Street Tree Crown Detection with Mobile Laser Scanning Data Using a Grid Index and Local Features View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2022-06-23

AUTHORS

Qiujie Li, Xiangcheng Li, Yuekai Tong, Xu Liu

ABSTRACT

In recent years, targeted spraying technology, which was proposed to solve the problems of pesticide waste and environmental pollution caused by traditional spraying methods, has been successfully applied in orchards. In street scenes with a variety of object classes, it is challenging to detect tree crowns, which limits the application of targeted spraying for street trees. Two-dimensional (2D) light detection and ranging (LiDAR) sensors have been widely used in targeted spraying to monitor the presence of tree crowns. Considering a mobile laser scanning (MLS) system with a single 2D LiDAR sensor in push-broom mode, this paper proposes a pointwise method for street tree crown detection from MLS point clouds by using a grid index and local features. First, an efficient two-level neighbourhood search method is proposed to obtain the spherical neighbourhood of a single point by using the grid index of the MLS point clouds. Subsequently, a set of local statistical features, including width features, depth features, elevation features, intensity features, echo number features, dimensionality features and a density feature, are extracted from the spherical neighbourhood. Finally, a supervised learning algorithm called boosting is used to automatically fuse these features and generate a pointwise tree crown detector from a labelled training set. An MLS point cloud with 15,134,000 points is captured from both sides of a 136.5 m street, and the cloud contains buildings, lanes, sidewalks, benches, street lights, bicycles, traffic signs, grids, trees, bushes, turf areas, parterres, and pedestrians. The estimated Bayesian errors of single-feature approaches range from 6.23 to 36.09%, and the error rate of the tree crown detector composed of all features is less than 0.73%, with a recall rate of over 98.30% and a precision of over 99.13%. The experimental results show that the proposed method can provide an online, fine and accurate protocol for targeted spraying. More... »

PAGES

305-317

References to SciGraph publications

  • 2004-05. Robust Real-Time Face Detection in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s41064-022-00208-w

