Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-02

AUTHORS

Iqbal Murtza, Asifullah Khan, Naeem Akhtar

ABSTRACT

This paper presents a learning mechanism based on hybridization of static and dynamic learning. Realizing the detection performances offered by the state-of-the-art deep learning techniques and the competitive performances offered by the conventional static learning techniques, we propose the idea of exploitation of the concatenated (parallel) hybridization of the static and dynamic learning-based feature spaces. This is contrary to the cascaded (series) hybridization topology in which the initial feature space (provided by the conventional, static, and handcrafted feature extraction technique) is explored using deep, dynamic, and automated learning technique. Consequently, the characteristics already suppressed by the conventional representation cannot be explored by the dynamic learning technique. Instead, the proposed technique combines the conventional static and deep dynamic representation in concatenated (parallel) topology to generate an information-rich hybrid feature space. Thus, this hybrid feature space may aggregate the good characteristics of both conventional and deep representations, which are then explored using an appropriate classification technique. We also hypothesize that ensemble classification may better exploit this parallel hybrid perspective of the feature spaces. For this purpose, pyramid histogram of oriented gradients-based static learning has been incorporated in conjunction with convolution neural network-based deep learning to produce concatenated hybrid feature space. This hybrid space is then explored with various state-of-the-art ensemble classification techniques. We have considered the publicly available INRIA person and Caltech pedestrian standard image datasets to assess the performance of the proposed hybrid learning system. Furthermore, McNemar’s test has been used to statistically validate the outperformance of the proposed technique over various contemporary techniques. The validated experimental results show that the employment of the proposed hybrid representation results in effective detection performance (an AUC of 0.9996 for INRIA person and 0.9985 for Caltech pedestrian datasets) as compared to the individual static and dynamic representations. More... »

PAGES

347-361

References to SciGraph publications

  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2013-09. Fast neural network learning algorithms for medical applications in NEURAL COMPUTING AND APPLICATIONS
  • 2013-05. Evaluation of unsupervised feature extraction neural networks for face recognition in NEURAL COMPUTING AND APPLICATIONS
  • 2005-05. Logistic Model Trees in MACHINE LEARNING
  • 2006. Human Detection Using Oriented Histograms of Flow and Appearance in COMPUTER VISION – ECCV 2006
  • 1947-06. Note on the sampling error of the difference between correlated proportions or percentages in PSYCHOMETRIKA
  • 2005. Speeding Up Logistic Model Tree Induction in KNOWLEDGE DISCOVERY IN DATABASES: PKDD 2005
  • 2009. Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection in ADVANCES IN IMAGE AND VIDEO TECHNOLOGY
  • 2013. Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks in ADVANCED INFORMATION SYSTEMS ENGINEERING
  • 2006. SURF: Speeded Up Robust Features in COMPUTER VISION – ECCV 2006
  • 2016-11. Deep multilayer multiple kernel learning in NEURAL COMPUTING AND APPLICATIONS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00521-017-3050-4

