Spatial and temporal variations of feature tracks for crowd behavior analysis View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2015-05-30

AUTHORS

Hajer Fradi, Jean-Luc Dugelay

ABSTRACT

The study of crowd behavior in public areas or during some public events is receiving a lot of attention in security community to detect potential risk and to prevent overcrowd. In this paper, we propose a novel approach for change detection, event recognition and characterization in human crowds. It consists of modeling time-varying dynamics of the crowd using local features. It also involves a feature tracking step which allows excluding feature points on the background and extracting long-term trajectories. This process is favourable for the later crowd event detection and recognition since the influence of features irrelevant to the underlying crowd is removed and the tracked features undergo an implicit temporal filtering. These feature tracks are further employed to extract regular motion patterns such as speed and flow direction. In addition, they are used as an observation of a probabilistic crowd function to generate fully automatic crowd density maps. Finally, the variation of these attributes (local density, speed, and flow direction) in time is employed to determine the ongoing crowd behaviors. The experimental results on two different datasets demonstrate the effectiveness of our proposed approach for early detection of crowd change and accurate results for event recognition and characterization. More... »

PAGES

307-317

References to SciGraph publications

  • 2008. Crowd Behavior Recognition for Video Surveillance in ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s12193-015-0179-2

    DOI

    http://dx.doi.org/10.1007/s12193-015-0179-2

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1039007752


    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": "EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France", 
              "id": "http://www.grid.ac/institutes/grid.28848.3e", 
              "name": [
                "EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fradi", 
            "givenName": "Hajer", 
            "id": "sg:person.013763206403.46", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013763206403.46"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France", 
              "id": "http://www.grid.ac/institutes/grid.28848.3e", 
              "name": [
                "EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Dugelay", 
            "givenName": "Jean-Luc", 
            "id": "sg:person.015053427343.37", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015053427343.37"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-540-88458-3_88", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028117238", 
              "https://doi.org/10.1007/978-3-540-88458-3_88"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015-05-30", 
        "datePublishedReg": "2015-05-30", 
        "description": "The study of crowd behavior in public areas or during some public events is receiving a lot of attention in security community to detect potential risk and to prevent overcrowd. In this paper, we propose a novel approach for change detection, event recognition and characterization in human crowds. It consists of modeling time-varying dynamics of the crowd using local features. It also involves a feature tracking step which allows excluding feature points on the background and extracting long-term trajectories. This process is favourable for the later crowd event detection and recognition since the influence of features irrelevant to the underlying crowd is removed and the tracked features undergo an implicit temporal filtering. These feature tracks are further employed to extract regular motion patterns such as speed and flow direction. In addition, they are used as an observation of a probabilistic crowd function to generate fully automatic crowd density maps. Finally, the variation of these attributes (local density, speed, and flow direction) in time is employed to determine the ongoing crowd behaviors. The experimental results on two different datasets demonstrate the effectiveness of our proposed approach for early detection of crowd change and accurate results for event recognition and characterization.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s12193-015-0179-2", 
        "inLanguage": "en", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1135962", 
            "issn": [
              "1783-7677", 
              "1783-8738"
            ], 
            "name": "Journal on Multimodal User Interfaces", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "4", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "10"
          }
        ], 
        "keywords": [
          "event recognition", 
          "feature tracks", 
          "crowd behavior", 
          "probabilistic crowd function", 
          "feature tracking step", 
          "crowd event detection", 
          "crowd density map", 
          "crowd behavior analysis", 
          "regular motion patterns", 
          "time-varying dynamics", 
          "tracked features", 
          "event detection", 
          "tracking step", 
          "feature points", 
          "crowd change", 
          "influence of features", 
          "local features", 
          "different datasets", 
          "temporal filtering", 
          "human crowds", 
          "change detection", 
          "security community", 
          "motion patterns", 
          "crowd", 
          "novel approach", 
          "behavior analysis", 
          "experimental results", 
          "public areas", 
          "accurate results", 
          "recognition", 
          "public events", 
          "detection", 
          "datasets", 
          "features", 
          "filtering", 
          "track", 
          "attributes", 
          "effectiveness", 
          "density maps", 
          "maps", 
          "trajectories", 
          "speed", 
          "long-term trajectories", 
          "step", 
          "early detection", 
          "results", 
          "point", 
          "process", 
          "time", 
          "attention", 
          "community", 
          "behavior", 
          "direction", 
          "area", 
          "background", 
          "function", 
          "analysis", 
          "patterns", 
          "dynamics", 
          "addition", 
          "events", 
          "potential risk", 
          "influence", 
          "approach", 
          "variation", 
          "study", 
          "temporal variation", 
          "observations", 
          "risk", 
          "changes", 
          "paper", 
          "characterization", 
          "overcrowd", 
          "extracting long-term trajectories", 
          "later crowd event detection", 
          "implicit temporal filtering", 
          "crowd function", 
          "automatic crowd density maps", 
          "ongoing crowd behaviors"
        ], 
        "name": "Spatial and temporal variations of feature tracks for crowd behavior analysis", 
        "pagination": "307-317", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1039007752"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s12193-015-0179-2"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s12193-015-0179-2", 
          "https://app.dimensions.ai/details/publication/pub.1039007752"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-01-01T18:36", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_658.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s12193-015-0179-2"
      }
    ]
     