    DOI

    http://dx.doi.org/10.1007/s41064-022-00208-w

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1148908776


    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": "Nanjing Forestry University, Nanjing, China", 
              "id": "http://www.grid.ac/institutes/grid.410625.4", 
              "name": [
                "Nanjing Forestry University, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Qiujie", 
            "id": "sg:person.016662612020.83", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016662612020.83"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Nanjing Forestry University, Nanjing, China", 
              "id": "http://www.grid.ac/institutes/grid.410625.4", 
              "name": [
                "Nanjing Forestry University, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Xiangcheng", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Nanjing Forestry University, Nanjing, China", 
              "id": "http://www.grid.ac/institutes/grid.410625.4", 
              "name": [
                "Nanjing Forestry University, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Tong", 
            "givenName": "Yuekai", 
            "id": "sg:person.016136145541.23", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016136145541.23"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Nanjing Forestry University, Nanjing, China", 
              "id": "http://www.grid.ac/institutes/grid.410625.4", 
              "name": [
                "Nanjing Forestry University, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Liu", 
            "givenName": "Xu", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/b:visi.0000013087.49260.fb", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001944608", 
              "https://doi.org/10.1023/b:visi.0000013087.49260.fb"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-06-23", 
        "datePublishedReg": "2022-06-23", 
        "description": "In recent years, targeted spraying technology, which was proposed to solve the problems of pesticide waste and environmental pollution caused by traditional spraying methods, has been successfully applied in orchards. In street scenes with a variety of object classes, it is challenging to detect tree crowns, which limits the application of targeted spraying for street trees. Two-dimensional (2D) light detection and ranging (LiDAR) sensors have been widely used in targeted spraying to monitor the presence of tree crowns. Considering a mobile laser scanning (MLS) system with a single 2D LiDAR sensor in push-broom mode, this paper proposes a pointwise method for street tree crown detection from MLS point clouds by using a grid index and local features. First, an efficient two-level neighbourhood search method is proposed to obtain the spherical neighbourhood of a single point by using the grid index of the MLS point clouds. Subsequently, a set of local statistical features, including width features, depth features, elevation features, intensity features, echo number features, dimensionality features and a density feature, are extracted from the spherical neighbourhood. Finally, a supervised learning algorithm called boosting is used to automatically fuse these features and generate a pointwise tree crown detector from a labelled training set. An MLS point cloud with 15,134,000 points is captured from both sides of a 136.5\u00a0m street, and the cloud contains buildings, lanes, sidewalks, benches, street lights, bicycles, traffic signs, grids, trees, bushes, turf areas, parterres, and pedestrians. The estimated Bayesian errors of single-feature approaches range from 6.23 to 36.09%, and the error rate of the tree crown detector composed of all features is less than 0.73%, with a recall rate of over 98.30% and a precision of over 99.13%. The experimental results show that the proposed method can provide an online, fine and accurate protocol for targeted spraying.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s41064-022-00208-w", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.8914396", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1320463", 
            "issn": [
              "2512-2789", 
              "2512-2819"
            ], 
            "name": "PFG \u2013 Journal of Photogrammetry, Remote Sensing and Geoinformation Science", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "90"
          }
        ], 
        "keywords": [
          "MLS point clouds", 
          "grid index", 
          "tree crown detection", 
          "point clouds", 
          "local features", 
          "mobile laser scanning data", 
          "crown detection", 
          "neighborhood search method", 
          "supervised learning algorithm", 
          "mobile laser scanning system", 
          "local statistical features", 
          "single-feature approach", 
          "depth features", 
          "learning algorithm", 
          "object classes", 
          "spherical neighborhood", 
          "street scenes", 
          "LiDAR sensors", 
          "dimensionality features", 
          "traffic signs", 
          "search method", 
          "recall rate", 
          "laser scanning data", 
          "statistical features", 
          "training set", 
          "intensity features", 
          "cloud", 
          "pointwise method", 
          "laser scanning system", 
          "width feature", 
          "elevation features", 
          "two-dimensional light detection", 
          "single point", 
          "error rate", 
          "push-broom mode", 
          "Bayesian error", 
          "scanning data", 
          "experimental results", 
          "density features", 
          "light detection", 
          "scanning system", 
          "street lights", 
          "recent years", 
          "sensors", 
          "features", 
          "set", 
          "detection", 
          "algorithm", 
          "scene", 
          "number features", 
          "trees", 
          "pedestrians", 
          "technology", 
          "tree crowns", 
          "grid", 
          "method", 
          "protocol", 
          "applications", 
          "neighborhood", 
          "lanes", 
          "precision", 
          "system", 
          "error", 
          "detector", 
          "point", 
          "buildings", 
          "sidewalks", 
          "data", 
          "class", 
          "accurate protocol", 
          "variety", 
          "bicycle", 
          "results", 
          "streets", 
          "area", 
          "bench", 
          "mode", 
          "parterre", 
          "pesticide waste", 
          "rate", 
          "street trees", 
          "index", 
          "side", 
          "years", 
          "environmental pollution", 
          "light", 
          "waste", 
          "signs", 
          "orchards", 
          "pollution", 
          "presence", 
          "spraying method", 
          "Bush", 
          "turf areas", 
          "crowns", 
          "problem", 
          "paper", 
          "approach"
        ], 
        "name": "Street Tree Crown Detection with Mobile Laser Scanning Data Using a Grid Index and Local Features", 
        "pagination": "305-317", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1148908776"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s41064-022-00208-w"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s41064-022-00208-w", 
          "https://app.dimensions.ai/details/publication/pub.1148908776"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-12-01T06:44", 
        "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_938.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s41064-022-00208-w"
      }
    ]
     

    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/s41064-022-00208-w'

    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/s41064-022-00208-w'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s41064-022-00208-w'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s41064-022-00208-w'


     

