Video stabilization using regularity of energy flow View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2017-05-22

AUTHORS

Rupesh Kumar, Afaque Azam, S. Gupta, K. S. Venkatesh

ABSTRACT

Jitter and shaky movements of camera are primarily responsible for video destabilization. Such movements usually produce an irregularity in the flow vectors of frames. Video stabilization technique aims to regularize the irregularity of flow vectors. In this paper, an energy-based motion smoothing approach is proposed to smooth the flow vectors using energy of frames. Energy regularity of frames assures a stabilized video while their irregularity causes a destabilized video. Flow vector estimation, motion smoothing and motion compensation are the three primary steps needed for video stabilization. Performance of the stabilization technique depends on each of the above steps, and an optimal method is sought to enhance the performance. In the proposed method, we estimate both the translational and affine flow vectors of a frame using the spatio-temporal regularity flow model. This model provides the approximated flow vectors of all pixels in a frame by minimizing its flow energy function. In the proposed approach, we estimate the flow vectors of the feature points of the maximally stable extremal region of each frame rather than all the pixels of a frame. The proposed video stabilization method is compared with existing state of art methods on the basis of inter-frame transform fidelity, correlation coefficient, regularity and energy of frames. The stability results achieved validate the robustness of the proposed algorithm. More... »

PAGES

1519-1526

References to SciGraph publications

  • 2013-12-06. A robust video stabilization technique using integral frame projection warping in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2014-04-05. Video stabilization with moving object detecting and tracking for aerial video surveillance in MULTIMEDIA TOOLS AND APPLICATIONS
  • 2011-02-16. Consistent image alignment for video mosaicing in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2012-04-29. Video stabilization using maximally stable extremal region features in MULTIMEDIA TOOLS AND APPLICATIONS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11760-017-1115-6

    DOI

    http://dx.doi.org/10.1007/s11760-017-1115-6

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1085559230


    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": "Department of Electrical Engineering, IIT Kanpur, Kanpur, India", 
              "id": "http://www.grid.ac/institutes/grid.417965.8", 
              "name": [
                "Department of Electrical Engineering, IIT Kanpur, Kanpur, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kumar", 
            "givenName": "Rupesh", 
            "id": "sg:person.011273510625.49", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011273510625.49"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Electrical Engineering, IIT Kanpur, Kanpur, India", 
              "id": "http://www.grid.ac/institutes/grid.417965.8", 
              "name": [
                "Department of Electrical Engineering, IIT Kanpur, Kanpur, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Azam", 
            "givenName": "Afaque", 
            "id": "sg:person.07653603004.68", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07653603004.68"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Electrical Engineering, IIT Kanpur, Kanpur, India", 
              "id": "http://www.grid.ac/institutes/grid.417965.8", 
              "name": [
                "Department of Electrical Engineering, IIT Kanpur, Kanpur, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gupta", 
            "givenName": "S.", 
            "id": "sg:person.011025441437.10", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011025441437.10"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Electrical Engineering, IIT Kanpur, Kanpur, India", 
              "id": "http://www.grid.ac/institutes/grid.417965.8", 
              "name": [
                "Department of Electrical Engineering, IIT Kanpur, Kanpur, India"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Venkatesh", 
            "givenName": "K. S.", 
            "id": "sg:person.011234155127.57", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011234155127.57"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11042-012-1095-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1021357721", 
              "https://doi.org/10.1007/s11042-012-1095-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-011-0212-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013742089", 
              "https://doi.org/10.1007/s11760-011-0212-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11042-014-1928-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023832557", 
              "https://doi.org/10.1007/s11042-014-1928-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-013-0584-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032969510", 
              "https://doi.org/10.1007/s11760-013-0584-5"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-05-22", 
        "datePublishedReg": "2017-05-22", 
        "description": "Jitter and shaky movements of camera are primarily responsible for video destabilization. Such movements usually produce an irregularity in the flow vectors of frames. Video stabilization technique aims to regularize the irregularity of flow vectors. In this paper, an energy-based motion smoothing approach is proposed to smooth the flow vectors using energy of frames. Energy regularity of frames assures a stabilized video while their irregularity causes a destabilized video. Flow vector estimation, motion smoothing and motion compensation are the three primary steps needed for video stabilization. Performance of the stabilization technique depends on each of the above steps, and an optimal method is sought to enhance the performance. In the proposed method, we estimate both the translational and affine flow vectors of a frame using the spatio-temporal regularity flow model. This model provides the approximated flow vectors of all pixels in a frame by minimizing its flow energy function. In the proposed approach, we estimate the flow vectors of the feature points of the maximally stable extremal region of each frame rather than all the pixels of a frame. The proposed video stabilization method is compared with existing state of art methods on the basis of inter-frame transform fidelity, correlation coefficient, regularity and energy of frames. The stability results achieved validate the robustness of the proposed algorithm.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11760-017-1115-6", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1050964", 
            "issn": [
              "1863-1703", 
              "1863-1711"
            ], 
            "name": "Signal, Image and Video Processing", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "8", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "11"
          }
        ], 
        "keywords": [
          "flow vectors", 
          "stability results", 
          "motion smoothing", 
          "stabilization technique", 
          "video stabilization", 
          "flow model", 
          "vector estimation", 
          "energy function", 
          "stabilization method", 
          "video stabilization method", 
          "regularity", 
          "energy flow", 
          "art methods", 
          "vector", 
          "optimal method", 
          "motion compensation", 
          "above steps", 
          "energy regularity", 
          "model", 
          "video stabilization technique", 
          "motion", 
          "smoothing", 
          "estimation", 
          "feature points", 
          "robustness", 
          "algorithm", 
          "irregularities", 
          "approach", 
          "energy", 
          "frame", 
          "technique", 
          "stabilization", 
          "flow", 
          "coefficient", 
          "performance", 
          "point", 
          "step", 
          "function", 
          "fidelity", 
          "video", 
          "pixels", 
          "state", 
          "correlation coefficient", 
          "compensation", 
          "results", 
          "method", 
          "Stable Extremal Regions", 
          "primary step", 
          "basis", 
          "extremal regions", 
          "region", 
          "camera", 
          "movement", 
          "paper", 
          "such movements", 
          "destabilization", 
          "shaky movements"
        ], 
        "name": "Video stabilization using regularity of energy flow", 
        "pagination": "1519-1526", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1085559230"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11760-017-1115-6"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11760-017-1115-6", 
          "https://app.dimensions.ai/details/publication/pub.1085559230"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-12-01T06:36", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/article/article_747.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11760-017-1115-6"
      }
    ]
     