    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/s12193-015-0179-2'

    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/s12193-015-0179-2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12193-015-0179-2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12193-015-0179-2'


     

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

    148 TRIPLES      22 PREDICATES      105 URIs      96 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s12193-015-0179-2 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N2cd976e2ee344a97a864d3cc90fea77a
    4 schema:citation sg:pub.10.1007/978-3-540-88458-3_88
    5 schema:datePublished 2015-05-30
    6 schema:datePublishedReg 2015-05-30
    7 schema:description The study of crowd behavior in public areas or during some public events is receiving a lot of attention in security community to detect potential risk and to prevent overcrowd. In this paper, we propose a novel approach for change detection, event recognition and characterization in human crowds. It consists of modeling time-varying dynamics of the crowd using local features. It also involves a feature tracking step which allows excluding feature points on the background and extracting long-term trajectories. This process is favourable for the later crowd event detection and recognition since the influence of features irrelevant to the underlying crowd is removed and the tracked features undergo an implicit temporal filtering. These feature tracks are further employed to extract regular motion patterns such as speed and flow direction. In addition, they are used as an observation of a probabilistic crowd function to generate fully automatic crowd density maps. Finally, the variation of these attributes (local density, speed, and flow direction) in time is employed to determine the ongoing crowd behaviors. The experimental results on two different datasets demonstrate the effectiveness of our proposed approach for early detection of crowd change and accurate results for event recognition and characterization.
    8 schema:genre article
    9 schema:inLanguage en
    10 schema:isAccessibleForFree false
    11 schema:isPartOf N4731b775a3324c0c8a49deeb2c8255e6
    12 N81e69dfaa80d4129b848b8af1e43f270
    13 sg:journal.1135962
    14 schema:keywords accurate results
    15 addition
    16 analysis
    17 approach
    18 area
    19 attention
    20 attributes
    21 automatic crowd density maps
    22 background
    23 behavior
    24 behavior analysis
    25 change detection
    26 changes
    27 characterization
    28 community
    29 crowd
    30 crowd behavior
    31 crowd behavior analysis
    32 crowd change
    33 crowd density map
    34 crowd event detection
    35 crowd function
    36 datasets
    37 density maps
    38 detection
    39 different datasets
    40 direction
    41 dynamics
    42 early detection
    43 effectiveness
    44 event detection
    45 event recognition
    46 events
    47 experimental results
    48 extracting long-term trajectories
    49 feature points
    50 feature tracking step
    51 feature tracks
    52 features
    53 filtering
    54 function
    55 human crowds
    56 implicit temporal filtering
    57 influence
    58 influence of features
    59 later crowd event detection
    60 local features
    61 long-term trajectories
    62 maps
    63 motion patterns
    64 novel approach
    65 observations
    66 ongoing crowd behaviors
    67 overcrowd
    68 paper
    69 patterns
    70 point
    71 potential risk
