0018720818791367 bibr36-0018720818791367 bibr23-0018720818791367 bibr1-0018720818791367 bibr10-0018720818791367 Gordon C. C. (bibr16-0018720818791367) 2014 bibr27-0018720818791367 bibr9-0018720818791367 bibr21-0018720818791367 bibr40-0018720818791367 bibr39-0018720818791367 bibr18-0018720818791367 bibr34-0018720818791367 bibr17-0018720818791367 bibr30-0018720818791367 bibr43-0018720818791367 bibr13-0018720818791367 bibr4-0018720818791367 bibr26-0018720818791367
References_xml	– volume: 55 start-page: 298 year: 2013 end-page: 308 article-title: Automated video exposure assessment of repetitive hand activity level for a load transfer task publication-title: Human Factors – volume: 17 start-page: 672 issue: 6 year: 1992 end-page: 677 article-title: Low back and neck/shoulder pain in construction workers: Occupational workload and psychosocial risk factors. Part 2: Relationship to neck and shoulder pain publication-title: Spine – volume: 31 start-page: 51 issue: 1 year: 2003 end-page: 59 article-title: The effects of initial lifting height, load magnitude, and lifting speed on the peak dynamic L5/S1 moments publication-title: International Journal of Industrial Ergonomics – volume: 76 start-page: 8109 issue: 6 year: 2016 end-page: 8129 article-title: A practical computer based vision system for posture and movement sensing in occupational medicine publication-title: Multimedia Tools and Applications – volume: 69 start-page: 40 year: 2018 end-page: 46 article-title: A computer vision based method for 3D posture estimation of symmetrical lifting publication-title: Journal of Biomechanics – volume: 65 start-page: 461 year: 2017 end-page: 472 article-title: Visualizing stressful aspects of repetitive motion tasks and opportunities for ergonomic improvements using computer vision publication-title: Applied Ergonomics – volume: 38 start-page: 377 issue: 2 year: 1995 end-page: 410 article-title: Biomechanical risk factors for occupationally related low back disorders publication-title: Ergonomics – volume: 65 start-page: 562 year: 2016 end-page: 569 article-title: Validation of an ergonomic assessment method using Kinect data in real workplace conditions publication-title: Applied Ergonomics – volume: 18 start-page: 617 issue: 5 year: 1993 end-page: 628 article-title: The role of dynamic three-dimensional trunk motion in occupationally-related low back disorders publication-title: Spine – volume: 91 start-page: 1069 issue: 7 year: 2001 article-title: Biomechanical and psychosocial risk factors for low back pain at work publication-title: American Journal of Public Health – volume: 39 start-page: 141 year: 1997 end-page: 148 article-title: Toward a quantitative definition of manual lifting postures publication-title: Human Factors – volume: 10 start-page: 15 year: 2009 article-title: Lower extremity joint kinetics and lumbar curvature during squat and stoop lifting publication-title: BMC Musculoskeletal Disorders – volume: 89 start-page: 1036 issue: 7 year: 1999 end-page: 1041 article-title: Back injury in municipal workers: A case-control study publication-title: