Realtime Edge Based Visual Inertial Odometry for MAV Teleoperation in Indoor Environments View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2017-10-13

AUTHORS

Juan José Tarrio, Sol Pedre

ABSTRACT

A working solution for control and teleoperation of Micro Aerial Vehicles using a frontal camera and an inertial measurement unit as sole sensors is presented. The system is an extension of an edge based visual odometry algorithm to integrate inertial sensors. A mixed tightly-loosely coupled approach is used, taking advantage of each sensor in this minimalistic setup, while keeping the complexity low. The system runs completely on board a MAV providing a semidense output that is more useful for navigation than the sparse maps generated by most feature based systems. To the best of the author’s knowledge, the system is the first semidense VO method running fully on board a MAV for vision in the loop control. An extensive evaluation of the method is presented using the EuRoC MAV dataset, that is specially targeted for MAV navigation in realistic situations. Some of the practical issues of teleoperation are also addressed, in particular how data is transmitted and presented to the user. Finally, real life experiments are included to illustrate the performance of the complete system and the teleoperation interface. More... »

PAGES

235-252

References to SciGraph publications

  • 2017-02-11. Combining Feature-Based and Direct Methods for Semi-dense Real-Time Stereo Visual Odometry in INTELLIGENT AUTONOMOUS SYSTEMS 14
  • 2014. LSD-SLAM: Large-Scale Direct Monocular SLAM in COMPUTER VISION – ECCV 2014
  • 2014-04-24. A Practical Multirobot Localization System in JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10846-017-0670-y

    DOI

    http://dx.doi.org/10.1007/s10846-017-0670-y

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1092212069


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina", 
              "id": "http://www.grid.ac/institutes/grid.466813.e", 
              "name": [
                "Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tarrio", 
            "givenName": "Juan Jos\u00e9", 
            "id": "sg:person.010477035077.79", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010477035077.79"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina", 
              "id": "http://www.grid.ac/institutes/grid.466813.e", 
              "name": [
                "Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Pedre", 
            "givenName": "Sol", 
            "id": "sg:person.014225022472.57", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014225022472.57"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-10605-2_54", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003628531", 
              "https://doi.org/10.1007/978-3-319-10605-2_54"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-48036-7_62", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1083755542", 
              "https://doi.org/10.1007/978-3-319-48036-7_62"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10846-014-0041-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045105129", 
              "https://doi.org/10.1007/s10846-014-0041-x"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-10-13", 
        "datePublishedReg": "2017-10-13", 
        "description": "A working solution for control and teleoperation of Micro Aerial Vehicles using a frontal camera and an inertial measurement unit as sole sensors is presented. The system is an extension of an edge based visual odometry algorithm to integrate inertial sensors. A mixed tightly-loosely coupled approach is used, taking advantage of each sensor in this minimalistic setup, while keeping the complexity low. The system runs completely on board a MAV providing a semidense output that is more useful for navigation than the sparse maps generated by most feature based systems. To the best of the author\u2019s knowledge, the system is the first semidense VO method running fully on board a MAV for vision in the loop control. An extensive evaluation of the method is presented using the EuRoC MAV dataset, that is specially targeted for MAV navigation in realistic situations. Some of the practical issues of teleoperation are also addressed, in particular how data is transmitted and presented to the user. Finally, real life experiments are included to illustrate the performance of the complete system and the teleoperation interface.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s10846-017-0670-y", 
        "inLanguage": "en", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1135942", 
            "issn": [
              "0921-0296", 
              "1573-0409"
            ], 
            "name": "Journal of Intelligent & Robotic Systems", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1-2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "90"
          }
        ], 
        "keywords": [
          "micro aerial vehicles", 
          "EuRoC MAV datasets", 
          "inertial measurement unit", 
          "visual odometry algorithm", 
          "Visual Inertial Odometry", 
          "MAV Navigation", 
          "aerial vehicles", 
          "measurement unit", 
          "inertial sensors", 
          "real life experiments", 
          "teleoperation interface", 
          "odometry algorithm", 
          "frontal camera", 
          "sparse map", 
          "Inertial Odometry", 
          "loop control", 
          "VO methods", 
          "sole sensor", 
          "extensive evaluation", 
          "sensors", 
          "life experiments", 
          "teleoperation", 
          "indoor environment", 
          "complete system", 
          "navigation", 
          "working solution", 
          "MAV", 
          "realistic situations", 
          "practical issues", 
          "odometry", 
          "system", 
          "users", 
          "algorithm", 
          "camera", 
          "datasets", 
          "vehicle", 
          "interface", 
          "complexity", 
          "setup", 
          "most features", 
          "board", 
          "vision", 
          "performance", 
          "method", 
          "environment", 
          "knowledge", 
          "solution", 
          "edge", 
          "maps", 
          "advantages", 
          "features", 
          "issues", 
          "output", 
          "extension", 
          "experiments", 
          "control", 
          "authors' knowledge", 
          "situation", 
          "units", 
          "data", 
          "approach", 
          "evaluation", 
          "minimalistic setup", 
          "semidense output", 
          "first semidense VO method", 
          "semidense VO method", 
          "MAV dataset", 
          "Realtime Edge Based Visual Inertial Odometry", 
          "Edge Based Visual Inertial Odometry", 
          "Based Visual Inertial Odometry", 
          "MAV Teleoperation"
        ], 
        "name": "Realtime Edge Based Visual Inertial Odometry for MAV Teleoperation in Indoor Environments", 
        "pagination": "235-252", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1092212069"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10846-017-0670-y"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10846-017-0670-y", 
          "https://app.dimensions.ai/details/publication/pub.1092212069"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2021-12-01T19:40", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/article/article_736.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s10846-017-0670-y"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s10846-017-0670-y'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10846-017-0670-y'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10846-017-0670-y'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10846-017-0670-y'


