Traffic flow detection and statistics via improved optical flow and connected region analysis View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2017-06-20

AUTHORS

Yanan Peng, Zhenxue Chen, Q. M. Jonathan Wu, Chengyun Liu

ABSTRACT

Moving vehicle detection plays an important role in intelligent transportation systems. One of the common methods used in moving vehicle detection is optical flow. However, conventional Horn–Schunck optical flow consumes too much time when calculating dense optical flows so that it cannot meet the real-time requirements. This paper proposes a novel improved Horn–Schunck optical flow algorithm based on inter-frame differential method. In our algorithm, optical flow field distribution is only calculated for pixels with larger gray values in the difference image, while for other pixels we applied the iterative smooth. The number of vehicles in the videos of traffic conditions is counted by setting the virtual loop and detecting optical flow information. To extract the moving vehicle as accurately as possible, we also propose a method to obtain moving vehicle minimum bounding rectangle based on the connected region analysis. Finally, we compare the improved optical flow with other four optical flow algorithms in moving vehicle extraction and vehicle flow detection, from which our method gives a much more accurate result. More... »

PAGES

99-105

References to SciGraph publications

  • 2012-11-16. Recognizing 50 human action categories of web videos in MACHINE VISION AND APPLICATIONS
  • 2004. High Accuracy Optical Flow Estimation Based on a Theory for Warping in COMPUTER VISION - ECCV 2004
  • 2011-02-02. The Color Monogenic Signal: Application to Color Edge Detection and Color Optical Flow in JOURNAL OF MATHEMATICAL IMAGING AND VISION
  • 2015-03-31. Sparsity in optical flow and trajectories in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2014-12-25. A phase-based framework for optical flow estimation on omnidirectional images in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2014-07-24. Optical flow-motion history image (OF-MHI) for action recognition in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2012-12-18. Symmetric synchronous stream encryption using images in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2013-12-14. High accuracy optical flow estimation based on PDE decomposition in SIGNAL, IMAGE AND VIDEO PROCESSING
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11760-017-1135-2

