Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Abschlussarbeit Buch |
| Sprache: | English |
| Veröffentlicht: |
2012
|
| Schlagworte: | |
| Online-Zugang: | kostenfrei https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 Inhaltsverzeichnis |
| Beschreibung: | XVI, 151 S. Ill., graph. Darst. |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV040897324 | ||
| 003 | DE-604 | ||
| 005 | 20130416 | ||
| 007 | t | ||
| 008 | 130319s2012 ad|| m||| 00||| eng d | ||
| 035 | |a (OCoLC)835632278 | ||
| 035 | |a (DE-599)BVBBV040897324 | ||
| 040 | |a DE-604 |b ger |e rakwb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-384 |a DE-473 |a DE-703 |a DE-1051 |a DE-824 |a DE-29 |a DE-12 |a DE-91 |a DE-19 |a DE-1049 |a DE-92 |a DE-739 |a DE-898 |a DE-355 |a DE-706 |a DE-20 |a DE-1102 |a DE-91G | ||
| 084 | |a DAT 260d |2 stub | ||
| 084 | |a DAT 770d |2 stub | ||
| 084 | |a DAT 815d |2 stub | ||
| 084 | |a DAT 708d |2 stub | ||
| 084 | |a DAT 760d |2 stub | ||
| 100 | 1 | |a Nair, Suraj |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems |c Suraj Nair |
| 264 | 1 | |c 2012 | |
| 300 | |a XVI, 151 S. |b Ill., graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 502 | |a München, Techn. Univ., Diss., 2012 | ||
| 650 | 0 | 7 | |a Objektverfolgung |0 (DE-588)4311226-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Mensch-Maschine-System |0 (DE-588)4038662-4 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Objektverfolgung |0 (DE-588)4311226-2 |D s |
| 689 | 0 | 1 | |a Mensch-Maschine-System |0 (DE-588)4038662-4 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |o urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 |
| 856 | 4 | 1 | |u http://mediatum.ub.tum.de/node?id=1096345 |x Verlag |z kostenfrei |3 Volltext |
| 856 | 4 | |u https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 |x Resolving-System | |
| 856 | 4 | 2 | |m DNB Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=025876867&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 912 | |a ebook | ||
| 999 | |a oai:aleph.bib-bvb.de:BVB01-025876867 | ||
Datensatz im Suchindex
| _version_ | 1804150181821677568 |
|---|---|
| adam_text | IMAGE 1
CONTENTS
LIST O F FIGURES I X
1 INTRODUCTION 1
1.1 COMPUTER VISION FOR SENSOR DRIVEN ROBOTICS 2
1.1.1 VISUAL TRACKING 3
1.1.2 TVACKING HUMANS IN SHARED WORKSPACES 3
1.1.3 REQUIREMENTS IN REAL-WORLD SCENARIOS 4
1.1.4 SHORTCOMINGS OF EXISTING SYSTEMS 4
1.2 THESIS PROPOSAL 5
1.2.1 3D MULTIPLE HUMAN DETECTION AND TRACKING SYSTEM 6
1.2.2 ROBUSTNESS ENHANCEMENT BY MACHINE LEARNING 6
1.2.3 VALIDATION OF DIFFERENT ROBUSTNESS ASPECTS 7
1.2.4 GENERAL PURPOSE INTERFACE FOR STAND ALONE OPERATION 7
1.2.5 INTEGRATION WITH REAL-WORLD ROBOTIC SYSTEMS 7
1.3 DISCUSSION 8
1.4 THESIS CONTENTS 8
2 PRIOR A R T 9
2.1 HUMAN DETECTION AND TRACKING 9
2.1.1 SINGLE TARGET TVACKERS 10
2.1.2 SLIDING WINDOW TECHNIQUES 10
2.1.3 PART BASED MODELS 11
2.1.4 STEREO TVACKERS 11
2.1.5 HUMAN POSE TRACKERS 15
2.1.6 HUMAN TVACKING IN ROBOTIC SCENARIOS 15
2.2 MOTIVATION OF THE THESIS 16
III
HTTP://D-NB.INFO/1034631470
IMAGE 2
CONTENTS
3 MULTIPLE H U M A N TRACKING S Y S T E M 19
3.1 OVERVIEW 19
3.2 OPENTL LIBRARY FOR RIGID AND ARTICULATED OBJECT TRACKING 20
3.2.1 LIBRARY ARCHITECTURE 20
3.2.2 FUNCTIONAL ARCHITECTURE OF THE LIBRARY 21
3.3 SYSTEM METHODOLOGY 22
3.4 SYSTEM ARCHITECTURE 24
3.4.1 VISUAL INPUT SENSORS 24