     

    This table displays all metadata directly associated to this object as RDF triples.

    148 TRIPLES      22 PREDICATES      99 URIs      88 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10846-017-0670-y schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nf78039c5e24946d090a3350bec99a6ad
    4 schema:citation sg:pub.10.1007/978-3-319-10605-2_54
    5 sg:pub.10.1007/978-3-319-48036-7_62
    6 sg:pub.10.1007/s10846-014-0041-x
    7 schema:datePublished 2017-10-13
    8 schema:datePublishedReg 2017-10-13
    9 schema:description A working solution for control and teleoperation of Micro Aerial Vehicles using a frontal camera and an inertial measurement unit as sole sensors is presented. The system is an extension of an edge based visual odometry algorithm to integrate inertial sensors. A mixed tightly-loosely coupled approach is used, taking advantage of each sensor in this minimalistic setup, while keeping the complexity low. The system runs completely on board a MAV providing a semidense output that is more useful for navigation than the sparse maps generated by most feature based systems. To the best of the author’s knowledge, the system is the first semidense VO method running fully on board a MAV for vision in the loop control. An extensive evaluation of the method is presented using the EuRoC MAV dataset, that is specially targeted for MAV navigation in realistic situations. Some of the practical issues of teleoperation are also addressed, in particular how data is transmitted and presented to the user. Finally, real life experiments are included to illustrate the performance of the complete system and the teleoperation interface.
    10 schema:genre article
    11 schema:inLanguage en
    12 schema:isAccessibleForFree false
    13 schema:isPartOf N697ef89b98f44980918fee3f1f60a305
    14 Nd13c39c98ef140268b22556018590d03
    15 sg:journal.1135942
    16 schema:keywords Based Visual Inertial Odometry
    17 Edge Based Visual Inertial Odometry
    18 EuRoC MAV datasets
    19 Inertial Odometry
    20 MAV
    21 MAV Navigation
    22 MAV Teleoperation
    23 MAV dataset
    24 Realtime Edge Based Visual Inertial Odometry
    25 VO methods
    26 Visual Inertial Odometry
    27 advantages
    28 aerial vehicles
    29 algorithm
    30 approach
    31 authors' knowledge
    32 board
    33 camera
    34 complete system
    35 complexity
    36 control
    37 data
    38 datasets
    39 edge
    40 environment
    41 evaluation
    42 experiments
    43 extension
    44 extensive evaluation
    45 features
    46 first semidense VO method
    47 frontal camera
    48 indoor environment
    49 inertial measurement unit
    50 inertial sensors
    51 interface
    52 issues
    53 knowledge
    54 life experiments
    55 loop control
    56 maps
    57 measurement unit
    58 method
    59 micro aerial vehicles
    60 minimalistic setup
    61 most features
    62 navigation
    63 odometry
    64 odometry algorithm
    65 output
    66 performance
    67 practical issues
    68 real life experiments
    69 realistic situations
    70 semidense VO method
    71 semidense output
    72 sensors
    73 setup
    74 situation
    75 sole sensor
    76 solution
    77 sparse map
    78 system
    79 teleoperation
    80 teleoperation interface
    81 units
    82 users
    83 vehicle
    84 vision
    85 visual odometry algorithm
    86 working solution