American Journal of Public Health – volume: 56 start-page: 73 year: 2014 end-page: 85 article-title: Efficacy of the revised NIOSH lifting equation for predicting risk of low back pain associated with manual lifting: A one-year prospective study publication-title: Human Factors – volume: 26 start-page: 15 year: 2014 article-title: Automation of workplace lifting hazard assessment for musculoskeletal injury prevention publication-title: Annals of Occupational and Environmental Medicine – volume: 59 start-page: 1514 year: 2016 end-page: 1525 article-title: Measuring elemental time and duty cycle using automated video processing publication-title: Ergonomics – volume: 65 start-page: 541 year: 2017 end-page: 550 article-title: Using a marker-less method for estimating L5/S1 moments during symmetrical lifting publication-title: Applied Ergonomics – volume: 36 start-page: 489 issue: 4 year: 2005 end-page: 503 article-title: A survey of tools and methods used by certified professional ergonomists publication-title: Applied Ergonomics – volume: 29 start-page: 1393 issue: 10 year: 1996 end-page: 1397 article-title: Posture prediction for static sagittal-plane lifting publication-title: Journal of Biomechanics – volume: 49 start-page: 381 issue: 4 year: 2006 end-page: 392 article-title: Quantifying repetitive hand activity for epidemiological research on musculoskeletal disorders–Part II: Comparison of different methods of measuring force level and repetitiveness publication-title: Ergonomics – volume: 42 start-page: 944 issue: 9 year: 1995 end-page: 948 article-title: A video-based system for acquiring biomechanical data synchronized with arbitrary events and activities publication-title: IEEE Transactions on Biomedical Engineering – volume: 49 start-page: 155 issue: 3 year: 1999 end-page: 160 article-title: Smoking, heavy physical work and low back pain: A four-year prospective study publication-title: Occupational Medicine – volume: 53 start-page: 285 issue: 3 year: 2010 end-page: 323 article-title: Risk factors for work-related musculoskeletal disorders: A systematic review of recent longitudinal studies publication-title: American Journal of Industrial Medicine – volume: 4 start-page: 41 issue: 1 year: 2008 end-page: 74 article-title: Digital human modeling for workspace design publication-title: Reviews of Human Factors and Ergonomics – volume: 18 start-page: 571 issue: 8 year: 1985 end-page: 584 article-title: A biomechanical model of the lumbosacral joint during lifting activities publication-title: Journal of Biomechanics – ident: bibr2-0018720818791367 – ident: bibr40-0018720818791367 – ident: bibr19-0018720818791367 doi: 10.1097/00007632-199206000-00006 – ident: bibr10-0018720818791367 doi: 10.1518/155723408X342844 – ident: bibr21-0018720818791367 doi: 10.2105/AJPH.91.7.1069 – ident: bibr11-0018720818791367 doi: 10.1177/0018720812458121 – ident: bibr7-0018720818791367 – ident: bibr23-0018720818791367 doi: 10.1061/41182(416)47 – ident: bibr37-0018720818791367 doi: 10.1186/2052-4374-26-15 – ident: bibr22-0018720818791367 doi: 10.1016/S0169-8141(02)00174-9 – ident: bibr14-0018720818791367 doi: 10.1016/0021-9290(96)00028-0 – volume-title: Classification and regression trees year: 1984 ident: bibr8-0018720818791367 – volume-title: Musculoskeletal disorders and the workplace: Low back and upper extremities year: 2001 ident: bibr5-0018720818791367 – ident: bibr17-0018720818791367 doi: 10.1016/j.apergo.2017.02.020 – ident: bibr32-0018720818791367 doi: 10.2105/AJPH.89.7.1036 – ident: bibr1-0018720818791367 doi: 10.1080/00140139.2016.1146347 – ident: bibr35-0018720818791367 – ident: bibr25-0018720818791367 doi: 10.1007/s11042-016-3469-0 – ident: bibr20-0018720818791367 doi: 10.1186/1471-2474-10-15 – ident: bibr41-0018720818791367 – ident: bibr13-0018720818791367 doi: 10.1016/j.apergo.2005.01.007 – ident: bibr6-0018720818791367 – ident: bibr24-0018720818791367 doi: 10.1177/0018720813513608 – ident: bibr3-0018720818791367 doi: 10.1016/0021-9290(85)90012-0 – ident: bibr18-0018720818791367 doi: 10.4271/2007-01-2480 – ident: bibr34-0018720818791367 doi: 10.1016/j.apergo.2016.10.015 – ident: bibr9-0018720818791367 doi: 10.1518/001872097778940632 – ident: bibr33-0018720818791367 – ident: bibr38-0018720818791367 – ident: bibr36-0018720818791367 doi: 10.1061/9780784479827.082 – ident: bibr44-0018720818791367 doi: 10.1109/10.412663 – ident: bibr43-0018720818791367 doi: 10.1109/CVPR.2007.383298 – ident: bibr4-0018720818791367 doi: 10.1080/00140130600555938 – ident: bibr12-0018720818791367 doi: 10.1002/ajim.20750 – ident: bibr31-0018720818791367 doi: 10.1016/j.apergo.2017.01.007 – ident: bibr28-0018720818791367 – ident: bibr27-0018720818791367 doi: 10.1097/00007632-199304000-00015 – ident: bibr39-0018720818791367 – ident: bibr42-0018720818791367 – ident: bibr26-0018720818791367 doi: 10.1080/00140139508925111 – ident: bibr15-0018720818791367 doi: 10.1093/occmed/49.3.155 – volume-title: 2012 anthropometric survey of U.S. Army personnel: Methods and summary statistics year: 2014 ident: bibr16-0018720818791367 – ident: bibr29-0018720818791367 doi: 10.1109/FG.2018.00078 – ident: bibr30-0018720818791367 doi: 10.1016/j.jbiomech.2018.01.012
SSID	ssj0006935
Score	2.2865193
Snippet	Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an... A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an "elastic"... Objective:A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an...
SourceID	proquest pubmed crossref sage
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	64
SubjectTerms	Algorithms Anthropometry Biomechanical Phenomena Body measurements Cameras Classification Computer vision Decision Trees Hoisting Humans Image classification Lifting Manikins Obstructions Posture - physiology Regression analysis Reproducibility of Results Smartphones Task Performance and Analysis Video data
Title	Predicting Sagittal Plane Lifting Postures From Image Bounding Box Dimensions
URI	https://journals.sagepub.com/doi/full/10.1177/0018720818791367 https://www.ncbi.nlm.nih.gov/pubmed/30091947 https://www.proquest.com/docview/2161234675 https://www.proquest.com/docview/2087588492
Volume	61
