Dynamic stereo vision:
Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or '...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Pittsburgh, Pa.
1989
|
| Series: | Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS
89,195 |
| Subjects: | |
| Summary: | Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or 'depth' of objects visible to a robot, as well as to estimate the motion of the robot as it travels through an unknown environment. We begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or 'landmarks'. We formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences In laboratory experiments, this system has achieved an accuracy of 2% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, we address the problem of estimating 'depth maps' from stereo images. Depth maps specify scene depth for each pixel in the image. We propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system Depth estimates obtained from this image pair are used to 'bootstrap' matching of a wide-baseline image pair acquired with both cameras of the stereo system. We formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair forms the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with scale models of complex, outdoor scenes demonstrate the power of the approach. |
| Item Description: | Pittsburgh, Pa., Carnegie-Mellon Univ., Diss. |
| Physical Description: | VII, 161 S. Ill., graph. Darst. |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV004173507 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 901212s1989 ad|| m||| 00||| eng d | ||
| 035 | |a (OCoLC)21387338 | ||
| 035 | |a (DE-599)BVBBV004173507 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 082 | 0 | |a 510.7808 |b C28r 89-195 | |
| 084 | |a DAT 760d |2 stub | ||
| 088 | |a CMU CS 89 195 | ||
| 100 | 1 | |a Matthies, Larry |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Dynamic stereo vision |
| 246 | 1 | 3 | |a CMU CS 89 195 |
| 264 | 1 | |a Pittsburgh, Pa. |c 1989 | |
| 300 | |a VII, 161 S. |b Ill., graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS |v 89,195 | |
| 500 | |a Pittsburgh, Pa., Carnegie-Mellon Univ., Diss. | ||
| 520 | 3 | |a Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or 'depth' of objects visible to a robot, as well as to estimate the motion of the robot as it travels through an unknown environment. We begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or 'landmarks'. We formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences | |
| 520 | 3 | |a In laboratory experiments, this system has achieved an accuracy of 2% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, we address the problem of estimating 'depth maps' from stereo images. Depth maps specify scene depth for each pixel in the image. We propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system | |
| 520 | 3 | |a Depth estimates obtained from this image pair are used to 'bootstrap' matching of a wide-baseline image pair acquired with both cameras of the stereo system. We formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair forms the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with scale models of complex, outdoor scenes demonstrate the power of the approach. | |
| 650 | 4 | |a Robot vision | |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 810 | 2 | |a Computer Science Department: CMU-CS |t Carnegie-Mellon University <Pittsburgh, Pa.> |v 89,195 |w (DE-604)BV006187264 |9 89,195 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-002602000 | ||
Record in the Search Index
| _version_ | 1804118383785934848 |
|---|---|
| any_adam_object | |
| author | Matthies, Larry |
| author_facet | Matthies, Larry |
| author_role | aut |
| author_sort | Matthies, Larry |
| author_variant | l m lm |
| building | Verbundindex |
| bvnumber | BV004173507 |
| classification_tum | DAT 760d |
| ctrlnum | (OCoLC)21387338 (DE-599)BVBBV004173507 |
| dewey-full | 510.7808 |
| dewey-hundreds | 500 - Natural sciences and mathematics |
| dewey-ones | 510 - Mathematics |
| dewey-raw | 510.7808 |
| dewey-search | 510.7808 |
| dewey-sort | 3510.7808 |
| dewey-tens | 510 - Mathematics |
| discipline | Informatik Mathematik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03436nam a2200373 cb4500</leader><controlfield tag="001">BV004173507</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">901212s1989 ad|| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)21387338</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV004173507</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">510.7808</subfield><subfield code="b">C28r 89-195</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 760d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="088" ind1=" " ind2=" "><subfield code="a">CMU CS 89 195</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Matthies, Larry</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Dynamic stereo vision</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">CMU CS 89 195</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Pittsburgh, Pa.</subfield><subfield code="c">1989</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">VII, 161 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="490" ind1="1" ind2=" "><subfield code="a">Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS</subfield><subfield code="v">89,195</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Pittsburgh, Pa., Carnegie-Mellon Univ., Diss.</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or 'depth' of objects visible to a robot, as well as to estimate the motion of the robot as it travels through an unknown environment. We begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or 'landmarks'. We formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">In laboratory experiments, this system has achieved an accuracy of 2% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, we address the problem of estimating 'depth maps' from stereo images. Depth maps specify scene depth for each pixel in the image. We propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Depth estimates obtained from this image pair are used to 'bootstrap' matching of a wide-baseline image pair acquired with both cameras of the stereo system. We formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair forms the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with scale models of complex, outdoor scenes demonstrate the power of the approach.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Robot vision</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="810" ind1="2" ind2=" "><subfield code="a">Computer Science Department: CMU-CS</subfield><subfield code="t">Carnegie-Mellon University <Pittsburgh, Pa.></subfield><subfield code="v">89,195</subfield><subfield code="w">(DE-604)BV006187264</subfield><subfield code="9">89,195</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-002602000</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV004173507 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T16:09:26Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-002602000 |
| oclc_num | 21387338 |
| open_access_boolean | |
| physical | VII, 161 S. Ill., graph. Darst. |
| publishDate | 1989 |
| publishDateSearch | 1989 |
| publishDateSort | 1989 |
| record_format | marc |
| series2 | Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS |
| spelling | Matthies, Larry Verfasser aut Dynamic stereo vision CMU CS 89 195 Pittsburgh, Pa. 1989 VII, 161 S. Ill., graph. Darst. txt rdacontent n rdamedia nc rdacarrier Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS 89,195 Pittsburgh, Pa., Carnegie-Mellon Univ., Diss. Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or 'depth' of objects visible to a robot, as well as to estimate the motion of the robot as it travels through an unknown environment. We begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or 'landmarks'. We formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences In laboratory experiments, this system has achieved an accuracy of 2% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, we address the problem of estimating 'depth maps' from stereo images. Depth maps specify scene depth for each pixel in the image. We propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system Depth estimates obtained from this image pair are used to 'bootstrap' matching of a wide-baseline image pair acquired with both cameras of the stereo system. We formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair forms the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with scale models of complex, outdoor scenes demonstrate the power of the approach. Robot vision (DE-588)4113937-9 Hochschulschrift gnd-content Computer Science Department: CMU-CS Carnegie-Mellon University <Pittsburgh, Pa.> 89,195 (DE-604)BV006187264 89,195 |
| spellingShingle | Matthies, Larry Dynamic stereo vision Robot vision |
| subject_GND | (DE-588)4113937-9 |
| title | Dynamic stereo vision |
| title_alt | CMU CS 89 195 |
| title_auth | Dynamic stereo vision |
| title_exact_search | Dynamic stereo vision |
| title_full | Dynamic stereo vision |
| title_fullStr | Dynamic stereo vision |
| title_full_unstemmed | Dynamic stereo vision |
| title_short | Dynamic stereo vision |
| title_sort | dynamic stereo vision |
| topic | Robot vision |
| topic_facet | Robot vision Hochschulschrift |
| volume_link | (DE-604)BV006187264 |
| work_keys_str_mv | AT matthieslarry dynamicstereovision AT matthieslarry cmucs89195 |