    DOI

    http://dx.doi.org/10.1007/s11760-017-1135-2

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1086102249


    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": "School of Control Science and Engineering, Shandong University, 250061, Jinan, China", 
              "id": "http://www.grid.ac/institutes/grid.27255.37", 
              "name": [
                "School of Control Science and Engineering, Shandong University, 250061, Jinan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Peng", 
            "givenName": "Yanan", 
            "id": "sg:person.011422406334.14", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011422406334.14"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Control Science and Engineering, Shandong University, 250061, Jinan, China", 
              "id": "http://www.grid.ac/institutes/grid.27255.37", 
              "name": [
                "School of Control Science and Engineering, Shandong University, 250061, Jinan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chen", 
            "givenName": "Zhenxue", 
            "id": "sg:person.013352007053.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013352007053.53"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Electrical and Computer Engineering, University of Windsor, N9B 3P4, Windsor, Canada", 
              "id": "http://www.grid.ac/institutes/grid.267455.7", 
              "name": [
                "Department of Electrical and Computer Engineering, University of Windsor, N9B 3P4, Windsor, Canada"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wu", 
            "givenName": "Q. M. Jonathan", 
            "id": "sg:person.015515226365.07", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015515226365.07"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "School of Control Science and Engineering, Shandong University, 250061, Jinan, China", 
              "id": "http://www.grid.ac/institutes/grid.27255.37", 
              "name": [
                "School of Control Science and Engineering, Shandong University, 250061, Jinan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Liu", 
            "givenName": "Chengyun", 
            "id": "sg:person.011417216703.29", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011417216703.29"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11760-014-0739-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046291729", 
              "https://doi.org/10.1007/s11760-014-0739-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-012-0416-z", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047779787", 
              "https://doi.org/10.1007/s11760-012-0416-z"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10851-011-0262-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041077146", 
              "https://doi.org/10.1007/s10851-011-0262-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-013-0594-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028159794", 
              "https://doi.org/10.1007/s11760-013-0594-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-015-0767-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044201652", 
              "https://doi.org/10.1007/s11760-015-0767-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-014-0677-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037878425", 
              "https://doi.org/10.1007/s11760-014-0677-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-24673-2_3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045812409", 
              "https://doi.org/10.1007/978-3-540-24673-2_3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00138-012-0450-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047490759", 
              "https://doi.org/10.1007/s00138-012-0450-4"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-06-20", 
        "datePublishedReg": "2017-06-20", 
        "description": "Moving vehicle detection plays an important role in intelligent transportation systems. One of the common methods used in moving vehicle detection is optical flow. However, conventional Horn\u2013Schunck optical flow consumes too much time when calculating dense optical flows so that it cannot meet the real-time requirements. This paper proposes a novel improved Horn\u2013Schunck optical flow algorithm based on inter-frame differential method. In our algorithm, optical flow field distribution is only calculated for pixels with larger gray values in the difference image, while for other pixels we applied the iterative smooth. The number of vehicles in the videos of traffic conditions is counted by setting the virtual loop and detecting optical flow information. To extract the moving vehicle as accurately as possible, we also propose a method to obtain moving vehicle minimum bounding rectangle based on the connected region analysis. Finally, we compare the improved optical flow with other four optical flow algorithms in moving vehicle extraction and vehicle flow detection, from which our method gives a much more accurate result.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11760-017-1135-2", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.6990491", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1050964", 
            "issn": [
              "1863-1703", 
              "1863-1711"
            ], 
            "name": "Signal, Image and Video Processing", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "12"
          }
        ], 
        "keywords": [
          "vehicle detection", 
          "flow field distribution", 
          "optical flow algorithm", 
          "traffic flow detection", 
          "connected region analysis", 
          "vehicle flow detection", 
          "flow algorithm", 
          "flow detection", 
          "vehicle extraction", 
          "optical flow", 
          "largest gray value", 
          "intelligent transportation systems", 
          "number of vehicles", 
          "field distribution", 
          "Horn-Schunck optical flow", 
          "transportation system", 
          "real-time requirements", 
          "Horn-Schunck optical flow algorithm", 
          "traffic conditions", 
          "dense optical flow", 
          "virtual loops", 
          "flow", 
          "vehicles", 
          "differential method", 
          "flow information", 
          "accurate results", 
          "minimum bounding rectangle", 
          "optical flow information", 
          "difference image", 
          "bounding rectangle", 
          "gray value", 
          "common method", 
          "method", 
          "pixels", 
          "algorithm", 
          "region analysis", 
          "detection", 
          "loop", 
          "smooth", 
          "extraction", 
          "requirements", 
          "conditions", 
          "system", 
          "video", 
          "distribution", 
          "analysis", 
          "images", 
          "results", 
          "values", 
          "time", 
          "information", 
          "important role", 
          "rectangle", 
          "novel", 
          "number", 
          "statistics", 
          "paper", 
          "role"
        ], 
        "name": "Traffic flow detection and statistics via improved optical flow and connected region analysis", 
        "pagination": "99-105", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1086102249"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11760-017-1135-2"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11760-017-1135-2", 
          "https://app.dimensions.ai/details/publication/pub.1086102249"
        ], 
        "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_740.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11760-017-1135-2"
      }
    ]
     

    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/s11760-017-1135-2'

    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/s11760-017-1135-2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11760-017-1135-2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11760-017-1135-2'


     

