<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1665-6423</journal-id>
<journal-title><![CDATA[Journal of applied research and technology]]></journal-title>
<abbrev-journal-title><![CDATA[J. appl. res. technol]]></abbrev-journal-title>
<issn>1665-6423</issn>
<publisher>
<publisher-name><![CDATA[Universidad Nacional Autónoma de México, Instituto de Ciencias Aplicadas y Tecnología]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1665-64232021000600644</article-id>
<article-id pub-id-type="doi">10.22201/icat.24486736e.2021.19.6.991</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Dense monocular simultaneous localization and mapping by direct surfel optimization]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Trabes]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
<xref ref-type="aff" rid="Aaf"/>
<xref ref-type="aff" rid="A a"/>
<xref ref-type="aff" rid="A3"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Avila]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
<xref ref-type="aff" rid="Aaf"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gazzano]]></surname>
<given-names><![CDATA[J. D.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Sosa Paez]]></surname>
<given-names><![CDATA[C. F.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Nacional de San Luis Facultad de Ciencias Físico Matemáticas y Naturales Departamento de Electrónica]]></institution>
<addr-line><![CDATA[San Luis ]]></addr-line>
<country>Argentina</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad Nacional de San Luis Facultad de Ingeniería y Ciencias Agropecuarias Departamento de Ingeniería]]></institution>
<addr-line><![CDATA[San Luis ]]></addr-line>
<country>Argentina</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,UNSL Laboratorio de Investigación y Desarrollo en Inteligencia Computacional ]]></institution>
<addr-line><![CDATA[San Luis ]]></addr-line>
<country>Argentina</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>00</month>
<year>2021</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>00</month>
<year>2021</year>
</pub-date>
<volume>19</volume>
<numero>6</numero>
<fpage>644</fpage>
<lpage>652</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1665-64232021000600644&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1665-64232021000600644&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1665-64232021000600644&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract This work presents a novel approach for monocular dense simultaneous localization and mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters the position and normal. These parameters are directly estimated from the raw camera pixels measurements using a Gauss-Newton iterative process. The representation of the surface as a group of surfels has many advantages. First, it allows recovering robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. What is more, new surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the use of GPU devices and achieving real-time processing. The method was tested on benchmark datasets, showing both its depth and normal estimation capacity, and its quality to recover the original scene. Results presented in this work showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Depth estimation]]></kwd>
<kwd lng="en"><![CDATA[visual odometry]]></kwd>
<kwd lng="en"><![CDATA[SLAM]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cadena]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Carlone]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Carrillo]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Latif]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Scaramuzza]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Neira]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Leonard]]></surname>
<given-names><![CDATA[J. J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age]]></article-title>
<source><![CDATA[IEEE Transactions on robotics]]></source>
<year>2016</year>
<volume>32</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>1309-32</page-range></nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Engel]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Koltun]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Cremers]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Direct sparse odometry]]></article-title>
<source><![CDATA[IEEE transactions on pattern analysis and machine intelligence]]></source>
<year>2017</year>
<volume>40</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>611-25</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Engel]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Schöps]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Cremers]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[LSD-SLAM: Large-scale direct monocular SLAM]]></source>
<year>2014</year>
<conf-name><![CDATA[ European conference on computer vision]]></conf-name>
<conf-loc> </conf-loc>
<page-range>834-49</page-range><publisher-name><![CDATA[Springer, Cham.]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Goodfellow]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Courville]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Deep learning]]></source>
<year>2016</year>
<publisher-name><![CDATA[MIT Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Grisetti]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[K &#776;ummerle]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Stachniss]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Burgard]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A tutorial on graph-based slam]]></article-title>
<source><![CDATA[IEEE Intelligent Transportation Systems Magazine]]></source>
<year>2010</year>
<volume>2</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>31-43</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hosni]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Rhemann]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Bleyer]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Rother]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Gelautz]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Fast cost-volume filtering for visual correspondence and beyond]]></article-title>
<source><![CDATA[IEEE transactions on pattern analysis and machine intelligence]]></source>
<year>2013</year>
<volume>35</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>504-11</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lemus]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Diaz]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Gutierrez]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Rodriguez]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Escobar]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Slam-R algorithm of simultaneous localization and mapping using RFID for obstacle location and recognition]]></article-title>
<source><![CDATA[Journal of applied research and technology]]></source>
<year>2014</year>
<volume>12</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>551-9</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mur-Artal]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Montiel]]></surname>
<given-names><![CDATA[J. M. M.]]></given-names>
</name>
<name>
<surname><![CDATA[Tard &#769;os]]></surname>
<given-names><![CDATA[J. D.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[ORB-SLAM: A versatile and accurate monocular slam system]]></article-title>
<source><![CDATA[IEEE Transactions on robotics]]></source>
<year>2015</year>
<volume>31</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>1147-63</page-range></nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Newcombe]]></surname>
<given-names><![CDATA[R. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Lovegrove]]></surname>
<given-names><![CDATA[S. J.]]></given-names>
</name>
<name>
<surname><![CDATA[Davison]]></surname>
<given-names><![CDATA[A. J.]]></given-names>
</name>
</person-group>
<source><![CDATA[DTAM: Dense tracking and mapping in real-time]]></source>
<year>2011</year>
<conf-name><![CDATA[ 2011 international conference on computer vision]]></conf-name>
<conf-loc> </conf-loc>
<page-range>2320-7</page-range></nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pizzoli]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Forster]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Scaramuzza]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[REMODE: Probabilistic, monocular dense reconstruction in real time]]></source>
<year>2014</year>
<conf-name><![CDATA[ 2014 IEEE International Conference on Robotics and Automation (ICRA)]]></conf-name>
<conf-loc> </conf-loc>
<page-range>2609-16</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="">
<collab>TUM Department of Informatics</collab>
<source><![CDATA[LSD-SLAM: Large-Scale Direct Monocular SLAM]]></source>
<year>2017</year>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Shen]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Real-time scalable dense surfel mapping]]></source>
<year>2019</year>
<conf-name><![CDATA[ 2019 International Conference on Robotics and Automation (ICRA)]]></conf-name>
<conf-loc> </conf-loc>
<page-range>6919-25</page-range></nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Whelan]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Salas-Moreno]]></surname>
<given-names><![CDATA[R. F.]]></given-names>
</name>
<name>
<surname><![CDATA[Glocker]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Davison]]></surname>
<given-names><![CDATA[A. J.]]></given-names>
</name>
<name>
<surname><![CDATA[Leutenegger]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Elasticfusion: Real-time dense slam and light source estimation]]></article-title>
<source><![CDATA[The International Journal of Robotics Research]]></source>
<year>2016</year>
<volume>35</volume>
<numero>14</numero>
<issue>14</issue>
<page-range>1697-716</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yan]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Ye]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Ren]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Dense visual slam with probabilistic surfel map]]></article-title>
<source><![CDATA[IEEE Transactions on Visualization and Computer Graphics]]></source>
<year>2017</year>
<volume>23</volume>
<numero>11</numero>
<issue>11</issue>
<page-range>2389-98</page-range></nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zienkiewicz]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Tsiotsios]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Davison]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Leutenegger]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Monocular, real-time surface reconstruction using dynamic level of detail]]></source>
<year>2016</year>
<conf-name><![CDATA[ 2016 Fourth International Conference on 3D Vision (3DV)]]></conf-name>
<conf-loc> </conf-loc>
<page-range>37-46</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