    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/s11760-017-1115-6'

    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/s11760-017-1115-6'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11760-017-1115-6'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11760-017-1115-6'


     

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

    151 TRIPLES      21 PREDICATES      85 URIs      73 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11760-017-1115-6 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N0bb7d8f8ad534d808ff8a853e191898d
    4 schema:citation sg:pub.10.1007/s11042-012-1095-z
    5 sg:pub.10.1007/s11042-014-1928-z
    6 sg:pub.10.1007/s11760-011-0212-1
    7 sg:pub.10.1007/s11760-013-0584-5
    8 schema:datePublished 2017-05-22
    9 schema:datePublishedReg 2017-05-22
    10 schema:description Jitter and shaky movements of camera are primarily responsible for video destabilization. Such movements usually produce an irregularity in the flow vectors of frames. Video stabilization technique aims to regularize the irregularity of flow vectors. In this paper, an energy-based motion smoothing approach is proposed to smooth the flow vectors using energy of frames. Energy regularity of frames assures a stabilized video while their irregularity causes a destabilized video. Flow vector estimation, motion smoothing and motion compensation are the three primary steps needed for video stabilization. Performance of the stabilization technique depends on each of the above steps, and an optimal method is sought to enhance the performance. In the proposed method, we estimate both the translational and affine flow vectors of a frame using the spatio-temporal regularity flow model. This model provides the approximated flow vectors of all pixels in a frame by minimizing its flow energy function. In the proposed approach, we estimate the flow vectors of the feature points of the maximally stable extremal region of each frame rather than all the pixels of a frame. The proposed video stabilization method is compared with existing state of art methods on the basis of inter-frame transform fidelity, correlation coefficient, regularity and energy of frames. The stability results achieved validate the robustness of the proposed algorithm.
    11 schema:genre article
    12 schema:isAccessibleForFree false
    13 schema:isPartOf N58770970be984d87875b871113bf39c7
    14 Nc8bae21efa7446eaac00db0f73a0d10b
    15 sg:journal.1050964
    16 schema:keywords Stable Extremal Regions
    17 above steps
    18 algorithm
    19 approach
    20 art methods
    21 basis
    22 camera
    23 coefficient
    24 compensation
    25 correlation coefficient
    26 destabilization
    27 energy
    28 energy flow
    29 energy function
    30 energy regularity
    31 estimation
    32 extremal regions
    33 feature points
    34 fidelity
    35 flow
    36 flow model
    37 flow vectors
    38 frame
    39 function
    40 irregularities
    41 method
    42 model
    43 motion
    44 motion compensation
    45 motion smoothing
    46 movement
    47 optimal method
    48 paper
    49 performance
    50 pixels
    51 point
    52 primary step
    53 region
    54 regularity
    55 results
    56 robustness
    57 shaky movements
    58 smoothing
    59 stability results
    60 stabilization
    61 stabilization method
    62 stabilization technique
    63 state
    64 step
    65 such movements
    66 technique
    67 vector
    68 vector estimation
    69 video
    70 video stabilization
    71 video stabilization method
    72 video stabilization technique
    73 schema:name Video stabilization using regularity of energy flow
    74 schema:pagination 1519-1526
    75 schema:productId N3ca2ded50bfc4d8685dd1a88a20b3e29
    76 Ne44659df237e4320936d7989742f5c20
    77 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085559230
    78 https://doi.org/10.1007/s11760-017-1115-6
    79 schema:sdDatePublished 2022-12-01T06:36