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

    173 TRIPLES      21 PREDICATES      90 URIs      74 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11760-017-1135-2 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N265ed5cc24a845bc8e8ab543ec6d51ce
    4 schema:citation sg:pub.10.1007/978-3-540-24673-2_3
    5 sg:pub.10.1007/s00138-012-0450-4
    6 sg:pub.10.1007/s10851-011-0262-6
    7 sg:pub.10.1007/s11760-012-0416-z
    8 sg:pub.10.1007/s11760-013-0594-3
    9 sg:pub.10.1007/s11760-014-0677-9
    10 sg:pub.10.1007/s11760-014-0739-z
    11 sg:pub.10.1007/s11760-015-0767-3
    12 schema:datePublished 2017-06-20
    13 schema:datePublishedReg 2017-06-20
    14 schema:description Moving vehicle detection plays an important role in intelligent transportation systems. One of the common methods used in moving vehicle detection is optical flow. However, conventional Horn–Schunck optical flow consumes too much time when calculating dense optical flows so that it cannot meet the real-time requirements. This paper proposes a novel improved Horn–Schunck optical flow algorithm based on inter-frame differential method. In our algorithm, optical flow field distribution is only calculated for pixels with larger gray values in the difference image, while for other pixels we applied the iterative smooth. The number of vehicles in the videos of traffic conditions is counted by setting the virtual loop and detecting optical flow information. To extract the moving vehicle as accurately as possible, we also propose a method to obtain moving vehicle minimum bounding rectangle based on the connected region analysis. Finally, we compare the improved optical flow with other four optical flow algorithms in moving vehicle extraction and vehicle flow detection, from which our method gives a much more accurate result.
    15 schema:genre article
    16 schema:isAccessibleForFree false
    17 schema:isPartOf N2de335ab546b4533b03a922c0d90acf8
    18 Na484b527987240ada2150d1ed945b7b9
    19 sg:journal.1050964
    20 schema:keywords Horn-Schunck optical flow
    21 Horn-Schunck optical flow algorithm
    22 accurate results
    23 algorithm
    24 analysis
    25 bounding rectangle
    26 common method
    27 conditions
    28 connected region analysis
    29 dense optical flow
    30 detection
    31 difference image
    32 differential method
    33 distribution
    34 extraction
    35 field distribution
    36 flow
    37 flow algorithm
    38 flow detection
    39 flow field distribution
    40 flow information
    41 gray value
    42 images
    43 important role
    44 information
    45 intelligent transportation systems
    46 largest gray value
    47 loop
    48 method
    49 minimum bounding rectangle
    50 novel
    51 number
    52 number of vehicles
    53 optical flow
    54 optical flow algorithm
    55 optical flow information
    56 paper
    57 pixels
    58 real-time requirements
    59 rectangle
    60 region analysis
    61 requirements
    62 results
    63 role
    64 smooth
    65 statistics
    66 system
    67 time
    68 traffic conditions
    69 traffic flow detection
    70 transportation system
    71 values
    72 vehicle detection
    73 vehicle extraction
    74 vehicle flow detection
    75 vehicles
    76 video
    77 virtual loops
    78 schema:name Traffic flow detection and statistics via improved optical flow and connected region analysis
    79 schema:pagination 99-105
    80 schema:productId N165b783339914ed0bb43319a6d1d9a3d
    81 Ne9a57961dfe34832a7daf51421218a38
    82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086102249
    83 https://doi.org/10.1007/s11760-017-1135-2
    84 schema:sdDatePublished 2022-12-01T06:36
    85 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    86 schema:sdPublisher N70bec9987873442b88ac8b9e07a95e97
    87 schema:url https://doi.org/10.1007/s11760-017-1135-2
    88 sgo:license sg:explorer/license/
    89 sgo:sdDataset articles
    90 rdf:type schema:ScholarlyArticle
    91 N165b783339914ed0bb43319a6d1d9a3d schema:name dimensions_id
    92 schema:value pub.1086102249
    93 rdf:type schema:PropertyValue
    94 N265ed5cc24a845bc8e8ab543ec6d51ce rdf:first sg:person.011422406334.14
    95 rdf:rest Ndb95686af0be4d558babcca2dcf03a70
    96 N2de335ab546b4533b03a922c0d90acf8 schema:issueNumber 1
    97 rdf:type schema:PublicationIssue
    98 N41c6f7a42e4d45fcbc7aa2459a08895f rdf:first sg:person.011417216703.29
    99 rdf:rest rdf:nil
