Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2016-08-27

AUTHORS

Jonas Uhrig , Marius Cordts , Uwe Franke , Thomas Brox

ABSTRACT

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling. More... »

PAGES

14-25

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-45886-1_2

DOI

http://dx.doi.org/10.1007/978-3-319-45886-1_2

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1019425063


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": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Daimler AG R&D, Stuttgart, Germany", 
            "University of Freiburg, Freiburg im Breisgau, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Uhrig", 
        "givenName": "Jonas", 
        "id": "sg:person.011200663521.38", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011200663521.38"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "TU Darmstadt, Darmstadt, Germany", 
          "id": "http://www.grid.ac/institutes/grid.6546.1", 
          "name": [
            "Daimler AG R&D, Stuttgart, Germany", 
            "TU Darmstadt, Darmstadt, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cordts", 
        "givenName": "Marius", 
        "id": "sg:person.010525522476.88", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010525522476.88"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Daimler AG R&D, Stuttgart, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5433.1", 
          "name": [
            "Daimler AG R&D, Stuttgart, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Franke", 
        "givenName": "Uwe", 
        "id": "sg:person.015101374255.11", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015101374255.11"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2016-08-27", 
    "datePublishedReg": "2016-08-27", 
    "description": "Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel\u2019s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.", 
    "editor": [
      {
        "familyName": "Rosenhahn", 
        "givenName": "Bodo", 
        "type": "Person"
      }, 
      {
        "familyName": "Andres", 
        "givenName": "Bjoern", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-45886-1_2", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-45885-4", 
        "978-3-319-45886-1"
      ], 
      "name": "Pattern Recognition", 
      "type": "Book"
    }, 
    "keywords": [
      "convolutional neural network", 
      "semantic labeling", 
      "low-level computer vision techniques", 
      "pixel-level semantic labeling", 
      "computer vision techniques", 
      "multi-task architecture", 
      "art instance segmentation", 
      "dataset KITTI", 
      "vision techniques", 
      "semantic labels", 
      "instance segmentation", 
      "convolutional network", 
      "monocular images", 
      "depth layering", 
      "neural network", 
      "graphical models", 
      "pixel direction", 
      "large margin", 
      "individual instances", 
      "recent approaches", 
      "network", 
      "encoding", 
      "KITTI", 
      "segmentation", 
      "architecture", 
      "absolute distance", 
      "cityscape", 
      "images", 
      "labels", 
      "instances", 
      "technique", 
      "work", 
      "model", 
      "method", 
      "labeling", 
      "direction", 
      "distance", 
      "state", 
      "layering", 
      "center", 
      "depth", 
      "margin", 
      "approach"
    ], 
    "name": "Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling", 
    "pagination": "14-25", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1019425063"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-45886-1_2"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-45886-1_2", 
      "https://app.dimensions.ai/details/publication/pub.1019425063"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-09-02T16:12", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/chapter/chapter_239.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-45886-1_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.10.1007/978-3-319-45886-1_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.10.1007/978-3-319-45886-1_2'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-45886-1_2'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-45886-1_2'


 