    80 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    81 schema:sdPublisher N5a3eea7568e141ee9bbdb1f01f5d963c
    82 schema:url https://doi.org/10.1007/s11760-017-1115-6
    83 sgo:license sg:explorer/license/
    84 sgo:sdDataset articles
    85 rdf:type schema:ScholarlyArticle
    86 N0bb7d8f8ad534d808ff8a853e191898d rdf:first sg:person.011273510625.49
    87 rdf:rest N0ff047d20ef840169b9ba22bac6845a8
    88 N0ff047d20ef840169b9ba22bac6845a8 rdf:first sg:person.07653603004.68
    89 rdf:rest N68bbaa4e14b5445582ec08b39eaa8e7e
    90 N3ca2ded50bfc4d8685dd1a88a20b3e29 schema:name dimensions_id
    91 schema:value pub.1085559230
    92 rdf:type schema:PropertyValue
    93 N58770970be984d87875b871113bf39c7 schema:issueNumber 8
    94 rdf:type schema:PublicationIssue
    95 N5a3eea7568e141ee9bbdb1f01f5d963c schema:name Springer Nature - SN SciGraph project
    96 rdf:type schema:Organization
    97 N68bbaa4e14b5445582ec08b39eaa8e7e rdf:first sg:person.011025441437.10
    98 rdf:rest Nab260ad52abd40bfbad800a9990ebecb
    99 Nab260ad52abd40bfbad800a9990ebecb rdf:first sg:person.011234155127.57
    100 rdf:rest rdf:nil
    101 Nc8bae21efa7446eaac00db0f73a0d10b schema:volumeNumber 11
    102 rdf:type schema:PublicationVolume
    103 Ne44659df237e4320936d7989742f5c20 schema:name doi
    104 schema:value 10.1007/s11760-017-1115-6
    105 rdf:type schema:PropertyValue
    106 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    107 schema:name Information and Computing Sciences
    108 rdf:type schema:DefinedTerm
    109 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    110 schema:name Artificial Intelligence and Image Processing
    111 rdf:type schema:DefinedTerm
    112 sg:journal.1050964 schema:issn 1863-1703
    113 1863-1711
    114 schema:name Signal, Image and Video Processing
    115 schema:publisher Springer Nature
    116 rdf:type schema:Periodical
    117 sg:person.011025441437.10 schema:affiliation grid-institutes:grid.417965.8
    118 schema:familyName Gupta
    119 schema:givenName S.
    120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011025441437.10
    121 rdf:type schema:Person
    122 sg:person.011234155127.57 schema:affiliation grid-institutes:grid.417965.8
    123 schema:familyName Venkatesh
    124 schema:givenName K. S.
    125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011234155127.57
    126 rdf:type schema:Person
    127 sg:person.011273510625.49 schema:affiliation grid-institutes:grid.417965.8
    128 schema:familyName Kumar
    129 schema:givenName Rupesh
    130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011273510625.49
    131 rdf:type schema:Person
    132 sg:person.07653603004.68 schema:affiliation grid-institutes:grid.417965.8
    133 schema:familyName Azam
    134 schema:givenName Afaque
    135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07653603004.68
    136 rdf:type schema:Person
    137 sg:pub.10.1007/s11042-012-1095-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1021357721
    138 https://doi.org/10.1007/s11042-012-1095-z
    139 rdf:type schema:CreativeWork
    140 sg:pub.10.1007/s11042-014-1928-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1023832557
    141 https://doi.org/10.1007/s11042-014-1928-z
    142 rdf:type schema:CreativeWork
    143 sg:pub.10.1007/s11760-011-0212-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013742089
    144 https://doi.org/10.1007/s11760-011-0212-1
    145 rdf:type schema:CreativeWork
    146 sg:pub.10.1007/s11760-013-0584-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032969510
    147 https://doi.org/10.1007/s11760-013-0584-5
    148 rdf:type schema:CreativeWork
    149 grid-institutes:grid.417965.8 schema:alternateName Department of Electrical Engineering, IIT Kanpur, Kanpur, India
    150 schema:name Department of Electrical Engineering, IIT Kanpur, Kanpur, India
    151 rdf:type schema:Organization
     




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


    ...