3.4.2 TARGET MODELLING 24
3.4.3 VISUAL MODALITIES 25
3.4.4 BAYESIAN TRACKING 26
3.5 TVACKING PIPELINE 27
3.5.1 IMAGE ACQUISITION 27
3.5.2 PRE-PROCESSING OF SENSOR IMAGES 27
3.5.3 ON LINE TARGET DETECTION 29
3.5.4 OCCLUSION TESTING 30
3.5.5 TRACKER 32
3.6 GRAPHICAL USER INTERFACE 36
3.7 COMMUNICATION INTERFACE 37
3.8 DISCUSSION 38
4 MACHINE LEARNING T O ENHANCE TVACKING ROBUSTNESS 3 9
4.1 OVERVIEW 39
4.2 COLOUR STATISTICS QUALITY UNDER CHANGING LIGHTING CONDITIONS 40
4.3 BACKGROUND SUBTRACTION QUALITY UNDER CHANGING LIGHTING CONDITIONS 41
4.4 OPTICAL FLOW QUALITY DEPENDING ON TARGET MOTION BEHAVIOUR 42
4.5 MACHINE LEARNING TO ENHANCE VISUAL MODALITY PERFORMANCE 43
4.5.1 SUPERVISED MACHINE LEARNING 43
4.5.1.1 GENERAL FORMULATION 44
4.5.1.2 MULTI CLASS SUPPORT VECTOR MACHINES 46
4.5.2 SUPERVISED MACHINE LEARNING TO MODEL LIGHTING CONDITIONS 46
4.5.3 CLASSIFICATION OF LIGHTING CONDITIONS IN TRACKING ENVIRONMENTS 49
4.5.4 BACKGROUND MODEL UPDATE IN THE PRESENCE OF FOREGROUND TARGETS . .
. . 51
4.6 MODALITY WEIGHT GENERATION FOR MULTI-MODAL FUSION 54
IMAGE 3
CONTENTS
4.6.1 QUALITY CLASSIFICATION FOR COLOUR HISTOGRAMS 56
4.6.2 QUALITY CLASSIFICATION FOR OPTICAL FLOW 56
4.6.3 MULTI-MODAL FUSION DEPENDING ON CLASSIFICATION 57
4.7 DISCUSSION 59
5 EXPERIMENTS 6 1
5.1 ZERO ERROR GROUND LYUTH GENERATION 61
5.2 TRACKING ACCURACY OF TRAJECTORIES IN THE PRESENCE OF MULTIPLE
TARGETS 66
5.2.1 TRACKING WITH 4 TARGETS IN THE SCENE 66
5.2.2 TRACKING WITH 5 TARGETS IN THE SCENE WITH CLOSE MOTION 68
5.2.3 TVACKING WITH 3 TARGETS IN A REAL SCENE AND CONSTRAINED AREA 70
5.3 ROBUSTNESS OF TVACKING AND BACKGROUND MODEL UPDATE UNDER DRASTICALLY
CHANG
ING LIGHTING CONDITIONS 71
5.3.1 EXPERIMENT IN SIMULATE ENVIRONMENT . . . 71
5.3.2 EXPERIMENT IN REAL ENVIRONMENT 72
5.4 ROBUSTNESS OF OCCLUSION HANDLING IN PRESENCE OF TARGETS WITH SIMILAR
APPEARANCE 75
5.4.1 OCCLUSION HANDLING WITH SIMILAR TARGETS AND VERY CLOSE MOTION 75
5.4.2 OCCLUSION HANDLING WITH 3 TARGETS AND VERY CLOSE MOTION AND
DRESSED
IN BLACK CLOTHING 76
5.5 POSITIVE IMPACT OF MULTI-MODAL FUSION UNDER DRASTICALLY CHANGING
LIGHTING CON
DITIONS 78
5.6 DISCUSSION 81
6 INTEGRATION W I T H REAL-WORLD R O B O T I C S Y S T E M S 8 5
6.1 OVERVIEW 85
6.2 MULTIPLE HUMAN IVACKING AND FACE TVACKING FOR VISUAL SERVOING USING
ROBOTS . 85
6.2.1 OVERVIEW 85
6.2.2 2D FACE TRACKING OF MODERATORS 88
6.2.2.1 PRE-PROCESSING 89
6.2.2.2 TVACKER PREDICTION 89
6.2.2.3 CCD LIKELIHOOD FOR FEATURE LEVEL MATCHING 89
6.2.3 THE ROBOT SYSTEM 92
6.2.4 SELF STEERING STUDIO 93
6.2.5 DEMONSTRATION AND RESULTS 94
IMAGE 4
CONTENTS
6.3 HUMAN TRACKING FOR INTERACTION WITH 3D OBJECTS IN VIRTUAL-AUGMENTED
REALITY
T V STUDIOS 97
6.3.1 OVERVIEW 97
6.3.2 SYSTEM ARCHITECTURE 98
6.3.3 DEMONSTRATION AND RESULTS 101
6.4 HUMAN TRACKING FOR STEREO-SCOPIC RENDERING IN HDTV STUDIOS 102
6.4.1 OVERVIEW 102
6.4.2 SYSTEM ARCHITECTURE 103
6.4.3 DEMONSTRATION AND RESULTS 105
6.5 3D POSITION BASED VISUAL SERVOING OF MULTIPLE HUMANS 106
6.5.1 OVERVIEW 106
6.5.2 SYSTEM ARCHITECTURE 108
6.5.3 ROBOT CONTROL SYSTEM 110
6.5.3.1 TVAJECTORY PLANNING I L L
6.5.3.2 PAN AND TILT I L L
6.5.3.3 CAMERA FOV 112
6.5.3.4 PATH PLANNING 114
6.5.4 3D VISUALIZATION SYSTEM 114
6.5.5 REMOTE INTERFACE SYSTEM 114
6.5.6 DEMONSTRATION AND RESULTS 114
6.6 CLOSE RANGE HUMAN ROBOT INTERACTION 117
6.6.1 OVERVIEW 117
6.6.2 SYSTEM ARCHITECTURE 117
