A Model-based Method for Autonomous Land Vehicle Navigation
Identifieur interne : 00D912 ( Main/Curation ); précédent : 00D911; suivant : 00D913A Model-based Method for Autonomous Land Vehicle Navigation
Auteurs : C. WuSource :
English descriptors
- KwdEn :
Abstract
A model-based method for reconstructing road edges in 3D space and determining the lateral offset position and the deflected angle of the camera with respect to the road edges from a single image is described. The road edges are modelled as a set of segments which consists of parallel straight lines and concentric circles in 3d space. Each segment is of same orientation. The edge image is then modelled as a set of straight lines and conic curves in image plane. The road is assumed to be a set of flat plane segments. The tilt of the camera and the road width are known. Given a point on one road image edge, the corresponding matching point on the other road image edge can be found for each segment by the methods described in this report. The reconstruction of the road edge in 3D space is straighforward after finding the matching points and by considering that the road width is known. The method is adapted for the flat road even though there is more rapid turn on the road. The method can also be fitted to unflat road. The reconstructed 3D world road finally can be refined by smoothing processing.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000B29
- to stream Crin, to step Curation: Pour aller vers cette notice dans l'étape Curation :000B29
- to stream Crin, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :003989
- to stream Main, to step Merge: Pour aller vers cette notice dans l'étape Curation :00E190
Links to Exploration step
CRIN:wu91aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="255">A Model-based Method for Autonomous Land Vehicle Navigation</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:wu91a</idno>
<date when="1991" year="1991">1991</date>
<idno type="wicri:Area/Crin/Corpus">000B29</idno>
<idno type="wicri:Area/Crin/Curation">000B29</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">000B29</idno>
<idno type="wicri:Area/Crin/Checkpoint">003989</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">003989</idno>
<idno type="wicri:Area/Main/Merge">00E190</idno>
<idno type="wicri:Area/Main/Curation">00D912</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">A Model-based Method for Autonomous Land Vehicle Navigation</title>
<author><name sortKey="Wu, C" sort="Wu, C" uniqKey="Wu C" first="C." last="Wu">C. Wu</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>ALV</term>
<term>backprojection</term>
<term>matching point</term>
<term>model-based</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3115">A model-based method for reconstructing road edges in 3D space and determining the lateral offset position and the deflected angle of the camera with respect to the road edges from a single image is described. The road edges are modelled as a set of segments which consists of parallel straight lines and concentric circles in 3d space. Each segment is of same orientation. The edge image is then modelled as a set of straight lines and conic curves in image plane. The road is assumed to be a set of flat plane segments. The tilt of the camera and the road width are known. Given a point on one road image edge, the corresponding matching point on the other road image edge can be found for each segment by the methods described in this report. The reconstruction of the road edge in 3D space is straighforward after finding the matching points and by considering that the road width is known. The method is adapted for the flat road even though there is more rapid turn on the road. The method can also be fitted to unflat road. The reconstructed 3D world road finally can be refined by smoothing processing.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00D912 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Curation/biblio.hfd -nk 00D912 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Curation |type= RBID |clé= CRIN:wu91a |texte= A Model-based Method for Autonomous Land Vehicle Navigation }}
This area was generated with Dilib version V0.6.33. |