    DOI

    http://dx.doi.org/10.1007/s00521-017-3050-4

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1090355629


    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Pakistan Institute of Engineering and Applied Sciences", 
              "id": "https://www.grid.ac/institutes/grid.420112.4", 
              "name": [
                "Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Murtza", 
            "givenName": "Iqbal", 
            "id": "sg:person.011446124473.33", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011446124473.33"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Pakistan Institute of Engineering and Applied Sciences", 
              "id": "https://www.grid.ac/institutes/grid.420112.4", 
              "name": [
                "Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Khan", 
            "givenName": "Asifullah", 
            "id": "sg:person.01106444435.33", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01106444435.33"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Pakistan Institute of Engineering and Applied Sciences", 
              "id": "https://www.grid.ac/institutes/grid.420112.4", 
              "name": [
                "Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Akhtar", 
            "givenName": "Naeem", 
            "id": "sg:person.013572450441.80", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013572450441.80"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/11744023_32", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000158525", 
              "https://doi.org/10.1007/11744023_32"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00521-015-2066-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003828482", 
              "https://doi.org/10.1007/s00521-015-2066-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00521-012-1026-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003945028", 
              "https://doi.org/10.1007/s00521-012-1026-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10994-005-0466-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005110454", 
              "https://doi.org/10.1007/s10994-005-0466-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10994-005-0466-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005110454", 
              "https://doi.org/10.1007/s10994-005-0466-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00521-012-0889-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008463493", 
              "https://doi.org/10.1007/s00521-012-0889-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2016.12.038", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012313573"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/0470011815.b2a15018", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014283410"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-40763-5_51", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014968475", 
              "https://doi.org/10.1007/978-3-642-40763-5_51"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11564126_72", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018220155", 
              "https://doi.org/10.1007/11564126_72"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11564126_72", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018220155", 
              "https://doi.org/10.1007/11564126_72"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/aos/1016218223", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020629296"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744047_33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022098216", 
              "https://doi.org/10.1007/11744047_33"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744047_33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022098216", 
              "https://doi.org/10.1007/11744047_33"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1656274.1656278", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028526411"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1017/atsip.2013.9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032663204"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-92957-4_4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037315232", 
              "https://doi.org/10.1007/978-3-540-92957-4_4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-92957-4_4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037315232", 
              "https://doi.org/10.1007/978-3-540-92957-4_4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2733373.2807412", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039662878"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.cviu.2007.09.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040969278"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1128/aem.67.5.2129-2135.2001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042187491"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02295996", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048367524", 
              "https://doi.org/10.1007/bf02295996"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052687286", 
              "https://doi.org/10.1023/b:visi.0000029664.99615.94"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/5.726791", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061179979"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/5326.897072", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061186742"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/72.554195", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061218851"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/proc.1969.7277", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061440654"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/proc.1972.8780", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061442059"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taslp.2014.2339736", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061517330"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tcom.1976.1093409", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061551904"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2010.2066286", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061717770"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2007.56", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743347"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.154", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743736"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2011.155", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744049"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2012.59", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744395"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2015.2389824", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744812"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmcb.2011.2167750", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061797396"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1561/2200000006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1068001401"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icsmc.2011.6084045", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093350156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ivs.2005.1505106", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093390324"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2002.1048231", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093770282"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093997066"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206631", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094061126"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iscas.2010.5537907", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094709720"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2003.1227801", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094714779"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2011.229", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095160470"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.254", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095271325"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.254", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095271325"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.1999.790410", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095766209"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.22436/jmcs.011.02.04", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1105029399"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/9780470627242", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1106815149"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-02", 
        "datePublishedReg": "2019-02-01", 
        "description": "This paper presents a learning mechanism based on hybridization of static and dynamic learning. Realizing the detection performances offered by the state-of-the-art deep learning techniques and the competitive performances offered by the conventional static learning techniques, we propose the idea of exploitation of the concatenated (parallel) hybridization of the static and dynamic learning-based feature spaces. This is contrary to the cascaded (series) hybridization topology in which the initial feature space (provided by the conventional, static, and handcrafted feature extraction technique) is explored using deep, dynamic, and automated learning technique. Consequently, the characteristics already suppressed by the conventional representation cannot be explored by the dynamic learning technique. Instead, the proposed technique combines the conventional static and deep dynamic representation in concatenated (parallel) topology to generate an information-rich hybrid feature space. Thus, this hybrid feature space may aggregate the good characteristics of both conventional and deep representations, which are then explored using an appropriate classification technique. We also hypothesize that ensemble classification may better exploit this parallel hybrid perspective of the feature spaces. For this purpose, pyramid histogram of oriented gradients-based static learning has been incorporated in conjunction with convolution neural network-based deep learning to produce concatenated hybrid feature space. This hybrid space is then explored with various state-of-the-art ensemble classification techniques. We have considered the publicly available INRIA person and Caltech pedestrian standard image datasets to assess the performance of the proposed hybrid learning system. Furthermore, McNemar\u2019s test has been used to statistically validate the outperformance of the proposed technique over various contemporary techniques. The validated experimental results show that the employment of the proposed hybrid representation results in effective detection performance (an AUC of 0.9996 for INRIA person and 0.9985 for Caltech pedestrian datasets) as compared to the individual static and dynamic representations.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s00521-017-3050-4", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7490751", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1104357", 
            "issn": [
              "0941-0643", 
              "1433-3058"
            ], 
            "name": "Neural Computing and Applications", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "31"
          }
        ], 
        "name": "Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification", 
        "pagination": "347-361", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "41659bdfa747875c652ea00d6793813c31ff24e0d32ebfae3f9885c5a829c3ba"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00521-017-3050-4"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1090355629"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00521-017-3050-4", 
          "https://app.dimensions.ai/details/publication/pub.1090355629"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T10:50", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000350_0000000350/records_77583_00000001.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs00521-017-3050-4"
      }
    ]
     

    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/s00521-017-3050-4'

    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/s00521-017-3050-4'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00521-017-3050-4'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00521-017-3050-4'


     