    100 N70bec9987873442b88ac8b9e07a95e97 schema:name Springer Nature - SN SciGraph project
    101 rdf:type schema:Organization
    102 Na484b527987240ada2150d1ed945b7b9 schema:volumeNumber 12
    103 rdf:type schema:PublicationVolume
    104 Nc2eadb056c5d4171a4437de545a2c189 rdf:first sg:person.015515226365.07
    105 rdf:rest N41c6f7a42e4d45fcbc7aa2459a08895f
    106 Ndb95686af0be4d558babcca2dcf03a70 rdf:first sg:person.013352007053.53
    107 rdf:rest Nc2eadb056c5d4171a4437de545a2c189
    108 Ne9a57961dfe34832a7daf51421218a38 schema:name doi
    109 schema:value 10.1007/s11760-017-1135-2
    110 rdf:type schema:PropertyValue
    111 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    112 schema:name Information and Computing Sciences
    113 rdf:type schema:DefinedTerm
    114 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    115 schema:name Artificial Intelligence and Image Processing
    116 rdf:type schema:DefinedTerm
    117 sg:grant.6990491 http://pending.schema.org/fundedItem sg:pub.10.1007/s11760-017-1135-2
    118 rdf:type schema:MonetaryGrant
    119 sg:journal.1050964 schema:issn 1863-1703
    120 1863-1711
    121 schema:name Signal, Image and Video Processing
    122 schema:publisher Springer Nature
    123 rdf:type schema:Periodical
    124 sg:person.011417216703.29 schema:affiliation grid-institutes:grid.27255.37
    125 schema:familyName Liu
    126 schema:givenName Chengyun
    127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011417216703.29
    128 rdf:type schema:Person
    129 sg:person.011422406334.14 schema:affiliation grid-institutes:grid.27255.37
    130 schema:familyName Peng
    131 schema:givenName Yanan
    132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011422406334.14
    133 rdf:type schema:Person
    134 sg:person.013352007053.53 schema:affiliation grid-institutes:grid.27255.37
    135 schema:familyName Chen
    136 schema:givenName Zhenxue
    137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013352007053.53
    138 rdf:type schema:Person
    139 sg:person.015515226365.07 schema:affiliation grid-institutes:grid.267455.7
    140 schema:familyName Wu
    141 schema:givenName Q. M. Jonathan
    142 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015515226365.07
    143 rdf:type schema:Person
    144 sg:pub.10.1007/978-3-540-24673-2_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045812409
    145 https://doi.org/10.1007/978-3-540-24673-2_3
    146 rdf:type schema:CreativeWork
    147 sg:pub.10.1007/s00138-012-0450-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047490759
    148 https://doi.org/10.1007/s00138-012-0450-4
    149 rdf:type schema:CreativeWork
    150 sg:pub.10.1007/s10851-011-0262-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041077146
    151 https://doi.org/10.1007/s10851-011-0262-6
    152 rdf:type schema:CreativeWork
    153 sg:pub.10.1007/s11760-012-0416-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1047779787
    154 https://doi.org/10.1007/s11760-012-0416-z
    155 rdf:type schema:CreativeWork
    156 sg:pub.10.1007/s11760-013-0594-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028159794
    157 https://doi.org/10.1007/s11760-013-0594-3
    158 rdf:type schema:CreativeWork
    159 sg:pub.10.1007/s11760-014-0677-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037878425
    160 https://doi.org/10.1007/s11760-014-0677-9
    161 rdf:type schema:CreativeWork
    162 sg:pub.10.1007/s11760-014-0739-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1046291729
    163 https://doi.org/10.1007/s11760-014-0739-z
    164 rdf:type schema:CreativeWork
    165 sg:pub.10.1007/s11760-015-0767-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044201652
    166 https://doi.org/10.1007/s11760-015-0767-3
    167 rdf:type schema:CreativeWork
    168 grid-institutes:grid.267455.7 schema:alternateName Department of Electrical and Computer Engineering, University of Windsor, N9B 3P4, Windsor, Canada
    169 schema:name Department of Electrical and Computer Engineering, University of Windsor, N9B 3P4, Windsor, Canada
    170 rdf:type schema:Organization
    171 grid-institutes:grid.27255.37 schema:alternateName School of Control Science and Engineering, Shandong University, 250061, Jinan, China
    172 schema:name School of Control Science and Engineering, Shandong University, 250061, Jinan, China
    173 rdf:type schema:Organization
     




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


    ...