    72 probabilistic crowd function
    73 process
    74 public areas
    75 public events
    76 recognition
    77 regular motion patterns
    78 results
    79 risk
    80 security community
    81 speed
    82 step
    83 study
    84 temporal filtering
    85 temporal variation
    86 time
    87 time-varying dynamics
    88 track
    89 tracked features
    90 tracking step
    91 trajectories
    92 variation
    93 schema:name Spatial and temporal variations of feature tracks for crowd behavior analysis
    94 schema:pagination 307-317
    95 schema:productId N3b2f2907611d42f9a6284855473ab2e0
    96 N46485b1c2f1c42eebdb02563f3406b35
    97 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039007752
    98 https://doi.org/10.1007/s12193-015-0179-2
    99 schema:sdDatePublished 2022-01-01T18:36
    100 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    101 schema:sdPublisher Nbb5fe552a55b4c5192eb04f8e518e62e
    102 schema:url https://doi.org/10.1007/s12193-015-0179-2
    103 sgo:license sg:explorer/license/
    104 sgo:sdDataset articles
    105 rdf:type schema:ScholarlyArticle
    106 N120c892334054c26bd4300554b0712bf rdf:first sg:person.015053427343.37
    107 rdf:rest rdf:nil
    108 N2cd976e2ee344a97a864d3cc90fea77a rdf:first sg:person.013763206403.46
    109 rdf:rest N120c892334054c26bd4300554b0712bf
    110 N3b2f2907611d42f9a6284855473ab2e0 schema:name doi
    111 schema:value 10.1007/s12193-015-0179-2
    112 rdf:type schema:PropertyValue
    113 N46485b1c2f1c42eebdb02563f3406b35 schema:name dimensions_id
    114 schema:value pub.1039007752
    115 rdf:type schema:PropertyValue
    116 N4731b775a3324c0c8a49deeb2c8255e6 schema:issueNumber 4
    117 rdf:type schema:PublicationIssue
    118 N81e69dfaa80d4129b848b8af1e43f270 schema:volumeNumber 10
    119 rdf:type schema:PublicationVolume
    120 Nbb5fe552a55b4c5192eb04f8e518e62e schema:name Springer Nature - SN SciGraph project
    121 rdf:type schema:Organization
    122 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    123 schema:name Information and Computing Sciences
    124 rdf:type schema:DefinedTerm
    125 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    126 schema:name Artificial Intelligence and Image Processing
    127 rdf:type schema:DefinedTerm
    128 sg:journal.1135962 schema:issn 1783-7677
    129 1783-8738
    130 schema:name Journal on Multimodal User Interfaces
    131 schema:publisher Springer Nature
    132 rdf:type schema:Periodical
    133 sg:person.013763206403.46 schema:affiliation grid-institutes:grid.28848.3e
    134 schema:familyName Fradi
    135 schema:givenName Hajer
    136 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013763206403.46
    137 rdf:type schema:Person
    138 sg:person.015053427343.37 schema:affiliation grid-institutes:grid.28848.3e
    139 schema:familyName Dugelay
    140 schema:givenName Jean-Luc
    141 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015053427343.37
    142 rdf:type schema:Person
    143 sg:pub.10.1007/978-3-540-88458-3_88 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028117238
    144 https://doi.org/10.1007/978-3-540-88458-3_88
    145 rdf:type schema:CreativeWork
    146 grid-institutes:grid.28848.3e schema:alternateName EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France
    147 schema:name EURECOM, Campus Sophia Tech 450 route des Chappes, 06410, Biot-Sophia Antipolis, France
    148 rdf:type schema:Organization
     




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


    ...