    87 schema:name Realtime Edge Based Visual Inertial Odometry for MAV Teleoperation in Indoor Environments
    88 schema:pagination 235-252
    89 schema:productId N3a1cea20d85c49bf97ea14ef94a9d058
    90 Nb9ebac146b9d4d7ca5792f428980c9e6
    91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092212069
    92 https://doi.org/10.1007/s10846-017-0670-y
    93 schema:sdDatePublished 2021-12-01T19:40
    94 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    95 schema:sdPublisher N0cf92231ee334d75b020f2f963348ae4
    96 schema:url https://doi.org/10.1007/s10846-017-0670-y
    97 sgo:license sg:explorer/license/
    98 sgo:sdDataset articles
    99 rdf:type schema:ScholarlyArticle
    100 N0cf92231ee334d75b020f2f963348ae4 schema:name Springer Nature - SN SciGraph project
    101 rdf:type schema:Organization
    102 N3a1cea20d85c49bf97ea14ef94a9d058 schema:name doi
    103 schema:value 10.1007/s10846-017-0670-y
    104 rdf:type schema:PropertyValue
    105 N697ef89b98f44980918fee3f1f60a305 schema:volumeNumber 90
    106 rdf:type schema:PublicationVolume
    107 Nb9ebac146b9d4d7ca5792f428980c9e6 schema:name dimensions_id
    108 schema:value pub.1092212069
    109 rdf:type schema:PropertyValue
    110 Nbf30d7fd301048818badaf62ffd91aa4 rdf:first sg:person.014225022472.57
    111 rdf:rest rdf:nil
    112 Nd13c39c98ef140268b22556018590d03 schema:issueNumber 1-2
    113 rdf:type schema:PublicationIssue
    114 Nf78039c5e24946d090a3350bec99a6ad rdf:first sg:person.010477035077.79
    115 rdf:rest Nbf30d7fd301048818badaf62ffd91aa4
    116 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    117 schema:name Information and Computing Sciences
    118 rdf:type schema:DefinedTerm
    119 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    120 schema:name Artificial Intelligence and Image Processing
    121 rdf:type schema:DefinedTerm
    122 sg:journal.1135942 schema:issn 0921-0296
    123 1573-0409
    124 schema:name Journal of Intelligent & Robotic Systems
    125 schema:publisher Springer Nature
    126 rdf:type schema:Periodical
    127 sg:person.010477035077.79 schema:affiliation grid-institutes:grid.466813.e
    128 schema:familyName Tarrio
    129 schema:givenName Juan José
    130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010477035077.79
    131 rdf:type schema:Person
    132 sg:person.014225022472.57 schema:affiliation grid-institutes:grid.466813.e
    133 schema:familyName Pedre
    134 schema:givenName Sol
    135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014225022472.57
    136 rdf:type schema:Person
    137 sg:pub.10.1007/978-3-319-10605-2_54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003628531
    138 https://doi.org/10.1007/978-3-319-10605-2_54
    139 rdf:type schema:CreativeWork
    140 sg:pub.10.1007/978-3-319-48036-7_62 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083755542
    141 https://doi.org/10.1007/978-3-319-48036-7_62
    142 rdf:type schema:CreativeWork
    143 sg:pub.10.1007/s10846-014-0041-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1045105129
    144 https://doi.org/10.1007/s10846-014-0041-x
    145 rdf:type schema:CreativeWork
    146 grid-institutes:grid.466813.e schema:alternateName Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina
    147 schema:name Instituto Balseiro - CNEA, 9500, Bustillo, Bariloche, Argentina
    148 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...