6.6.2.1 3D OBJECT DETECTION 119
6.6.2.2 3D HUMAN LYACKING SYSTEM 121
6.6.2.3 OBJECT-HUMAN ASSOCIATOR 121
6.6.2.4 ROBOT SYSTEM 122
6.6.2.5 TASK GENERATOR 122
6.6.2.6 SAFETY SYSTEM: 123
6.6.3 DEMONSTRATION AND RESULTS 123
IMAGE 5
C O N T E N T S
7 CONCLUSION 127
7.1 PRIMARY CONTRIBUTIONS OF THE THESIS 127
7.2 SHORTCOMINGS OF THE SYSTEM 128
7.3 PROPOSED FUTURE WORK 130
A A P P E N D I X 133
A.L SOFTWARE ARCHITECTURE 133
REFERENCES 135
|
| any_adam_object | 1 |
| author | Nair, Suraj |
| author_facet | Nair, Suraj |
| author_role | aut |
| author_sort | Nair, Suraj |
| author_variant | s n sn |
| building | Verbundindex |
| bvnumber | BV040897324 |
| classification_tum | DAT 260d DAT 770d DAT 815d DAT 708d DAT 760d |
| collection | ebook |
| ctrlnum | (OCoLC)835632278 (DE-599)BVBBV040897324 |
| discipline | Informatik |
| format | Thesis Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01964nam a2200445 c 4500</leader><controlfield tag="001">BV040897324</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20130416 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">130319s2012 ad|| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)835632278</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV040897324</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-384</subfield><subfield code="a">DE-473</subfield><subfield code="a">DE-703</subfield><subfield code="a">DE-1051</subfield><subfield code="a">DE-824</subfield><subfield code="a">DE-29</subfield><subfield code="a">DE-12</subfield><subfield code="a">DE-91</subfield><subfield code="a">DE-19</subfield><subfield code="a">DE-1049</subfield><subfield code="a">DE-92</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-898</subfield><subfield code="a">DE-355</subfield><subfield code="a">DE-706</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-1102</subfield><subfield code="a">DE-91G</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 260d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 770d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 815d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 708d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 760d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Nair, Suraj</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems</subfield><subfield code="c">Suraj Nair</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2012</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XVI, 151 S.</subfield><subfield code="b">Ill., graph. Darst.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="a">München, Techn. Univ., Diss., 2012</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Objektverfolgung</subfield><subfield code="0">(DE-588)4311226-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Mensch-Maschine-System</subfield><subfield code="0">(DE-588)4038662-4</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Objektverfolgung</subfield><subfield code="0">(DE-588)4311226-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Mensch-Maschine-System</subfield><subfield code="0">(DE-588)4038662-4</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="o">urn:nbn:de:bvb:91-diss-20121029-1096345-1-5</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://mediatum.ub.tum.de/node?id=1096345</subfield><subfield code="x">Verlag</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2=" "><subfield code="u">https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121029-1096345-1-5</subfield><subfield code="x">Resolving-System</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">DNB Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=025876867&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ebook</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-025876867</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV040897324 |