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

136 TRIPLES      22 PREDICATES      67 URIs      60 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-45886-1_2 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N0c9baaf5ca5a45369bd58a9af2001816
4 schema:datePublished 2016-08-27
5 schema:datePublishedReg 2016-08-27
6 schema:description Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.
7 schema:editor N95e2e321ba7842d697eb327ef7ca3a4d
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N0dc4f835129049c19f0c8d13cce24589
11 schema:keywords KITTI
12 absolute distance
13 approach
14 architecture
15 art instance segmentation
16 center
17 cityscape
18 computer vision techniques
19 convolutional network
20 convolutional neural network
21 dataset KITTI
22 depth
23 depth layering
24 direction
25 distance
26 encoding
27 graphical models
28 images
29 individual instances
30 instance segmentation
31 instances
32 labeling
33 labels
34 large margin
35 layering
36 low-level computer vision techniques
37 margin
38 method
39 model
40 monocular images
41 multi-task architecture
42 network
43 neural network
44 pixel direction
45 pixel-level semantic labeling
46 recent approaches
47 segmentation
48 semantic labeling
49 semantic labels
50 state
51 technique
52 vision techniques
53 work
54 schema:name Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling
55 schema:pagination 14-25
56 schema:productId Nd6822da30a3d4648953760d0e9f702e6
57 Nead36fdc619d44159151db25a04d3c13
58 schema:publisher Ncccf8cbf741540598c28d7549a29728d
59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019425063
60 https://doi.org/10.1007/978-3-319-45886-1_2
61 schema:sdDatePublished 2022-09-02T16:12
62 schema:sdLicense https://scigraph.springernature.com/explorer/license/
63 schema:sdPublisher Ncf74e3c94c58474591797fdeb6ae8609
64 schema:url https://doi.org/10.1007/978-3-319-45886-1_2
65 sgo:license sg:explorer/license/
66 sgo:sdDataset chapters
67 rdf:type schema:Chapter
68 N0c9baaf5ca5a45369bd58a9af2001816 rdf:first sg:person.011200663521.38
69 rdf:rest Na5ff5f91fc384c54835b5614e2a9cb1b
70 N0dc4f835129049c19f0c8d13cce24589 schema:isbn 978-3-319-45885-4
71 978-3-319-45886-1
72 schema:name Pattern Recognition
73 rdf:type schema:Book
74 N10aafcb3900c4e89b6352d6e35241f30 schema:familyName Andres
75 schema:givenName Bjoern
76 rdf:type schema:Person
77 N197f14d31935447f9d24fe3ea5bdc2d9 rdf:first sg:person.015101374255.11
78 rdf:rest N491c4a31518e4ef29c42a585ca2c2083
79 N491c4a31518e4ef29c42a585ca2c2083 rdf:first sg:person.012443225372.65
80 rdf:rest rdf:nil
81 N6841cab2aa7840a09b48905b3a399348 schema:familyName Rosenhahn
82 schema:givenName Bodo
83 rdf:type schema:Person
84 N95e2e321ba7842d697eb327ef7ca3a4d rdf:first N6841cab2aa7840a09b48905b3a399348
85 rdf:rest Nd0ba2e1c01f5403b9b49f7253737b342
86 Na5ff5f91fc384c54835b5614e2a9cb1b rdf:first sg:person.010525522476.88
87 rdf:rest N197f14d31935447f9d24fe3ea5bdc2d9
88 Ncccf8cbf741540598c28d7549a29728d schema:name Springer Nature
89 rdf:type schema:Organisation
90 Ncf74e3c94c58474591797fdeb6ae8609 schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 Nd0ba2e1c01f5403b9b49f7253737b342 rdf:first N10aafcb3900c4e89b6352d6e35241f30
93 rdf:rest rdf:nil
94 Nd6822da30a3d4648953760d0e9f702e6 schema:name dimensions_id
95 schema:value pub.1019425063
96 rdf:type schema:PropertyValue
97 Nead36fdc619d44159151db25a04d3c13 schema:name doi
98 schema:value 10.1007/978-3-319-45886-1_2
99 rdf:type schema:PropertyValue
100 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
101 schema:name Information and Computing Sciences
102 rdf:type schema:DefinedTerm
103 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
104 schema:name Artificial Intelligence and Image Processing
105 rdf:type schema:DefinedTerm
106 sg:person.010525522476.88 schema:affiliation grid-institutes:grid.6546.1
107 schema:familyName Cordts
108 schema:givenName Marius
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010525522476.88
110 rdf:type schema:Person
111 sg:person.011200663521.38 schema:affiliation grid-institutes:grid.5963.9
112 schema:familyName Uhrig
113 schema:givenName Jonas
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011200663521.38
115 rdf:type schema:Person
116 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
117 schema:familyName Brox
118 schema:givenName Thomas
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
120 rdf:type schema:Person
121 sg:person.015101374255.11 schema:affiliation grid-institutes:grid.5433.1
122 schema:familyName Franke
123 schema:givenName Uwe
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015101374255.11
125 rdf:type schema:Person
126 grid-institutes:grid.5433.1 schema:alternateName Daimler AG R&D, Stuttgart, Germany
127 schema:name Daimler AG R&D, Stuttgart, Germany
128 rdf:type schema:Organization
129 grid-institutes:grid.5963.9 schema:alternateName University of Freiburg, Freiburg im Breisgau, Germany
130 schema:name Daimler AG R&D, Stuttgart, Germany
131 University of Freiburg, Freiburg im Breisgau, Germany
132 rdf:type schema:Organization
133 grid-institutes:grid.6546.1 schema:alternateName TU Darmstadt, Darmstadt, Germany
134 schema:name Daimler AG R&D, Stuttgart, Germany
135 TU Darmstadt, Darmstadt, Germany
136 rdf:type schema:Organization
 




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


...