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

    226 TRIPLES      21 PREDICATES      73 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00521-017-3050-4 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N9c67f486670e457b8c0c0d3f61298a6e
    4 schema:citation sg:pub.10.1007/11564126_72
    5 sg:pub.10.1007/11744023_32
    6 sg:pub.10.1007/11744047_33
    7 sg:pub.10.1007/978-3-540-92957-4_4
    8 sg:pub.10.1007/978-3-642-40763-5_51
    9 sg:pub.10.1007/bf02295996
    10 sg:pub.10.1007/s00521-012-0889-2
    11 sg:pub.10.1007/s00521-012-1026-y
    12 sg:pub.10.1007/s00521-015-2066-x
    13 sg:pub.10.1007/s10994-005-0466-3
    14 sg:pub.10.1023/b:visi.0000029664.99615.94
    15 https://doi.org/10.1002/0470011815.b2a15018
    16 https://doi.org/10.1002/9780470627242
    17 https://doi.org/10.1016/j.cviu.2007.09.014
    18 https://doi.org/10.1016/j.neucom.2016.12.038
    19 https://doi.org/10.1017/atsip.2013.9
    20 https://doi.org/10.1109/5.726791
    21 https://doi.org/10.1109/5326.897072
    22 https://doi.org/10.1109/72.554195
    23 https://doi.org/10.1109/cvpr.2005.177
    24 https://doi.org/10.1109/cvpr.2005.254
    25 https://doi.org/10.1109/cvpr.2009.5206631
    26 https://doi.org/10.1109/iccv.1999.790410
    27 https://doi.org/10.1109/icdar.2003.1227801
    28 https://doi.org/10.1109/icdar.2011.229
    29 https://doi.org/10.1109/icpr.2002.1048231
    30 https://doi.org/10.1109/icsmc.2011.6084045
    31 https://doi.org/10.1109/iscas.2010.5537907
    32 https://doi.org/10.1109/ivs.2005.1505106
    33 https://doi.org/10.1109/proc.1969.7277
    34 https://doi.org/10.1109/proc.1972.8780
    35 https://doi.org/10.1109/taslp.2014.2339736
    36 https://doi.org/10.1109/tcom.1976.1093409
    37 https://doi.org/10.1109/tnn.2010.2066286
    38 https://doi.org/10.1109/tpami.2007.56
    39 https://doi.org/10.1109/tpami.2009.154
    40 https://doi.org/10.1109/tpami.2011.155
    41 https://doi.org/10.1109/tpami.2012.59
    42 https://doi.org/10.1109/tpami.2015.2389824
    43 https://doi.org/10.1109/tsmcb.2011.2167750
    44 https://doi.org/10.1128/aem.67.5.2129-2135.2001
    45 https://doi.org/10.1145/1656274.1656278
    46 https://doi.org/10.1145/2733373.2807412
    47 https://doi.org/10.1214/aos/1016218223
    48 https://doi.org/10.1561/2200000006
    49 https://doi.org/10.22436/jmcs.011.02.04
    50 schema:datePublished 2019-02
    51 schema:datePublishedReg 2019-02-01
    52 schema:description This paper presents a learning mechanism based on hybridization of static and dynamic learning. Realizing the detection performances offered by the state-of-the-art deep learning techniques and the competitive performances offered by the conventional static learning techniques, we propose the idea of exploitation of the concatenated (parallel) hybridization of the static and dynamic learning-based feature spaces. This is contrary to the cascaded (series) hybridization topology in which the initial feature space (provided by the conventional, static, and handcrafted feature extraction technique) is explored using deep, dynamic, and automated learning technique. Consequently, the characteristics already suppressed by the conventional representation cannot be explored by the dynamic learning technique. Instead, the proposed technique combines the conventional static and deep dynamic representation in concatenated (parallel) topology to generate an information-rich hybrid feature space. Thus, this hybrid feature space may aggregate the good characteristics of both conventional and deep representations, which are then explored using an appropriate classification technique. We also hypothesize that ensemble classification may better exploit this parallel hybrid perspective of the feature spaces. For this purpose, pyramid histogram of oriented gradients-based static learning has been incorporated in conjunction with convolution neural network-based deep learning to produce concatenated hybrid feature space. This hybrid space is then explored with various state-of-the-art ensemble classification techniques. We have considered the publicly available INRIA person and Caltech pedestrian standard image datasets to assess the performance of the proposed hybrid learning system. Furthermore, McNemar’s test has been used to statistically validate the outperformance of the proposed technique over various contemporary techniques. The validated experimental results show that the employment of the proposed hybrid representation results in effective detection performance (an AUC of 0.9996 for INRIA person and 0.9985 for Caltech pedestrian datasets) as compared to the individual static and dynamic representations.
    53 schema:genre research_article
    54 schema:inLanguage en
    55 schema:isAccessibleForFree false
    56 schema:isPartOf N3f9eb7a2ce934ce896b8a6510e3d9807
    57 Nf6a171f16ce94240b662cbf9b2a9b555
    58 sg:journal.1104357
    59 schema:name Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification
    60 schema:pagination 347-361
    61 schema:productId N5ecfac32de4145a4a66e4bb43aa4aa2a