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

    180 TRIPLES      21 PREDICATES      123 URIs      114 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s41064-022-00208-w schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N8662871a551f43c698e5b97785d42c59
    4 schema:citation sg:pub.10.1023/b:visi.0000013087.49260.fb
    5 schema:datePublished 2022-06-23
    6 schema:datePublishedReg 2022-06-23
    7 schema:description In recent years, targeted spraying technology, which was proposed to solve the problems of pesticide waste and environmental pollution caused by traditional spraying methods, has been successfully applied in orchards. In street scenes with a variety of object classes, it is challenging to detect tree crowns, which limits the application of targeted spraying for street trees. Two-dimensional (2D) light detection and ranging (LiDAR) sensors have been widely used in targeted spraying to monitor the presence of tree crowns. Considering a mobile laser scanning (MLS) system with a single 2D LiDAR sensor in push-broom mode, this paper proposes a pointwise method for street tree crown detection from MLS point clouds by using a grid index and local features. First, an efficient two-level neighbourhood search method is proposed to obtain the spherical neighbourhood of a single point by using the grid index of the MLS point clouds. Subsequently, a set of local statistical features, including width features, depth features, elevation features, intensity features, echo number features, dimensionality features and a density feature, are extracted from the spherical neighbourhood. Finally, a supervised learning algorithm called boosting is used to automatically fuse these features and generate a pointwise tree crown detector from a labelled training set. An MLS point cloud with 15,134,000 points is captured from both sides of a 136.5 m street, and the cloud contains buildings, lanes, sidewalks, benches, street lights, bicycles, traffic signs, grids, trees, bushes, turf areas, parterres, and pedestrians. The estimated Bayesian errors of single-feature approaches range from 6.23 to 36.09%, and the error rate of the tree crown detector composed of all features is less than 0.73%, with a recall rate of over 98.30% and a precision of over 99.13%. The experimental results show that the proposed method can provide an online, fine and accurate protocol for targeted spraying.
    8 schema:genre article
    9 schema:isAccessibleForFree false
    10 schema:isPartOf N1dac21d936b14602a27f6ec6692d50dc
    11 N64d5188222484a26b7c151ca40e71bc0
    12 sg:journal.1320463
    13 schema:keywords Bayesian error
    14 Bush
    15 LiDAR sensors
    16 MLS point clouds
    17 accurate protocol
    18 algorithm
    19 applications
    20 approach
    21 area
    22 bench
    23 bicycle
    24 buildings
    25 class
    26 cloud
    27 crown detection
    28 crowns
    29 data
    30 density features
    31 depth features
    32 detection
    33 detector
    34 dimensionality features
    35 elevation features
    36 environmental pollution
    37 error
    38 error rate
    39 experimental results
    40 features
    41 grid
    42 grid index
    43 index
    44 intensity features
    45 lanes
    46 laser scanning data
    47 laser scanning system
    48 learning algorithm
    49 light
    50 light detection
    51 local features
    52 local statistical features
    53 method
    54 mobile laser scanning data
    55 mobile laser scanning system
    56 mode
    57 neighborhood
    58 neighborhood search method
    59 number features
    60 object classes
    61 orchards
    62 paper
    63 parterre
    64 pedestrians
    65 pesticide waste
    66 point
    67 point clouds
    68 pointwise method
    69 pollution
    70 precision
    71 presence
    72 problem
    73 protocol
    74 push-broom mode
    75 rate
    76 recall rate
    77 recent years
    78 results
    79 scanning data
    80 scanning system
    81 scene
    82 search method
    83 sensors
    84 set
    85 side
    86 sidewalks
    87 signs
    88 single point
    89 single-feature approach
    90 spherical neighborhood
    91 spraying method
    92 statistical features
    93 street lights
    94 street scenes