WOSCitedRecordID	wos000454502100006&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: PRVSPB databaseName: SAGE HSS 2015 customDbUrl: eissn: 1547-8181 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006935 issn: 0018-7208 databaseCode: AEVPJ dateStart: 19990301 isFulltext: true titleUrlDefault: http://journals.sagepub.com/ providerName: SAGE Publications
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwvV1LT9wwEB7B0gMcoKUFtlDkSlWlHtLdOHYcnyqgrNqqRSv1ob1FE8epVuruomyC4N_jyYsCasWJq-3Y8fuzZ_x9AG-y1JqA3AaFCdATIWoPeRZ4oUMjdCBJhpmpxCbU2Vk0mejxCszbtzBNCy7fk1uV-6NqsabZTbfRg8bIOKik5DixsSlNnGMfymIW17fdragGhZB5upyRZduQP-SV175uW4U1B8V92YO1o9Nf4y_d2h3qoNE8iDwq4Mawea_M2xvZPXR6yzOs2qxGW49dzaew2cBadlSPw2ewYufbsPEX2eE2rHdr7dVz-DbOyUJEPtfsO_6eFu4MwEhAybKv06wKJhnhMrdLNsoXM_Z55qrAjkkEiiKPF5fsIwkT0GXf8gX8HJ3-OPnkNcoOnhGhLLwkURYdVDMhCmmCJELUUqLUyK3hPvoKUzW0KjKZ0GkahhhkVjgsaSMirLHBDvTmi7ndA4ah5r4VPkpFNl6SMMU0SRWXyFGptA-Dtpti09Cek_rGn9hvmc7vtHIf3nVfnNeUH_9Je9D2fNz2acx94rRxO5Dsw-su2k1bssW4hlyULg0pCUSR0LwPu_WI6QoLHO71tXCZv6XhcZPxv_7i5UMT7sO6A3y69jo_gF6Rl_YVPDEXxXSZH8KqmkSHzZS4Bs9iGs4
linkProvider	SAGE Publications
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ZS8NAEB60CtYH76OeK4jgQ7TZbLLZR6_iUUvBA9_CZLORgrbSQ_Tfu9Om8UIRfM0eGWb2-JIZvg9gO02M9qhsUGgPHRGgcpCnnhNYNEIfJHE51X2xCVmrhXd3qv5B6ivzYGePyqqsRf3DOt_dxJREKnKciNikIrqxURgTFrWXCzB2cHJbP8-P4UB5mXxB6NCA9xzltzk-30nfgOanIq_-vVOZ_ofFMzCVgU12MFgdszBimnMw-YGCcA6K-Qn4Og-X9TblbagSml3hfaNrkTkjWSPDqo20_5jEfXv2E51V2q1HdvZorWGHJM1EjYetF3ZMcgH0C66zADeVk-ujUyfTW3C0CPyuE8fSoAVQOkDhay8OEZXvo6-QG81ddCUmsmxkqFOhkiQI0EuNsAjPhEQjY7xFKDRbTbMMDAPFXSNc9CVlXklYFJM4kdxHjlImJdgfejzSGRk5aWI8RO6Qf_yL10qwm494GhBx_NJ3bRjEaBieiLvENGPvBb8EW3mz3UyUIbGObPVsH-L3D0OheAmWBsHPX-ZZNOoqYSffoUi_T_yTFSt_7bgJE6fXl9Woela7WIWihWRqUBe-BoVuu2fWYVw_dxud9ka2xt8ASZ3xyQ
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Za9tAEB5Su5TkIWndNHHiJlsohT4otlYrrfYxiW3ixjWGHuRNjFarYKgPfIT232dHluW4pqXQV-2hYfb6VjP6PoD3aWK0R2mDQnvoiACVgzz1nMCiEbqQxI1UZ2ITstcL7-5UP8_NoX9hcg_OLiitylqUbda0uidJWs9jjPVMSY4TGZtURDn2DMr2VtPgJShftr73PxVbcaC8XMIgdKjBOk651cfmubQFNjcSvbKzp33wn1a_hP0cdLLL5Sx5BTtmVIG9J1SEFdgtdsJfr-Fzf0rxG8qIZl_wfjC3CJ2RvJFh3UGaPSaR34W9qrP2dDxknaG1iF2RRBMVXo1_sibJBtCnuNkhfGu3vl7fOLnugqNF4M-dOJYGLZDSAQpfe3GIqHwffYXcaO6iKzGRDSNDnQqVJEGAXmqERXomJDoZ472B0mg8MsfAMFDcNcJFX1IElgRGMYkTyX3kKGVShfrK65HOSclJG-NH5K54yH_zWhU-Fi0mS0KOv9StrQYyWg1RxF1inLHng1-Fd0WxXVQUKbGOHC9sHeL5D0OheBWOlhOgeJlnUamrhO38A432uuM_WXHyrxXP4UW_2Y66nd7tKexaZKaW6eE1KM2nC_MWnuuH-WA2Pcun-SNjLvQ9
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=Predicting+Sagittal+Plane+Lifting+Postures+From+Image+Bounding+Box+Dimensions&rft.jtitle=Human+factors&rft.au=Greene%2C+Runyu+L.&rft.au=Hu%2C+Yu+Hen&rft.au=Difranco%2C+Nicholas&rft.au=Wang%2C+Xuan&rft.date=2019-02-01&rft.issn=0018-7208&rft.eissn=1547-8181&rft.volume=61&rft.issue=1&rft.spage=64&rft.epage=77&rft_id=info:doi/10.1177%2F0018720818791367&rft.externalDBID=n%2Fa&rft.externalDocID=10_1177_0018720818791367
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-7208&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-7208&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-7208&client=summon