    62 N6a16487a9c924688bb1241a536105f07
    63 N8ed695dd1d214afeb0629748d93d668c
    64 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090355629
    65 https://doi.org/10.1007/s00521-017-3050-4
    66 schema:sdDatePublished 2019-04-11T10:50
    67 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    68 schema:sdPublisher N07c81b1d18cf4dbf9cd85f20b656d451
    69 schema:url https://link.springer.com/10.1007%2Fs00521-017-3050-4
    70 sgo:license sg:explorer/license/
    71 sgo:sdDataset articles
    72 rdf:type schema:ScholarlyArticle
    73 N07c81b1d18cf4dbf9cd85f20b656d451 schema:name Springer Nature - SN SciGraph project
    74 rdf:type schema:Organization
    75 N3f9eb7a2ce934ce896b8a6510e3d9807 schema:volumeNumber 31
    76 rdf:type schema:PublicationVolume
    77 N5ecfac32de4145a4a66e4bb43aa4aa2a schema:name readcube_id
    78 schema:value 41659bdfa747875c652ea00d6793813c31ff24e0d32ebfae3f9885c5a829c3ba
    79 rdf:type schema:PropertyValue
    80 N6a16487a9c924688bb1241a536105f07 schema:name dimensions_id
    81 schema:value pub.1090355629
    82 rdf:type schema:PropertyValue
    83 N83e40bc45b194ab3b6255b0fbbabe830 rdf:first sg:person.01106444435.33
    84 rdf:rest Nf6176bfec33942c98ca5e9b0588f505f
    85 N8ed695dd1d214afeb0629748d93d668c schema:name doi
    86 schema:value 10.1007/s00521-017-3050-4
    87 rdf:type schema:PropertyValue
    88 N9c67f486670e457b8c0c0d3f61298a6e rdf:first sg:person.011446124473.33
    89 rdf:rest N83e40bc45b194ab3b6255b0fbbabe830
    90 Nf6176bfec33942c98ca5e9b0588f505f rdf:first sg:person.013572450441.80
    91 rdf:rest rdf:nil
    92 Nf6a171f16ce94240b662cbf9b2a9b555 schema:issueNumber 2
    93 rdf:type schema:PublicationIssue
    94 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Information and Computing Sciences
    96 rdf:type schema:DefinedTerm
    97 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    98 schema:name Artificial Intelligence and Image Processing
    99 rdf:type schema:DefinedTerm
    100 sg:grant.7490751 http://pending.schema.org/fundedItem sg:pub.10.1007/s00521-017-3050-4
    101 rdf:type schema:MonetaryGrant
    102 sg:journal.1104357 schema:issn 0941-0643
    103 1433-3058
    104 schema:name Neural Computing and Applications
    105 rdf:type schema:Periodical
    106 sg:person.01106444435.33 schema:affiliation https://www.grid.ac/institutes/grid.420112.4
    107 schema:familyName Khan
    108 schema:givenName Asifullah
    109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01106444435.33
    110 rdf:type schema:Person
    111 sg:person.011446124473.33 schema:affiliation https://www.grid.ac/institutes/grid.420112.4
    112 schema:familyName Murtza
    113 schema:givenName Iqbal
    114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011446124473.33
    115 rdf:type schema:Person
    116 sg:person.013572450441.80 schema:affiliation https://www.grid.ac/institutes/grid.420112.4
    117 schema:familyName Akhtar
    118 schema:givenName Naeem
    119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013572450441.80
    120 rdf:type schema:Person
    121 sg:pub.10.1007/11564126_72 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018220155
    122 https://doi.org/10.1007/11564126_72
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1007/11744023_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000158525
    125 https://doi.org/10.1007/11744023_32
    126 rdf:type schema:CreativeWork
    127 sg:pub.10.1007/11744047_33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022098216
    128 https://doi.org/10.1007/11744047_33
    129 rdf:type schema:CreativeWork
    130 sg:pub.10.1007/978-3-540-92957-4_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037315232
    131 https://doi.org/10.1007/978-3-540-92957-4_4
    132 rdf:type schema:CreativeWork
    133 sg:pub.10.1007/978-3-642-40763-5_51 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014968475
    134 https://doi.org/10.1007/978-3-642-40763-5_51
    135 rdf:type schema:CreativeWork
    136 sg:pub.10.1007/bf02295996 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048367524
    137 https://doi.org/10.1007/bf02295996
    138 rdf:type schema:CreativeWork
    139 sg:pub.10.1007/s00521-012-0889-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008463493
    140 https://doi.org/10.1007/s00521-012-0889-2
    141 rdf:type schema:CreativeWork
    142 sg:pub.10.1007/s00521-012-1026-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1003945028
    143 https://doi.org/10.1007/s00521-012-1026-y
    144 rdf:type schema:CreativeWork
    145 sg:pub.10.1007/s00521-015-2066-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1003828482
    146 https://doi.org/10.1007/s00521-015-2066-x
    147 rdf:type schema:CreativeWork
    148 sg:pub.10.1007/s10994-005-0466-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005110454
    149 https://doi.org/10.1007/s10994-005-0466-3
    150 rdf:type schema:CreativeWork
    151 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    152 https://doi.org/10.1023/b:visi.0000029664.99615.94