    95 street trees
    96 streets
    97 supervised learning algorithm
    98 system
    99 technology
    100 traffic signs
    101 training set
    102 tree crown detection
    103 tree crowns
    104 trees
    105 turf areas
    106 two-dimensional light detection
    107 variety
    108 waste
    109 width feature
    110 years
    111 schema:name Street Tree Crown Detection with Mobile Laser Scanning Data Using a Grid Index and Local Features
    112 schema:pagination 305-317
    113 schema:productId N88d8d2142271475ba1f3b877e8a4ffe0
    114 Na08ee00ab50b4034b08be5a777cf0c2c
    115 schema:sameAs https://app.dimensions.ai/details/publication/pub.1148908776
    116 https://doi.org/10.1007/s41064-022-00208-w
    117 schema:sdDatePublished 2022-12-01T06:44
    118 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    119 schema:sdPublisher N5de1642209a54479bdc0245ecb8b75ad
    120 schema:url https://doi.org/10.1007/s41064-022-00208-w
    121 sgo:license sg:explorer/license/
    122 sgo:sdDataset articles
    123 rdf:type schema:ScholarlyArticle
    124 N1dac21d936b14602a27f6ec6692d50dc schema:volumeNumber 90
    125 rdf:type schema:PublicationVolume
    126 N2b141bed77d64c9baa9adbd0d16779fb rdf:first N7df5462d0f3a495082c82b1c09a1ee3a
    127 rdf:rest N9ed2fef405a54377a259bf294d00de9e
    128 N5de1642209a54479bdc0245ecb8b75ad schema:name Springer Nature - SN SciGraph project
    129 rdf:type schema:Organization
    130 N64d5188222484a26b7c151ca40e71bc0 schema:issueNumber 3
    131 rdf:type schema:PublicationIssue
    132 N6b801976c1cf487e9bd5a548d2655274 schema:affiliation grid-institutes:grid.410625.4
    133 schema:familyName Liu
    134 schema:givenName Xu
    135 rdf:type schema:Person
    136 N7df5462d0f3a495082c82b1c09a1ee3a schema:affiliation grid-institutes:grid.410625.4
    137 schema:familyName Li
    138 schema:givenName Xiangcheng
    139 rdf:type schema:Person
    140 N8662871a551f43c698e5b97785d42c59 rdf:first sg:person.016662612020.83
    141 rdf:rest N2b141bed77d64c9baa9adbd0d16779fb
    142 N88d8d2142271475ba1f3b877e8a4ffe0 schema:name dimensions_id
    143 schema:value pub.1148908776
    144 rdf:type schema:PropertyValue
    145 N9ed2fef405a54377a259bf294d00de9e rdf:first sg:person.016136145541.23
    146 rdf:rest Na9fbac001b5e4f6f8bd911e45605334e
    147 Na08ee00ab50b4034b08be5a777cf0c2c schema:name doi
    148 schema:value 10.1007/s41064-022-00208-w
    149 rdf:type schema:PropertyValue
    150 Na9fbac001b5e4f6f8bd911e45605334e rdf:first N6b801976c1cf487e9bd5a548d2655274
    151 rdf:rest rdf:nil
    152 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    153 schema:name Information and Computing Sciences
    154 rdf:type schema:DefinedTerm
    155 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    156 schema:name Artificial Intelligence and Image Processing
    157 rdf:type schema:DefinedTerm
    158 sg:grant.8914396 http://pending.schema.org/fundedItem sg:pub.10.1007/s41064-022-00208-w
    159 rdf:type schema:MonetaryGrant
    160 sg:journal.1320463 schema:issn 2512-2789
    161 2512-2819
    162 schema:name PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science
    163 schema:publisher Springer Nature
    164 rdf:type schema:Periodical
    165 sg:person.016136145541.23 schema:affiliation grid-institutes:grid.410625.4
    166 schema:familyName Tong
    167 schema:givenName Yuekai
    168 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016136145541.23
    169 rdf:type schema:Person
    170 sg:person.016662612020.83 schema:affiliation grid-institutes:grid.410625.4
    171 schema:familyName Li
    172 schema:givenName Qiujie
    173 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016662612020.83
    174 rdf:type schema:Person
    175 sg:pub.10.1023/b:visi.0000013087.49260.fb schema:sameAs https://app.dimensions.ai/details/publication/pub.1001944608
    176 https://doi.org/10.1023/b:visi.0000013087.49260.fb
    177 rdf:type schema:CreativeWork
    178 grid-institutes:grid.410625.4 schema:alternateName Nanjing Forestry University, Nanjing, China
    179 schema:name Nanjing Forestry University, Nanjing, China
    180 rdf:type schema:Organization
     




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


    ...