| illustrated | Illustrated |
| indexdate | 2024-07-10T00:34:51Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-025876867 |
| oclc_num | 835632278 |
| open_access_boolean | 1 |
| owner | DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 DE-91G DE-BY-TUM |
| owner_facet | DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 DE-91G DE-BY-TUM |
| physical | XVI, 151 S. Ill., graph. Darst. |
| psigel | ebook |
| publishDate | 2012 |
| publishDateSearch | 2012 |
| publishDateSort | 2012 |
| record_format | marc |
| spelling | Nair, Suraj Verfasser aut Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems Suraj Nair 2012 XVI, 151 S. Ill., graph. Darst. txt rdacontent n rdamedia nc rdacarrier München, Techn. Univ., Diss., 2012 Objektverfolgung (DE-588)4311226-2 gnd rswk-swf Mensch-Maschine-System (DE-588)4038662-4 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Objektverfolgung (DE-588)4311226-2 s Mensch-Maschine-System (DE-588)4038662-4 s DE-604 Erscheint auch als Online-Ausgabe urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 http://mediatum.ub.tum.de/node?id=1096345 Verlag kostenfrei Volltext https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 Resolving-System DNB Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=025876867&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Nair, Suraj Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems Objektverfolgung (DE-588)4311226-2 gnd Mensch-Maschine-System (DE-588)4038662-4 gnd |
| subject_GND | (DE-588)4311226-2 (DE-588)4038662-4 (DE-588)4113937-9 |
| title | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems |
| title_auth | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems |
| title_exact_search | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems |
| title_full | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems Suraj Nair |
| title_fullStr | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems Suraj Nair |
| title_full_unstemmed | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems Suraj Nair |
| title_short | Visual tracking of multiple humans with machine learning based robustness enhancement applied to real-world robotic systems |
| title_sort | visual tracking of multiple humans with machine learning based robustness enhancement applied to real world robotic systems |
| topic | Objektverfolgung (DE-588)4311226-2 gnd Mensch-Maschine-System (DE-588)4038662-4 gnd |
| topic_facet | Objektverfolgung Mensch-Maschine-System Hochschulschrift |
| url | http://mediatum.ub.tum.de/node?id=1096345 https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20121029-1096345-1-5 http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=025876867&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT nairsuraj visualtrackingofmultiplehumanswithmachinelearningbasedrobustnessenhancementappliedtorealworldroboticsystems |