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1002/0470011815.b2a15018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014283410
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1002/9780470627242 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106815149
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1016/j.cviu.2007.09.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040969278
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1016/j.neucom.2016.12.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012313573
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1017/atsip.2013.9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032663204
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1109/5326.897072 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061186742
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1109/72.554195 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061218851
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1109/cvpr.2005.254 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095271325
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1109/cvpr.2009.5206631 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094061126
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1109/iccv.1999.790410 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095766209
    177 rdf:type schema:CreativeWork
    178 https://doi.org/10.1109/icdar.2003.1227801 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094714779
    179 rdf:type schema:CreativeWork
    180 https://doi.org/10.1109/icdar.2011.229 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095160470
    181 rdf:type schema:CreativeWork
    182 https://doi.org/10.1109/icpr.2002.1048231 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093770282
    183 rdf:type schema:CreativeWork
    184 https://doi.org/10.1109/icsmc.2011.6084045 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093350156
    185 rdf:type schema:CreativeWork
    186 https://doi.org/10.1109/iscas.2010.5537907 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094709720
    187 rdf:type schema:CreativeWork
    188 https://doi.org/10.1109/ivs.2005.1505106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093390324
    189 rdf:type schema:CreativeWork
    190 https://doi.org/10.1109/proc.1969.7277 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061440654
    191 rdf:type schema:CreativeWork
    192 https://doi.org/10.1109/proc.1972.8780 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061442059
    193 rdf:type schema:CreativeWork
    194 https://doi.org/10.1109/taslp.2014.2339736 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517330
    195 rdf:type schema:CreativeWork
    196 https://doi.org/10.1109/tcom.1976.1093409 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061551904
    197 rdf:type schema:CreativeWork
    198 https://doi.org/10.1109/tnn.2010.2066286 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717770
    199 rdf:type schema:CreativeWork
    200 https://doi.org/10.1109/tpami.2007.56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743347
    201 rdf:type schema:CreativeWork
    202 https://doi.org/10.1109/tpami.2009.154 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743736
    203 rdf:type schema:CreativeWork
    204 https://doi.org/10.1109/tpami.2011.155 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744049
    205 rdf:type schema:CreativeWork
    206 https://doi.org/10.1109/tpami.2012.59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744395
    207 rdf:type schema:CreativeWork
    208 https://doi.org/10.1109/tpami.2015.2389824 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744812
    209 rdf:type schema:CreativeWork
    210 https://doi.org/10.1109/tsmcb.2011.2167750 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061797396
    211 rdf:type schema:CreativeWork
    212 https://doi.org/10.1128/aem.67.5.2129-2135.2001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042187491
    213 rdf:type schema:CreativeWork
    214 https://doi.org/10.1145/1656274.1656278 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028526411
    215 rdf:type schema:CreativeWork
    216 https://doi.org/10.1145/2733373.2807412 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039662878
    217 rdf:type schema:CreativeWork
    218 https://doi.org/10.1214/aos/1016218223 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020629296
    219 rdf:type schema:CreativeWork
    220 https://doi.org/10.1561/2200000006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001401
    221 rdf:type schema:CreativeWork
    222 https://doi.org/10.22436/jmcs.011.02.04 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105029399
    223 rdf:type schema:CreativeWork
    224 https://www.grid.ac/institutes/grid.420112.4 schema:alternateName Pakistan Institute of Engineering and Applied Sciences
    225 schema:name Pattern Recognition Lab, Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan
    226 rdf:type schema:Organization
     




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


    ...